release 2013.09.24.1

This reverts commit 0fd49457f5.

It seems that the redesign was temporary.

.gitignore

@@ -17,4 +17,11 @@ youtube-dl.tar.gz
 .coverage
 cover/
 updates_key.pem
-*.egg-info
+*.egg-info
+*.srt
+*.sbv
+*.vtt
+*.flv
+*.mp4
+*.part
+test/testdata

.travis.yml

@@ -9,6 +9,7 @@ notifications:
     - filippo.valsorda@gmail.com
     - phihag@phihag.de
     - jaime.marquinez.ferrandiz+travis@gmail.com
+    - yasoob.khld@gmail.com
 #  irc:
 #    channels:
 #      - "irc.freenode.org#youtube-dl"

README.md

@@ -16,8 +16,11 @@ which means you can modify it, redistribute it or use it however you like.
 # OPTIONS
     -h, --help                 print this help text and exit
     --version                  print program version and exit
-    -U, --update               update this program to latest version
-    -i, --ignore-errors        continue on download errors
+    -U, --update               update this program to latest version. Make sure
+                               that you have sufficient permissions (run with
+                               sudo if needed)
+    -i, --ignore-errors        continue on download errors, for example to to
+                               skip unavailable videos in a playlist
     --dump-user-agent          display the current browser identification
     --user-agent UA            specify a custom user agent
     --referer REF              specify a custom referer, use if the video access
@@ -27,6 +30,10 @@ which means you can modify it, redistribute it or use it however you like.
     --extractor-descriptions   Output descriptions of all supported extractors
     --proxy URL                Use the specified HTTP/HTTPS proxy
     --no-check-certificate     Suppress HTTPS certificate validation.
+    --cache-dir None           Location in the filesystem where youtube-dl can
+                               store downloaded information permanently.
+                               ~/.youtube-dl/cache by default
+    --no-cache-dir             Disable filesystem caching
 
 ## Video Selection:
     --playlist-start NUMBER    playlist video to start at (default is 1)
@@ -111,25 +118,26 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Video Format Options:
     -f, --format FORMAT        video format code, specifiy the order of
-                               preference using slashes: "-f 22/17/18"
+                               preference using slashes: "-f 22/17/18". "-f mp4"
+                               and "-f flv" are also supported
     --all-formats              download all available video formats
     --prefer-free-formats      prefer free video formats unless a specific one
                                is requested
     --max-quality FORMAT       highest quality format to download
     -F, --list-formats         list all available formats (currently youtube
                                only)
-    --write-sub                write subtitle file (currently youtube only)
-    --write-auto-sub           write automatic subtitle file (currently youtube
-                               only)
-    --only-sub                 [deprecated] alias of --skip-download
+
+## Subtitle Options:
+    --write-sub                write subtitle file
+    --write-auto-sub           write automatic subtitle file (youtube only)
     --all-subs                 downloads all the available subtitles of the
-                               video (currently youtube only)
+                               video
     --list-subs                lists all available subtitles for the video
-                               (currently youtube only)
-    --sub-format FORMAT        subtitle format [srt/sbv/vtt] (default=srt)
-                               (currently youtube only)
-    --sub-lang LANG            language of the subtitles to download (optional)
-                               use IETF language tags like 'en'
+    --sub-format FORMAT        subtitle format (default=srt) ([sbv/vtt] youtube
+                               only)
+    --sub-lang LANGS           languages of the subtitles to download (optional)
+                               separated by commas, use IETF language tags like
+                               'en,pt'
 
 ## Authentication Options:
     -u, --username USERNAME    account username
@@ -151,6 +159,8 @@ which means you can modify it, redistribute it or use it however you like.
                                processing; the video is erased by default
     --no-post-overwrites       do not overwrite post-processed files; the post-
                                processed files are overwritten by default
+    --embed-subs               embed subtitles in the video (only for mp4
+                               videos)
 
 # CONFIGURATION
 

devscripts/bash-completion.in

@@ -4,8 +4,12 @@ __youtube-dl()
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
     opts="{{flags}}"
+    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater"
 
-    if [[ ${cur} == * ]] ; then
+    if [[ ${cur} =~ : ]]; then
+        COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )
+        return 0
+    elif [[ ${cur} == * ]] ; then
         COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
         return 0
     fi

devscripts/buildserver.py

@@ -0,0 +1,405 @@
+#!/usr/bin/python3
+
+from http.server import HTTPServer, BaseHTTPRequestHandler
+from socketserver import ThreadingMixIn
+import argparse
+import ctypes
+import functools
+import sys
+import threading
+import traceback
+import os.path
+
+
+class BuildHTTPServer(ThreadingMixIn, HTTPServer):
+    allow_reuse_address = True
+
+
+advapi32 = ctypes.windll.advapi32
+
+SC_MANAGER_ALL_ACCESS = 0xf003f
+SC_MANAGER_CREATE_SERVICE = 0x02
+SERVICE_WIN32_OWN_PROCESS = 0x10
+SERVICE_AUTO_START = 0x2
+SERVICE_ERROR_NORMAL = 0x1
+DELETE = 0x00010000
+SERVICE_STATUS_START_PENDING = 0x00000002
+SERVICE_STATUS_RUNNING = 0x00000004
+SERVICE_ACCEPT_STOP = 0x1
+
+SVCNAME = 'youtubedl_builder'
+
+LPTSTR = ctypes.c_wchar_p
+START_CALLBACK = ctypes.WINFUNCTYPE(None, ctypes.c_int, ctypes.POINTER(LPTSTR))
+
+
+class SERVICE_TABLE_ENTRY(ctypes.Structure):
+    _fields_ = [
+        ('lpServiceName', LPTSTR),
+        ('lpServiceProc', START_CALLBACK)
+    ]
+
+
+HandlerEx = ctypes.WINFUNCTYPE(
+    ctypes.c_int,     # return
+    ctypes.c_int,     # dwControl
+    ctypes.c_int,     # dwEventType
+    ctypes.c_void_p,  # lpEventData,
+    ctypes.c_void_p,  # lpContext,
+)
+
+
+def _ctypes_array(c_type, py_array):
+    ar = (c_type * len(py_array))()
+    ar[:] = py_array
+    return ar
+
+
+def win_OpenSCManager():
+    res = advapi32.OpenSCManagerW(None, None, SC_MANAGER_ALL_ACCESS)
+    if not res:
+        raise Exception('Opening service manager failed - '
+                        'are you running this as administrator?')
+    return res
+
+
+def win_install_service(service_name, cmdline):
+    manager = win_OpenSCManager()
+    try:
+        h = advapi32.CreateServiceW(
+            manager, service_name, None,
+            SC_MANAGER_CREATE_SERVICE, SERVICE_WIN32_OWN_PROCESS,
+            SERVICE_AUTO_START, SERVICE_ERROR_NORMAL,
+            cmdline, None, None, None, None, None)
+        if not h:
+            raise OSError('Service creation failed: %s' % ctypes.FormatError())
+
+        advapi32.CloseServiceHandle(h)
+    finally:
+        advapi32.CloseServiceHandle(manager)
+
+
+def win_uninstall_service(service_name):
+    manager = win_OpenSCManager()
+    try:
+        h = advapi32.OpenServiceW(manager, service_name, DELETE)
+        if not h:
+            raise OSError('Could not find service %s: %s' % (
+                service_name, ctypes.FormatError()))
+
+        try:
+            if not advapi32.DeleteService(h):
+                raise OSError('Deletion failed: %s' % ctypes.FormatError())
+        finally:
+            advapi32.CloseServiceHandle(h)
+    finally:
+        advapi32.CloseServiceHandle(manager)
+
+
+def win_service_report_event(service_name, msg, is_error=True):
+    with open('C:/sshkeys/log', 'a', encoding='utf-8') as f:
+        f.write(msg + '\n')
+
+    event_log = advapi32.RegisterEventSourceW(None, service_name)
+    if not event_log:
+        raise OSError('Could not report event: %s' % ctypes.FormatError())
+
+    try:
+        type_id = 0x0001 if is_error else 0x0004
+        event_id = 0xc0000000 if is_error else 0x40000000
+        lines = _ctypes_array(LPTSTR, [msg])
+
+        if not advapi32.ReportEventW(
+                event_log, type_id, 0, event_id, None, len(lines), 0,
+                lines, None):
+            raise OSError('Event reporting failed: %s' % ctypes.FormatError())
+    finally:
+        advapi32.DeregisterEventSource(event_log)
+
+
+def win_service_handler(stop_event, *args):
+    try:
+        raise ValueError('Handler called with args ' + repr(args))
+        TODO
+    except Exception as e:
+        tb = traceback.format_exc()
+        msg = str(e) + '\n' + tb
+        win_service_report_event(service_name, msg, is_error=True)
+        raise
+
+
+def win_service_set_status(handle, status_code):
+    svcStatus = SERVICE_STATUS()
+    svcStatus.dwServiceType = SERVICE_WIN32_OWN_PROCESS
+    svcStatus.dwCurrentState = status_code
+    svcStatus.dwControlsAccepted = SERVICE_ACCEPT_STOP
+
+    svcStatus.dwServiceSpecificExitCode = 0
+
+    if not advapi32.SetServiceStatus(handle, ctypes.byref(svcStatus)):
+        raise OSError('SetServiceStatus failed: %r' % ctypes.FormatError())
+
+
+def win_service_main(service_name, real_main, argc, argv_raw):
+    try:
+        #args = [argv_raw[i].value for i in range(argc)]
+        stop_event = threading.Event()
+        handler = HandlerEx(functools.partial(stop_event, win_service_handler))
+        h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None)
+        if not h:
+            raise OSError('Handler registration failed: %s' %
+                          ctypes.FormatError())
+
+        TODO
+    except Exception as e:
+        tb = traceback.format_exc()
+        msg = str(e) + '\n' + tb
+        win_service_report_event(service_name, msg, is_error=True)
+        raise
+
+
+def win_service_start(service_name, real_main):
+    try:
+        cb = START_CALLBACK(
+            functools.partial(win_service_main, service_name, real_main))
+        dispatch_table = _ctypes_array(SERVICE_TABLE_ENTRY, [
+            SERVICE_TABLE_ENTRY(
+                service_name,
+                cb
+            ),
+            SERVICE_TABLE_ENTRY(None, ctypes.cast(None, START_CALLBACK))
+        ])
+
+        if not advapi32.StartServiceCtrlDispatcherW(dispatch_table):
+            raise OSError('ctypes start failed: %s' % ctypes.FormatError())
+    except Exception as e:
+        tb = traceback.format_exc()
+        msg = str(e) + '\n' + tb
+        win_service_report_event(service_name, msg, is_error=True)
+        raise
+
+
+def main(args=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i', '--install',
+                        action='store_const', dest='action', const='install',
+                        help='Launch at Windows startup')
+    parser.add_argument('-u', '--uninstall',
+                        action='store_const', dest='action', const='uninstall',
+                        help='Remove Windows service')
+    parser.add_argument('-s', '--service',
+                        action='store_const', dest='action', const='service',
+                        help='Run as a Windows service')
+    parser.add_argument('-b', '--bind', metavar='<host:port>',
+                        action='store', default='localhost:8142',
+                        help='Bind to host:port (default %default)')
+    options = parser.parse_args(args=args)
+
+    if options.action == 'install':
+        fn = os.path.abspath(__file__).replace('v:', '\\\\vboxsrv\\vbox')
+        cmdline = '%s %s -s -b %s' % (sys.executable, fn, options.bind)
+        win_install_service(SVCNAME, cmdline)
+        return
+
+    if options.action == 'uninstall':
+        win_uninstall_service(SVCNAME)
+        return
+
+    if options.action == 'service':
+        win_service_start(SVCNAME, main)
+        return
+
+    host, port_str = options.bind.split(':')
+    port = int(port_str)
+
+    print('Listening on %s:%d' % (host, port))
+    srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler)
+    thr = threading.Thread(target=srv.serve_forever)
+    thr.start()
+    input('Press ENTER to shut down')
+    srv.shutdown()
+    thr.join()
+
+
+def rmtree(path):
+    for name in os.listdir(path):
+        fname = os.path.join(path, name)
+        if os.path.isdir(fname):
+            rmtree(fname)
+        else:
+            os.chmod(fname, 0o666)
+            os.remove(fname)
+    os.rmdir(path)
+
+#==============================================================================
+
+class BuildError(Exception):
+    def __init__(self, output, code=500):
+        self.output = output
+        self.code = code
+
+    def __str__(self):
+        return self.output
+
+
+class HTTPError(BuildError):
+    pass
+
+
+class PythonBuilder(object):
+    def __init__(self, **kwargs):
+        pythonVersion = kwargs.pop('python', '2.7')
+        try:
+            key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion)
+            try:
+                self.pythonPath, _ = _winreg.QueryValueEx(key, '')
+            finally:
+                _winreg.CloseKey(key)
+        except Exception:
+            raise BuildError('No such Python version: %s' % pythonVersion)
+
+        super(PythonBuilder, self).__init__(**kwargs)
+
+
+class GITInfoBuilder(object):
+    def __init__(self, **kwargs):
+        try:
+            self.user, self.repoName = kwargs['path'][:2]
+            self.rev = kwargs.pop('rev')
+        except ValueError:
+            raise BuildError('Invalid path')
+        except KeyError as e:
+            raise BuildError('Missing mandatory parameter "%s"' % e.args[0])
+
+        path = os.path.join(os.environ['APPDATA'], 'Build archive', self.repoName, self.user)
+        if not os.path.exists(path):
+            os.makedirs(path)
+        self.basePath = tempfile.mkdtemp(dir=path)
+        self.buildPath = os.path.join(self.basePath, 'build')
+
+        super(GITInfoBuilder, self).__init__(**kwargs)
+
+
+class GITBuilder(GITInfoBuilder):
+    def build(self):
+        try:
+            subprocess.check_output(['git', 'clone', 'git://github.com/%s/%s.git' % (self.user, self.repoName), self.buildPath])
+            subprocess.check_output(['git', 'checkout', self.rev], cwd=self.buildPath)
+        except subprocess.CalledProcessError as e:
+            raise BuildError(e.output)
+
+        super(GITBuilder, self).build()
+
+
+class YoutubeDLBuilder(object):
+    authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile']
+
+    def __init__(self, **kwargs):
+        if self.repoName != 'youtube-dl':
+            raise BuildError('Invalid repository "%s"' % self.repoName)
+        if self.user not in self.authorizedUsers:
+            raise HTTPError('Unauthorized user "%s"' % self.user, 401)
+
+        super(YoutubeDLBuilder, self).__init__(**kwargs)
+
+    def build(self):
+        try:
+            subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
+                                    cwd=self.buildPath)
+        except subprocess.CalledProcessError as e:
+            raise BuildError(e.output)
+
+        super(YoutubeDLBuilder, self).build()
+
+
+class DownloadBuilder(object):
+    def __init__(self, **kwargs):
+        self.handler = kwargs.pop('handler')
+        self.srcPath = os.path.join(self.buildPath, *tuple(kwargs['path'][2:]))
+        self.srcPath = os.path.abspath(os.path.normpath(self.srcPath))
+        if not self.srcPath.startswith(self.buildPath):
+            raise HTTPError(self.srcPath, 401)
+
+        super(DownloadBuilder, self).__init__(**kwargs)
+
+    def build(self):
+        if not os.path.exists(self.srcPath):
+            raise HTTPError('No such file', 404)
+        if os.path.isdir(self.srcPath):
+            raise HTTPError('Is a directory: %s' % self.srcPath, 401)
+
+        self.handler.send_response(200)
+        self.handler.send_header('Content-Type', 'application/octet-stream')
+        self.handler.send_header('Content-Disposition', 'attachment; filename=%s' % os.path.split(self.srcPath)[-1])
+        self.handler.send_header('Content-Length', str(os.stat(self.srcPath).st_size))
+        self.handler.end_headers()
+
+        with open(self.srcPath, 'rb') as src:
+            shutil.copyfileobj(src, self.handler.wfile)
+
+        super(DownloadBuilder, self).build()
+
+
+class CleanupTempDir(object):
+    def build(self):
+        try:
+            rmtree(self.basePath)
+        except Exception as e:
+            print('WARNING deleting "%s": %s' % (self.basePath, e))
+
+        super(CleanupTempDir, self).build()
+
+
+class Null(object):
+    def __init__(self, **kwargs):
+        pass
+
+    def start(self):
+        pass
+
+    def close(self):
+        pass
+
+    def build(self):
+        pass
+
+
+class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, CleanupTempDir, Null):
+    pass
+
+
+class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
+    actionDict = { 'build': Builder, 'download': Builder } # They're the same, no more caching.
+
+    def do_GET(self):
+        path = urlparse.urlparse(self.path)
+        paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()])
+        action, _, path = path.path.strip('/').partition('/')
+        if path:
+            path = path.split('/')
+            if action in self.actionDict:
+                try:
+                    builder = self.actionDict[action](path=path, handler=self, **paramDict)
+                    builder.start()
+                    try:
+                        builder.build()
+                    finally:
+                        builder.close()
+                except BuildError as e:
+                    self.send_response(e.code)
+                    msg = unicode(e).encode('UTF-8')
+                    self.send_header('Content-Type', 'text/plain; charset=UTF-8')
+                    self.send_header('Content-Length', len(msg))
+                    self.end_headers()
+                    self.wfile.write(msg)
+                except HTTPError as e:
+                    self.send_response(e.code, str(e))
+            else:
+                self.send_response(500, 'Unknown build method "%s"' % action)
+        else:
+            self.send_response(500, 'Malformed URL')
+
+#==============================================================================
+
+if __name__ == '__main__':
+    main()

devscripts/gh-pages/add-version.py

@@ -3,31 +3,40 @@
 import json
 import sys
 import hashlib
-import urllib.request
+import os.path
+
 
 if len(sys.argv) <= 1:
-	print('Specify the version number as parameter')
-	sys.exit()
+    print('Specify the version number as parameter')
+    sys.exit()
 version = sys.argv[1]
 
 with open('update/LATEST_VERSION', 'w') as f:
-	f.write(version)
+    f.write(version)
 
 versions_info = json.load(open('update/versions.json'))
 if 'signature' in versions_info:
-	del versions_info['signature']
+    del versions_info['signature']
 
 new_version = {}
 
-filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
+filenames = {
+    'bin': 'youtube-dl',
+    'exe': 'youtube-dl.exe',
+    'tar': 'youtube-dl-%s.tar.gz' % version}
+build_dir = os.path.join('..', '..', 'build', version)
 for key, filename in filenames.items():
-	print('Downloading and checksumming %s...' %filename)
-	url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
-	data = urllib.request.urlopen(url).read()
-	sha256sum = hashlib.sha256(data).hexdigest()
-	new_version[key] = (url, sha256sum)
+    url = 'https://yt-dl.org/downloads/%s/%s' % (version, filename)
+    fn = os.path.join(build_dir, filename)
+    with open(fn, 'rb') as f:
+        data = f.read()
+    if not data:
+        raise ValueError('File %s is empty!' % fn)
+    sha256sum = hashlib.sha256(data).hexdigest()
+    new_version[key] = (url, sha256sum)
 
 versions_info['versions'][version] = new_version
 versions_info['latest'] = version
 
-json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
+with open('update/versions.json', 'w') as jsonf:
+    json.dump(versions_info, jsonf, indent=4, sort_keys=True)

devscripts/gh-pages/update-feed.py

@@ -22,7 +22,7 @@ entry_template=textwrap.dedent("""
 									<atom:link href="http://rg3.github.io/youtube-dl" />
 									<atom:content type="xhtml">
 										<div xmlns="http://www.w3.org/1999/xhtml">
-											Downloads available at <a href="http://youtube-dl.org/downloads/@VERSION@/">http://youtube-dl.org/downloads/@VERSION@/</a>
+											Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
 										</div>
 									</atom:content>
 									<atom:author>
@@ -54,4 +54,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
 with open('update/releases.atom','w',encoding='utf-8') as atom_file:
 	atom_file.write(atom_template)
 
-

devscripts/gh-pages/update-sites.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+
+import sys
+import os
+import textwrap
+
+# We must be able to import youtube_dl
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+import youtube_dl
+
+def main():
+    with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
+        template = tmplf.read()
+
+    ie_htmls = []
+    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
+        ie_html = '<b>{}</b>'.format(ie.IE_NAME)
+        try:
+            ie_html += ': {}'.format(ie.IE_DESC)
+        except AttributeError:
+            pass
+        if ie.working() == False:
+            ie_html += ' (Currently broken)'
+        ie_htmls.append('<li>{}</li>'.format(ie_html))
+
+    template = template.replace('@SITES@', textwrap.indent('\n'.join(ie_htmls), '\t'))
+
+    with open('supportedsites.html', 'w', encoding='utf-8') as sitesf:
+        sitesf.write(template)
+
+if __name__ == '__main__':
+    main()

devscripts/release.sh

@@ -55,8 +55,8 @@ git push origin "$version"
 /bin/echo -e "\n### OK, now it is time to build the binaries..."
 REV=$(git rev-parse HEAD)
 make youtube-dl youtube-dl.tar.gz
-wget "http://jeromelaheurte.net:8142/download/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe || \
-	wget "http://jeromelaheurte.net:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
+read -p "VM running? (y/n) " -n 1
+wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
 mkdir -p "build/$version"
 mv youtube-dl youtube-dl.exe "build/$version"
 mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"
@@ -67,7 +67,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
 git checkout HEAD -- youtube-dl youtube-dl.exe
 
-/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
+/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
 for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
 scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
 ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
@@ -85,6 +85,7 @@ ROOT=$(pwd)
     "$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem"
     "$ROOT/devscripts/gh-pages/generate-download.py"
     "$ROOT/devscripts/gh-pages/update-copyright.py"
+    "$ROOT/devscripts/gh-pages/update-sites.py"
     git add *.html *.html.in update
     git commit -m "release $version"
     git show HEAD

devscripts/youtube_genalgo.py

@@ -1,31 +1,62 @@
 #!/usr/bin/env python
+# encoding: utf-8
 
 # Generate youtube signature algorithm from test cases
 
 import sys
 
 tests = [
-    # 88
+    # 93 - vfl79wBKW 2013/07/20
+    (u"qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~\"€",
+     u".>/?;:|}][{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ098765'321mnbvcxzasdfghjklpoiu"),
+    # 92 - vflQw-fB4 2013/07/17
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~\"",
+     "mrtyuioplkjhgfdsazxcvbnq1234567890QWERTY}IOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]\"|:;"),
+    # 91 - vfl79wBKW 2013/07/20 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~",
+     "/?;:|}][{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ09876543.1mnbvcxzasdfghjklpoiu"),
+    # 90
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`",
+     "mrtyuioplkjhgfdsazxcvbne1234567890QWER[YUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={`]}|"),
+    # 89 
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
+     "/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
+    # 88 - vflapUV9V 2013/08/28
     ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
-     "J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
+     "ioplkjhgfdsazxcvbnm12<4567890QWERTYUIOZLKJHGFDSAeXCVBNM!@#$%^&*()_-+={[]}|:;?/>.3"),
     # 87
     ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
-     "!?;:|}][{=+-_)(*&^$#@/MNBVCXZASqFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
-    # 86 - vfl_ymO4Z 2013/06/27
+     "uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
+    # 86 - vflHql6Pr 2013/09/24
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
+     ";}|[{=+-d)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYT_EWQ0987654321mnbvcxzas/fghjklpoiuytrewq"),
+    # 85 - vflkuzxcs 2013/09/11
+    ('0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[',
+     '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@'),
+    # 84 - vflHql6Pr 2013/09/24 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
+     "}[{=+-_)g*&^%$#@!MNBVCXZASDFGHJKLPOIUYTRE(Q0987654321mnbvcxzasdf?hjklpoiuytrewq"),
+    # 83
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
+     ".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
+    # 82 - vflGNjMhJ 2013/09/12
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
+     ".>/?;}[<=+-(*&^%$#@!MNBVCXeASDFGHKLPOqUYTREWQ0987654321mnbvcxzasdfghjklpoiuytrIwZ"),
+    # 81 - vflLC8JvQ 2013/07/25
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
+     "C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
+    # 80 - vflZK4ZYR 2013/08/23 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>",
+     "wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>"),
+    # 79 - vflLC8JvQ 2013/07/25 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/",
+     "Z?;}[{=+-(*&^%$#@!MNBVCXRASDFGHKLPOIUYT/EWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
+]
+
+tests_age_gate = [
+    # 86 - vflqinMWD
     ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
      "ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"),
-    # 85
-    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
-     "{>/?;}[.=+-_)(*&^%$#@!MqBVCXZASDFwHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
-    # 84
-    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
-     "<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"),
-    # 83 - vflcaqGO8 2013/07/11
-    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
-     "urty8ioplkjhgfdsazxcvbqm1234567S90QWERTYUIOPLKJHGFDnAZXCVBNM!#$%^&*()_+={[};?/>.<"),
-    # 82
-    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
-     "Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"),
 ]
 
 def find_matching(wrong, right):
@@ -78,6 +109,8 @@ def genall(tests):
 
 def main():
     print(genall(tests))
+    print(u'    Age gate:')
+    print(genall(tests_age_gate))
 
 if __name__ == '__main__':
     main()

test/parameters.json

@@ -38,7 +38,6 @@
     "writedescription": false, 
     "writeinfojson": true, 
     "writesubtitles": false,
-    "onlysubtitles": false,
     "allsubtitles": false,
     "listssubtitles": false
 }

test/test_all_urls.py

@@ -11,24 +11,50 @@ from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE,
 from helper import get_testcases
 
 class TestAllURLsMatching(unittest.TestCase):
+    def setUp(self):
+        self.ies = gen_extractors()
+
+    def matching_ies(self, url):
+        return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
+
+    def assertMatch(self, url, ie_list):
+        self.assertEqual(self.matching_ies(url), ie_list)
+
     def test_youtube_playlist_matching(self):
-        self.assertTrue(YoutubePlaylistIE.suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
-        self.assertTrue(YoutubePlaylistIE.suitable(u'UUBABnxM4Ar9ten8Mdjj1j0Q')) #585
-        self.assertTrue(YoutubePlaylistIE.suitable(u'PL63F0C78739B09958'))
-        self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q'))
-        self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
-        self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC'))
-        self.assertTrue(YoutubePlaylistIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
-        self.assertFalse(YoutubePlaylistIE.suitable(u'PLtS2H6bU1M'))
+        assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
+        assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
+        assertPlaylist(u'PL63F0C78739B09958')
+        assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
+        self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
 
     def test_youtube_matching(self):
         self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
         self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+        self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
+        self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
+        self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
 
     def test_youtube_channel_matching(self):
-        self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM'))
-        self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec'))
-        self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos'))
+        assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
+        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
+        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
+        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
+
+    def test_youtube_user_matching(self):
+        self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
+
+    def test_youtube_feeds(self):
+        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
+        self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
+        self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
+        self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
+
+    def test_youtube_show_matching(self):
+        self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
@@ -47,9 +73,13 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
 
     def test_youtube_extract(self):
-        self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
-        self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
-        self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+        assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
+        assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
     def test_no_duplicates(self):
         ies = gen_extractors()
@@ -62,15 +92,12 @@ class TestAllURLsMatching(unittest.TestCase):
                     self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
 
     def test_keywords(self):
-        ies = gen_extractors()
-        matching_ies = lambda url: [ie.IE_NAME for ie in ies
-                                    if ie.suitable(url) and ie.IE_NAME != 'generic']
-        self.assertEqual(matching_ies(':ytsubs'), ['youtube:subscriptions'])
-        self.assertEqual(matching_ies(':ytsubscriptions'), ['youtube:subscriptions'])
-        self.assertEqual(matching_ies(':thedailyshow'), ['ComedyCentral'])
-        self.assertEqual(matching_ies(':tds'), ['ComedyCentral'])
-        self.assertEqual(matching_ies(':colbertreport'), ['ComedyCentral'])
-        self.assertEqual(matching_ies(':cr'), ['ComedyCentral'])
+        self.assertMatch(':ytsubs', ['youtube:subscriptions'])
+        self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
+        self.assertMatch(':thedailyshow', ['ComedyCentral'])
+        self.assertMatch(':tds', ['ComedyCentral'])
+        self.assertMatch(':colbertreport', ['ComedyCentral'])
+        self.assertMatch(':cr', ['ComedyCentral'])
 
 
 if __name__ == '__main__':

test/test_dailymotion_subtitles.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+import sys
+import unittest
+import json
+import io
+import hashlib
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor import DailymotionIE
+from youtube_dl.utils import *
+from helper import FakeYDL
+
+md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+class TestDailymotionSubtitles(unittest.TestCase):
+    def setUp(self):
+        self.DL = FakeYDL()
+        self.url = 'http://www.dailymotion.com/video/xczg00'
+    def getInfoDict(self):
+        IE = DailymotionIE(self.DL)
+        info_dict = IE.extract(self.url)
+        return info_dict
+    def getSubtitles(self):
+        info_dict = self.getInfoDict()
+        return info_dict[0]['subtitles']
+    def test_no_writesubtitles(self):
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles.keys()), 5)
+    def test_list_subtitles(self):
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+    def test_automatic_captions(self):
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
+        subtitles = self.getSubtitles()
+        self.assertTrue(len(subtitles.keys()) == 0)
+    def test_nosubtitles(self):
+        self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+    def test_multiple_langs(self):
+        self.DL.params['writesubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_download.py

@@ -127,12 +127,11 @@ def generator(test_case):
                     info_dict = json.load(infof)
                 for (info_field, expected) in tc.get('info_dict', {}).items():
                     if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        self.assertEqual(expected, 'md5:' + md5(info_dict.get(info_field)))
+                        got = 'md5:' + md5(info_dict.get(info_field))
                     else:
                         got = info_dict.get(info_field)
-                        self.assertEqual(
-                            expected, got,
-                            u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+                    self.assertEqual(expected, got,
+                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
                 # If checkable fields are missing from the test case, print the info_dict
                 test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))

test/test_playlists.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import sys
+import unittest
+import json
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor import (
+    DailymotionPlaylistIE,
+    DailymotionUserIE,
+    VimeoChannelIE,
+    UstreamChannelIE,
+    SoundcloudUserIE,
+    LivestreamIE,
+)
+from youtube_dl.utils import *
+
+from helper import FakeYDL
+
+class TestPlaylists(unittest.TestCase):
+    def assertIsPlaylist(self, info):
+        """Make sure the info has '_type' set to 'playlist'"""
+        self.assertEqual(info['_type'], 'playlist')
+
+    def test_dailymotion_playlist(self):
+        dl = FakeYDL()
+        ie = DailymotionPlaylistIE(dl)
+        result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'SPORT')
+        self.assertTrue(len(result['entries']) > 20)
+
+    def test_dailymotion_user(self):
+        dl = FakeYDL()
+        ie = DailymotionUserIE(dl)
+        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Génération Quoi')
+        self.assertTrue(len(result['entries']) >= 26)
+
+    def test_vimeo_channel(self):
+        dl = FakeYDL()
+        ie = VimeoChannelIE(dl)
+        result = ie.extract('http://vimeo.com/channels/tributes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Vimeo Tributes')
+        self.assertTrue(len(result['entries']) > 24)
+
+    def test_ustream_channel(self):
+        dl = FakeYDL()
+        ie = UstreamChannelIE(dl)
+        result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'5124905')
+        self.assertTrue(len(result['entries']) >= 11)
+
+    def test_soundcloud_user(self):
+        dl = FakeYDL()
+        ie = SoundcloudUserIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'9615865')
+        self.assertTrue(len(result['entries']) >= 12)
+
+    def test_livestream_event(self):
+        dl = FakeYDL()
+        ie = LivestreamIE(dl)
+        result = ie.extract('http://new.livestream.com/tedx/cityenglish')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'TEDCity2.0 (English)')
+        self.assertTrue(len(result['entries']) >= 4)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -11,13 +11,16 @@ import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 #from youtube_dl.utils import htmlentity_transform
-from youtube_dl.utils import timeconvert
-from youtube_dl.utils import sanitize_filename
-from youtube_dl.utils import unescapeHTML
-from youtube_dl.utils import orderedSet
-from youtube_dl.utils import DateRange
-from youtube_dl.utils import unified_strdate
-from youtube_dl.utils import find_xpath_attr
+from youtube_dl.utils import (
+    timeconvert,
+    sanitize_filename,
+    unescapeHTML,
+    orderedSet,
+    DateRange,
+    unified_strdate,
+    find_xpath_attr,
+    get_meta_content,
+)
 
 if sys.version_info < (3, 0):
     _compat_str = lambda b: b.decode('unicode-escape')
@@ -127,5 +130,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
+    def test_meta_parser(self):
+        testhtml = u'''
+        <head>
+            <meta name="description" content="foo &amp; bar">
+            <meta content='Plato' name='author'/>
+        </head>
+        '''
+        get_meta = lambda name: get_meta_content(name, testhtml)
+        self.assertEqual(get_meta('description'), u'foo & bar')
+        self.assertEqual(get_meta('author'), 'Plato')
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_sig.py

@@ -1,57 +0,0 @@
-#!/usr/bin/env python
-
-import unittest
-import sys
-
-# Allow direct execution
-import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from youtube_dl.extractor.youtube import YoutubeIE
-from helper import FakeYDL
-
-sig = YoutubeIE(FakeYDL())._decrypt_signature
-
-class TestYoutubeSig(unittest.TestCase):
-    def test_43_43(self):
-        wrong = '5AEEAE0EC39677BC65FD9021CCD115F1F2DBD5A59E4.C0B243A3E2DED6769199AF3461781E75122AE135135'
-        right = '931EA22157E1871643FA9519676DED253A342B0C.4E95A5DBD2F1F511DCC1209DF56CB77693CE0EAE'
-        self.assertEqual(sig(wrong), right)
-
-    def test_88(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<"
-        right = "J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"
-        self.assertEqual(sig(wrong), right)
-
-    def test_87(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<"
-        right = "!?;:|}][{=+-_)(*&^$#@/MNBVCXZASqFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"
-        self.assertEqual(sig(wrong), right)
-
-    def test_86(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<"
-        right = "ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"
-        self.assertEqual(sig(wrong), right)
-
-    def test_85(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<"
-        right = "{>/?;}[.=+-_)(*&^%$#@!MqBVCXZASDFwHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"
-        self.assertEqual(sig(wrong), right)
-
-    def test_84(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<"
-        right = "<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"
-        self.assertEqual(sig(wrong), right)
-
-    def test_83(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<"
-        right = "urty8ioplkjhgfdsazxcvbqm1234567S90QWERTYUIOPLKJHGFDnAZXCVBNM!#$%^&*()_+={[};?/>.<"
-        self.assertEqual(sig(wrong), right)
-
-    def test_82(self):
-        wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<"
-        right = "Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"
-        self.assertEqual(sig(wrong), right)
-
-if __name__ == '__main__':
-    unittest.main()

test/test_youtube_signature.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+
+import io
+import re
+import string
+import sys
+import unittest
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor import YoutubeIE
+from youtube_dl.utils import compat_str, compat_urlretrieve
+
+_TESTS = [
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
+        u'js',
+        86,
+        u'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
+    ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
+        u'js',
+        85,
+        u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
+    ),
+    (
+        u'https://s.ytimg.com/yts/swfbin/watch_as3-vflg5GhxU.swf',
+        u'swf',
+        82,
+        u':/.-,+*)=\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBAzyxw>utsrqponmlkjihgfedcba987654321'
+    ),
+]
+
+
+class TestSignature(unittest.TestCase):
+    def setUp(self):
+        TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+        self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
+        if not os.path.exists(self.TESTDATA_DIR):
+            os.mkdir(self.TESTDATA_DIR)
+
+
+def make_tfunc(url, stype, sig_length, expected_sig):
+    basename = url.rpartition('/')[2]
+    m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename)
+    assert m, '%r should follow URL format' % basename
+    test_id = m.group(1)
+
+    def test_func(self):
+        fn = os.path.join(self.TESTDATA_DIR, basename)
+
+        if not os.path.exists(fn):
+            compat_urlretrieve(url, fn)
+
+        ie = YoutubeIE()
+        if stype == 'js':
+            with io.open(fn, encoding='utf-8') as testf:
+                jscode = testf.read()
+            func = ie._parse_sig_js(jscode)
+        else:
+            assert stype == 'swf'
+            with open(fn, 'rb') as testf:
+                swfcode = testf.read()
+            func = ie._parse_sig_swf(swfcode)
+        src_sig = compat_str(string.printable[:sig_length])
+        got_sig = func(src_sig)
+        self.assertEqual(got_sig, expected_sig)
+
+    test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
+    setattr(TestSignature, test_func.__name__, test_func)
+
+for test_spec in _TESTS:
+    make_tfunc(*test_spec)
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_subtitles.py

@@ -18,78 +18,67 @@ md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 class TestYoutubeSubtitles(unittest.TestCase):
     def setUp(self):
-        DL = FakeYDL()
-        DL.params['allsubtitles'] = False
-        DL.params['writesubtitles'] = False
-        DL.params['subtitlesformat'] = 'srt'
-        DL.params['listsubtitles'] = False
-    def test_youtube_no_subtitles(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = False
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        subtitles = info_dict[0]['subtitles']
+        self.DL = FakeYDL()
+        self.url = 'QRS8MkLhQmM'
+    def getInfoDict(self):
+        IE = YoutubeIE(self.DL)
+        info_dict = IE.extract(self.url)
+        return info_dict
+    def getSubtitles(self):
+        info_dict = self.getInfoDict()
+        return info_dict[0]['subtitles']        
+    def test_youtube_no_writesubtitles(self):
+        self.DL.params['writesubtitles'] = False
+        subtitles = self.getSubtitles()
         self.assertEqual(subtitles, None)
     def test_youtube_subtitles(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
-    def test_youtube_subtitles_it(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        DL.params['subtitleslang'] = 'it'
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
-    def test_youtube_onlysubtitles(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        DL.params['onlysubtitles'] = True
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
+    def test_youtube_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['it']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
     def test_youtube_allsubtitles(self):
-        DL = FakeYDL()
-        DL.params['allsubtitles'] = True
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        subtitles = info_dict[0]['subtitles']
-        self.assertEqual(len(subtitles), 13)
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles.keys()), 13)
     def test_youtube_subtitles_sbv_format(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        DL.params['subtitlesformat'] = 'sbv'
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitlesformat'] = 'sbv'
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
     def test_youtube_subtitles_vtt_format(self):
-        DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        DL.params['subtitlesformat'] = 'vtt'
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '356cdc577fde0c6783b9b822e7206ff7')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitlesformat'] = 'vtt'
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
     def test_youtube_list_subtitles(self):
-        DL = FakeYDL()
-        DL.params['listsubtitles'] = True
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('QRS8MkLhQmM')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
         self.assertEqual(info_dict, None)
     def test_youtube_automatic_captions(self):
-        DL = FakeYDL()
-        DL.params['writeautomaticsub'] = True
-        DL.params['subtitleslang'] = 'it'
-        IE = YoutubeIE(DL)
-        info_dict = IE.extract('8YoUxe5ncPo')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertTrue(sub[2] is not None)
+        self.url = '8YoUxe5ncPo'
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslangs'] = ['it']
+        subtitles = self.getSubtitles()
+        self.assertTrue(subtitles['it'] is not None)
+    def test_youtube_nosubtitles(self):
+        self.url = 'sAjKT8FhjI8'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+    def test_youtube_multiple_langs(self):
+        self.url = 'QRS8MkLhQmM'
+        self.DL.params['writesubtitles'] = True
+        langs = ['it', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/FileDownloader.py

@@ -63,32 +63,57 @@ class FileDownloader(object):
         converted = float(bytes) / float(1024 ** exponent)
         return '%.2f%s' % (converted, suffix)
 
+    @staticmethod
+    def format_seconds(seconds):
+        (mins, secs) = divmod(seconds, 60)
+        (hours, mins) = divmod(mins, 60)
+        if hours > 99:
+            return '--:--:--'
+        if hours == 0:
+            return '%02d:%02d' % (mins, secs)
+        else:
+            return '%02d:%02d:%02d' % (hours, mins, secs)
+
     @staticmethod
     def calc_percent(byte_counter, data_len):
         if data_len is None:
+            return None
+        return float(byte_counter) / float(data_len) * 100.0
+
+    @staticmethod
+    def format_percent(percent):
+        if percent is None:
             return '---.-%'
-        return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
+        return '%6s' % ('%3.1f%%' % percent)
 
     @staticmethod
     def calc_eta(start, now, total, current):
         if total is None:
-            return '--:--'
+            return None
         dif = now - start
         if current == 0 or dif < 0.001: # One millisecond
-            return '--:--'
+            return None
         rate = float(current) / dif
-        eta = int((float(total) - float(current)) / rate)
-        (eta_mins, eta_secs) = divmod(eta, 60)
-        if eta_mins > 99:
+        return int((float(total) - float(current)) / rate)
+
+    @staticmethod
+    def format_eta(eta):
+        if eta is None:
             return '--:--'
-        return '%02d:%02d' % (eta_mins, eta_secs)
+        return FileDownloader.format_seconds(eta)
 
     @staticmethod
     def calc_speed(start, now, bytes):
         dif = now - start
         if bytes == 0 or dif < 0.001: # One millisecond
+            return None
+        return float(bytes) / dif
+
+    @staticmethod
+    def format_speed(speed):
+        if speed is None:
             return '%10s' % '---b/s'
-        return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
+        return '%10s' % ('%s/s' % FileDownloader.format_bytes(speed))
 
     @staticmethod
     def best_block_size(elapsed_time, bytes):
@@ -197,11 +222,14 @@ class FileDownloader(object):
         """Report destination filename."""
         self.to_screen(u'[download] Destination: ' + filename)
 
-    def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
+    def report_progress(self, percent, data_len_str, speed, eta):
         """Report download progress."""
         if self.params.get('noprogress', False):
             return
         clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+        eta_str = self.format_eta(eta)
+        percent_str = self.format_percent(percent)
+        speed_str = self.format_speed(speed)
         if self.params.get('progress_with_newline', False):
             self.to_screen(u'[download] %s of %s at %s ETA %s' %
                 (percent_str, data_len_str, speed_str, eta_str))
@@ -230,12 +258,14 @@ class FileDownloader(object):
         """Report it was impossible to resume download."""
         self.to_screen(u'[download] Unable to resume')
 
-    def report_finish(self):
+    def report_finish(self, data_len_str, tot_time):
         """Report download finished."""
         if self.params.get('noprogress', False):
             self.to_screen(u'[download] Download completed')
         else:
-            self.to_screen(u'')
+            clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+            self.to_screen(u'\r%s[download] 100%% of %s in %s' %
+                (clear_line, data_len_str, self.format_seconds(tot_time)))
 
     def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
         self.report_destination(filename)
@@ -329,6 +359,35 @@ class FileDownloader(object):
             self.report_error(u'mplayer exited with code %d' % retval)
             return False
 
+    def _download_m3u8_with_ffmpeg(self, filename, url):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', tmpfilename]
+        # Check for ffmpeg first
+        try:
+            subprocess.call(['ffmpeg', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error(u'm3u8 download detected but "%s" could not be run' % args[0] )
+            return False
+
+        retval = subprocess.call(args)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'ffmpeg exited with code %d' % retval)
+            return False
+
 
     def _do_download(self, filename, info_dict):
         url = info_dict['url']
@@ -339,6 +398,7 @@ class FileDownloader(object):
             self._hook_progress({
                 'filename': filename,
                 'status': 'finished',
+                'total_bytes': os.path.getsize(encodeFilename(filename)),
             })
             return True
 
@@ -354,6 +414,10 @@ class FileDownloader(object):
         if url.startswith('mms') or url.startswith('rtsp'):
             return self._download_with_mplayer(filename, url)
 
+        # m3u8 manifest are downloaded with ffmpeg
+        if determine_ext(url) == u'm3u8':
+            return self._download_m3u8_with_ffmpeg(filename, url)
+
         tmpfilename = self.temp_name(filename)
         stream = None
 
@@ -481,13 +545,14 @@ class FileDownloader(object):
                 block_size = self.best_block_size(after - before, len(data_block))
 
             # Progress message
-            speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
+            speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
             if data_len is None:
                 self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+                eta = None
             else:
-                percent_str = self.calc_percent(byte_counter, data_len)
-                eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
-                self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+                percent = self.calc_percent(byte_counter, data_len)
+                eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+                self.report_progress(percent, data_len_str, speed, eta)
 
             self._hook_progress({
                 'downloaded_bytes': byte_counter,
@@ -495,6 +560,8 @@ class FileDownloader(object):
                 'tmpfilename': tmpfilename,
                 'filename': filename,
                 'status': 'downloading',
+                'eta': eta,
+                'speed': speed,
             })
 
             # Apply rate limit
@@ -505,7 +572,7 @@ class FileDownloader(object):
             self.report_error(u'Did not get any data blocks')
             return False
         stream.close()
-        self.report_finish()
+        self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.try_rename(tmpfilename, filename)
@@ -537,6 +604,8 @@ class FileDownloader(object):
         * downloaded_bytes: Bytes on disks
         * total_bytes: Total bytes, None if unknown
         * tmpfilename: The filename we're currently writing to
+        * eta: The estimated time in seconds, None if unknown
+        * speed: The download speed in bytes/second, None if unknown
 
         Hooks are guaranteed to be called at least once (with status "finished")
         if the download is successful.

youtube_dl/PostProcessor.py

@@ -71,12 +71,17 @@ class FFmpegPostProcessor(PostProcessor):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
         return dict((program, executable(program)) for program in programs)
 
-    def run_ffmpeg(self, path, out_path, opts):
+    def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
         if not self._exes['ffmpeg'] and not self._exes['avconv']:
             raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
-        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path)]
+
+        files_cmd = []
+        for path in input_paths:
+            files_cmd.extend(['-i', encodeFilename(path)])
+        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
                + opts +
                [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         stdout,stderr = p.communicate()
         if p.returncode != 0:
@@ -84,6 +89,9 @@ class FFmpegPostProcessor(PostProcessor):
             msg = stderr.strip().split('\n')[-1]
             raise FFmpegPostProcessorError(msg)
 
+    def run_ffmpeg(self, path, out_path, opts):
+        self.run_ffmpeg_multiple_files([path], out_path, opts)
+
     def _ffmpeg_filename_argument(self, fn):
         # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
         if fn.startswith(u'-'):
@@ -100,7 +108,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         self._nopostoverwrites = nopostoverwrites
 
     def get_audio_codec(self, path):
-        if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
+        if not self._exes['ffprobe'] and not self._exes['avprobe']:
+            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
         try:
             cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
             handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
@@ -128,7 +137,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         try:
             FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
         except FFmpegPostProcessorError as err:
-            raise AudioConversionError(err.message)
+            raise AudioConversionError(err.msg)
 
     def run(self, information):
         path = information['filepath']
@@ -198,7 +207,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         except:
             etype,e,tb = sys.exc_info()
             if isinstance(e, AudioConversionError):
-                msg = u'audio conversion failed: ' + e.message
+                msg = u'audio conversion failed: ' + e.msg
             else:
                 msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
             raise PostProcessingError(msg)
@@ -208,7 +217,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
             try:
                 os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
             except:
-                self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+                self._downloader.report_warning(u'Cannot update utime of audio file')
 
         information['filepath'] = new_path
         return self._nopostoverwrites,information
@@ -231,3 +240,227 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
         information['format'] = self._preferedformat
         information['ext'] = self._preferedformat
         return False,information
+
+
+class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    def __init__(self, downloader=None, subtitlesformat='srt'):
+        super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
+        self._subformat = subtitlesformat
+
+    @classmethod
+    def _conver_lang_code(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    def run(self, information):
+        if information['ext'] != u'mp4':
+            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
+            return True, information
+        sub_langs = [key for key in information['subtitles']]
+
+        filename = information['filepath']
+        input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
+
+        opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
+        for (i, lang) in enumerate(sub_langs):
+            opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
+            lang_code = self._conver_lang_code(lang)
+            if lang_code is not None:
+                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
+        opts.extend(['-f', 'mp4'])
+
+        temp_filename = filename + u'.temp'
+        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
+        self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
+        os.remove(encodeFilename(filename))
+        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+        return True, information

youtube_dl/YoutubeDL.py

@@ -74,12 +74,15 @@ class YoutubeDL(object):
     writesubtitles:    Write the video subtitles to a file
     writeautomaticsub: Write the automatic subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
+                       (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video
     subtitlesformat:   Subtitle format [srt/sbv/vtt] (default=srt)
-    subtitleslang:     Language of the subtitles to download
+    subtitleslangs:    List of languages of the subtitles to download
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
+    cachedir:          Location of the cache files in the filesystem.
+                       None to disable filesystem cache.
     
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -97,11 +100,23 @@ class YoutubeDL(object):
     def __init__(self, params):
         """Create a FileDownloader object with the given options."""
         self._ies = []
+        self._ies_instances = {}
         self._pps = []
         self._progress_hooks = []
         self._download_retcode = 0
         self._num_downloads = 0
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+
+        if (sys.version_info >= (3,) and sys.platform != 'win32' and
+                sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
+                and not params['restrictfilenames']):
+            # On Python 3, the Unicode filesystem API will throw errors (#1474)
+            self.report_warning(
+                u'Assuming --restrict-filenames isnce file system encoding '
+                u'cannot encode all charactes. '
+                u'Set the LC_ALL environment variable to fix this.')
+            params['restrictfilenames'] = True
+
         self.params = params
         self.fd = FileDownloader(self, self.params)
 
@@ -111,8 +126,21 @@ class YoutubeDL(object):
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
+        self._ies_instances[ie.ie_key()] = ie
         ie.set_downloader(self)
 
+    def get_info_extractor(self, ie_key):
+        """
+        Get an instance of an IE with name ie_key, it will try to get one from
+        the _ies list, if there's no instance it will create a new one and add
+        it to the extractor list.
+        """
+        ie = self._ies_instances.get(ie_key)
+        if ie is None:
+            ie = get_info_extractor(ie_key)()
+            self.add_info_extractor(ie)
+        return ie
+
     def add_default_info_extractors(self):
         """
         Add the InfoExtractors returned by gen_extractors to the end of the list
@@ -127,14 +155,10 @@ class YoutubeDL(object):
 
     def to_screen(self, message, skip_eol=False):
         """Print message to stdout if not in quiet mode."""
-        assert type(message) == type(u'')
         if not self.params.get('quiet', False):
             terminator = [u'\n', u''][skip_eol]
             output = message + terminator
-            if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
-                output = output.encode(preferredencoding(), 'ignore')
-            self._screen_file.write(output)
-            self._screen_file.flush()
+            write_string(output, self._screen_file)
 
     def to_stderr(self, message):
         """Print message to stderr."""
@@ -264,7 +288,7 @@ class YoutubeDL(object):
             self.report_error(u'Erroneous output template')
             return None
         except ValueError as err:
-            self.report_error(u'Insufficient system charset ' + repr(preferredencoding()))
+            self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
     def _match_entry(self, info_dict):
@@ -294,9 +318,7 @@ class YoutubeDL(object):
          '''
         
         if ie_key:
-            ie = get_info_extractor(ie_key)()
-            ie.set_downloader(self)
-            ies = [ie]
+            ies = [self.get_info_extractor(ie_key)]
         else:
             ies = self._ies
 
@@ -448,7 +470,8 @@ class YoutubeDL(object):
         if self.params.get('forceid', False):
             compat_print(info_dict['id'])
         if self.params.get('forceurl', False):
-            compat_print(info_dict['url'])
+            # For RTMP URLs, also include the playpath
+            compat_print(info_dict['url'] + info_dict.get('play_path', u''))
         if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
             compat_print(info_dict['thumbnail'])
         if self.params.get('forcedescription', False) and 'description' in info_dict:
@@ -479,45 +502,33 @@ class YoutubeDL(object):
                 self.report_writedescription(descfn)
                 with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
                     descfile.write(info_dict['description'])
+            except (KeyError, TypeError):
+                self.report_warning(u'There\'s no description to write.')
             except (OSError, IOError):
                 self.report_error(u'Cannot write description file ' + descfn)
                 return
 
-        if (self.params.get('writesubtitles', False) or self.params.get('writeautomaticsub')) and 'subtitles' in info_dict and info_dict['subtitles']:
+        subtitles_are_requested = any([self.params.get('writesubtitles', False),
+                                       self.params.get('writeautomaticsub')])
+
+        if  subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE
-            subtitle = info_dict['subtitles'][0]
-            (sub_error, sub_lang, sub) = subtitle
+            subtitles = info_dict['subtitles']
             sub_format = self.params.get('subtitlesformat')
-            if sub_error:
-                self.report_warning("Some error while getting the subtitles")
-            else:
+            for sub_lang in subtitles.keys():
+                sub = subtitles[sub_lang]
+                if sub is None:
+                    continue
                 try:
-                    sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+                    sub_filename = subtitles_filename(filename, sub_lang, sub_format)
                     self.report_writesubtitles(sub_filename)
                     with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
-                        subfile.write(sub)
+                            subfile.write(sub)
                 except (OSError, IOError):
                     self.report_error(u'Cannot write subtitles file ' + descfn)
                     return
 
-        if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
-            subtitles = info_dict['subtitles']
-            sub_format = self.params.get('subtitlesformat')
-            for subtitle in subtitles:
-                (sub_error, sub_lang, sub) = subtitle
-                if sub_error:
-                    self.report_warning("Some error while getting the subtitles")
-                else:
-                    try:
-                        sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
-                        self.report_writesubtitles(sub_filename)
-                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
-                                subfile.write(sub)
-                    except (OSError, IOError):
-                        self.report_error(u'Cannot write subtitles file ' + descfn)
-                        return
-
         if self.params.get('writeinfojson', False):
             infofn = filename + u'.info.json'
             self.report_writeinfojson(infofn)
@@ -529,10 +540,8 @@ class YoutubeDL(object):
                 return
 
         if self.params.get('writethumbnail', False):
-            if 'thumbnail' in info_dict:
-                thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
-                if not thumb_format:
-                    thumb_format = 'jpg'
+            if info_dict.get('thumbnail') is not None:
+                thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
                 thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
                 self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
                                (info_dict['extractor'], info_dict['id']))
@@ -548,11 +557,11 @@ class YoutubeDL(object):
             else:
                 try:
                     success = self.fd._do_download(filename, info_dict)
-                except (OSError, IOError) as err:
-                    raise UnavailableVideoError()
                 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                     self.report_error(u'unable to download video data: %s' % str(err))
                     return
+                except (OSError, IOError) as err:
+                    raise UnavailableVideoError(err)
                 except (ContentTooShortError, ) as err:
                     self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
                     return
@@ -596,7 +605,7 @@ class YoutubeDL(object):
                         # No clear decision yet, let IE decide
                         keep_video = keep_video_wish
             except PostProcessingError as e:
-                self.to_stderr(u'ERROR: ' + e.msg)
+                self.report_error(e.msg)
         if keep_video is False and not self.params.get('keepvideo', False):
             try:
                 self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename)

youtube_dl/__init__.py

@@ -27,6 +27,10 @@ __authors__  = (
     'Johny Mo Swag',
     'Axel Noack',
     'Albert Kim',
+    'Pierre Rudloff',
+    'Huarong Huo',
+    'Ismael Mejía',
+    'Steffan \'Ruirize\' James',
 )
 
 __license__ = 'Public Domain'
@@ -44,6 +48,7 @@ import sys
 import warnings
 import platform
 
+
 from .utils import *
 from .update import update_self
 from .version import __version__
@@ -82,6 +87,9 @@ def parseOpts(overrideArguments=None):
 
         return "".join(opts)
 
+    def _comma_separated_values_options_callback(option, opt_str, value, parser):
+        setattr(parser.values, option.dest, value.split(','))
+
     def _find_term_columns():
         columns = os.environ.get('COLUMNS', None)
         if columns:
@@ -95,6 +103,16 @@ def parseOpts(overrideArguments=None):
             pass
         return None
 
+    def _hide_login_info(opts):
+        opts = list(opts)
+        for private_opt in ['-p', '--password', '-u', '--username']:
+            try:
+                i = opts.index(private_opt)
+                opts[i+1] = '<PRIVATE>'
+            except ValueError:
+                pass
+        return opts
+
     max_width = 80
     max_help_position = 80
 
@@ -119,6 +137,7 @@ def parseOpts(overrideArguments=None):
     selection      = optparse.OptionGroup(parser, 'Video Selection')
     authentication = optparse.OptionGroup(parser, 'Authentication Options')
     video_format   = optparse.OptionGroup(parser, 'Video Format Options')
+    subtitles      = optparse.OptionGroup(parser, 'Subtitle Options')
     downloader     = optparse.OptionGroup(parser, 'Download Options')
     postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
     filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
@@ -129,9 +148,9 @@ def parseOpts(overrideArguments=None):
     general.add_option('-v', '--version',
             action='version', help='print program version and exit')
     general.add_option('-U', '--update',
-            action='store_true', dest='update_self', help='update this program to latest version')
+            action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
     general.add_option('--dump-user-agent',
             action='store_true', dest='dump_user_agent',
             help='display the current browser identification', default=False)
@@ -148,6 +167,12 @@ def parseOpts(overrideArguments=None):
             help='Output descriptions of all supported extractors', default=False)
     general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
+    general.add_option(
+        '--cache-dir', dest='cachedir', default=u'~/.youtube-dl/cache',
+        help='Location in the filesystem where youtube-dl can store downloaded information permanently. %default by default')
+    general.add_option(
+        '--no-cache-dir', action='store_const', const=None, dest='cachedir',
+        help='Disable filesystem caching')
 
 
     selection.add_option('--playlist-start',
@@ -176,7 +201,7 @@ def parseOpts(overrideArguments=None):
 
     video_format.add_option('-f', '--format',
             action='store', dest='format', metavar='FORMAT',
-            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18"')
+            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -185,27 +210,26 @@ def parseOpts(overrideArguments=None):
             action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
     video_format.add_option('-F', '--list-formats',
             action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
-    video_format.add_option('--write-sub', '--write-srt',
+
+    subtitles.add_option('--write-sub', '--write-srt',
             action='store_true', dest='writesubtitles',
-            help='write subtitle file (currently youtube only)', default=False)
-    video_format.add_option('--write-auto-sub', '--write-automatic-sub',
+            help='write subtitle file', default=False)
+    subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
             action='store_true', dest='writeautomaticsub',
-            help='write automatic subtitle file (currently youtube only)', default=False)
-    video_format.add_option('--only-sub',
-            action='store_true', dest='skip_download',
-            help='[deprecated] alias of --skip-download', default=False)
-    video_format.add_option('--all-subs',
+            help='write automatic subtitle file (youtube only)', default=False)
+    subtitles.add_option('--all-subs',
             action='store_true', dest='allsubtitles',
-            help='downloads all the available subtitles of the video (currently youtube only)', default=False)
-    video_format.add_option('--list-subs',
+            help='downloads all the available subtitles of the video', default=False)
+    subtitles.add_option('--list-subs',
             action='store_true', dest='listsubtitles',
-            help='lists all available subtitles for the video (currently youtube only)', default=False)
-    video_format.add_option('--sub-format',
+            help='lists all available subtitles for the video', default=False)
+    subtitles.add_option('--sub-format',
             action='store', dest='subtitlesformat', metavar='FORMAT',
-            help='subtitle format [srt/sbv/vtt] (default=srt) (currently youtube only)', default='srt')
-    video_format.add_option('--sub-lang', '--srt-lang',
-            action='store', dest='subtitleslang', metavar='LANG',
-            help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
+            help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
+    subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
+            action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
+            default=[], callback=_comma_separated_values_options_callback,
+            help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
 
     downloader.add_option('-r', '--rate-limit',
             dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
@@ -254,6 +278,10 @@ def parseOpts(overrideArguments=None):
     verbosity.add_option('--dump-intermediate-pages',
             action='store_true', dest='dump_intermediate_pages', default=False,
             help='print downloaded pages to debug problems(very verbose)')
+    verbosity.add_option('--youtube-print-sig-code',
+            action='store_true', dest='youtube_print_sig_code', default=False,
+            help=optparse.SUPPRESS_HELP)
+
 
     filesystem.add_option('-t', '--title',
             action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
@@ -320,6 +348,8 @@ def parseOpts(overrideArguments=None):
             help='keeps the video file on disk after the post-processing; the video is erased by default')
     postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
             help='do not overwrite post-processed files; the post-processed files are overwritten by default')
+    postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
+            help='embed subtitles in the video (only for mp4 videos)')
 
 
     parser.add_option_group(general)
@@ -328,13 +358,14 @@ def parseOpts(overrideArguments=None):
     parser.add_option_group(filesystem)
     parser.add_option_group(verbosity)
     parser.add_option_group(video_format)
+    parser.add_option_group(subtitles)
     parser.add_option_group(authentication)
     parser.add_option_group(postproc)
 
     if overrideArguments is not None:
         opts, args = parser.parse_args(overrideArguments)
         if opts.verbose:
-            sys.stderr.write(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
+            write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
         xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
         if xdg_config_home:
@@ -343,13 +374,13 @@ def parseOpts(overrideArguments=None):
             userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
         systemConf = _readOptions('/etc/youtube-dl.conf')
         userConf = _readOptions(userConfFile)
-        commandLineConf = sys.argv[1:] 
+        commandLineConf = sys.argv[1:]
         argv = systemConf + userConf + commandLineConf
         opts, args = parser.parse_args(argv)
         if opts.verbose:
-            sys.stderr.write(u'[debug] System config: ' + repr(systemConf) + '\n')
-            sys.stderr.write(u'[debug] User config: ' + repr(userConf) + '\n')
-            sys.stderr.write(u'[debug] Command-line args: ' + repr(commandLineConf) + '\n')
+            write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
+            write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
+            write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
 
     return parser, opts, args
 
@@ -372,12 +403,12 @@ def _real_main(argv=None):
         except (IOError, OSError) as err:
             if opts.verbose:
                 traceback.print_exc()
-            sys.stderr.write(u'ERROR: unable to open cookie file\n')
+            write_string(u'ERROR: unable to open cookie file\n')
             sys.exit(101)
     # Set user agent
     if opts.user_agent is not None:
         std_headers['User-Agent'] = opts.user_agent
-    
+
     # Set referer
     if opts.referer is not None:
         std_headers['Referer'] = opts.referer
@@ -398,6 +429,8 @@ def _real_main(argv=None):
             batchurls = batchfd.readlines()
             batchurls = [x.strip() for x in batchurls]
             batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+            if opts.verbose:
+                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
     all_urls = batchurls + args
@@ -418,6 +451,10 @@ def _real_main(argv=None):
     proxy_handler = compat_urllib_request.ProxyHandler(proxies)
     https_handler = make_HTTPS_handler(opts)
     opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
+    # Delete the default user-agent header, which would otherwise apply in
+    # cases where our custom HTTP handler doesn't come into play
+    # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
+    opener.addheaders =[]
     compat_urllib_request.install_opener(opener)
     socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
 
@@ -507,6 +544,11 @@ def _real_main(argv=None):
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
 
+    # --all-sub automatically sets --write-sub if --write-auto-sub is not given
+    # this was the old behaviour if only --all-sub was given.
+    if opts.allsubtitles and (opts.writeautomaticsub == False):
+        opts.writesubtitles = True
+
     if sys.version_info < (3,):
         # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
         if opts.outtmpl is not None:
@@ -519,7 +561,11 @@ def _real_main(argv=None):
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
             or u'%(title)s-%(id)s.%(ext)s')
-
+    if '%(ext)s' not in outtmpl and opts.extractaudio:
+        parser.error(u'Cannot download a video and extract audio into the same'
+                     u' file! Use "%%(ext)s" instead of %r' %
+                     determine_ext(outtmpl, u''))
+    raise ValueError(repr(opts.cachedir))
     # YoutubeDL
     ydl = YoutubeDL({
         'usenetrc': opts.usenetrc,
@@ -565,7 +611,7 @@ def _real_main(argv=None):
         'allsubtitles': opts.allsubtitles,
         'listsubtitles': opts.listsubtitles,
         'subtitlesformat': opts.subtitlesformat,
-        'subtitleslang': opts.subtitleslang,
+        'subtitleslangs': opts.subtitleslangs,
         'matchtitle': decodeOption(opts.matchtitle),
         'rejecttitle': decodeOption(opts.rejecttitle),
         'max_downloads': opts.max_downloads,
@@ -577,10 +623,12 @@ def _real_main(argv=None):
         'min_filesize': opts.min_filesize,
         'max_filesize': opts.max_filesize,
         'daterange': date,
+        'cachedir': opts.cachedir,
+        'youtube_print_sig_code': opts.youtube_print_sig_code,
         })
 
     if opts.verbose:
-        ydl.to_screen(u'[debug] youtube-dl version ' + __version__)
+        write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
         try:
             sp = subprocess.Popen(
                 ['git', 'rev-parse', '--short', 'HEAD'],
@@ -589,11 +637,14 @@ def _real_main(argv=None):
             out, err = sp.communicate()
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
-                ydl.to_screen(u'[debug] Git HEAD: ' + out)
+                write_string(u'[debug] Git HEAD: ' + out + u'\n')
         except:
-            sys.exc_clear()
-        ydl.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()))
-        ydl.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
+            try:
+                sys.exc_clear()
+            except:
+                pass
+        write_string(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
+        write_string(u'[debug] Proxy map: ' + str(proxy_handler.proxies) + u'\n')
 
     ydl.add_default_info_extractors()
 
@@ -602,6 +653,8 @@ def _real_main(argv=None):
         ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
     if opts.recodevideo:
         ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
+    if opts.embedsubtitles:
+        ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
 
     # Update version
     if opts.update_self:

youtube_dl/aes.py

@@ -0,0 +1,202 @@
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
+
+import base64
+from math import ceil
+
+from .utils import bytes_to_intlist, intlist_to_bytes
+
+BLOCK_SIZE_BYTES = 16
+
+def aes_ctr_decrypt(data, key, counter):
+    """
+    Decrypt with aes in counter mode
+    
+    @param {int[]} data        cipher
+    @param {int[]} key         16/24/32-Byte cipher key
+    @param {instance} counter  Instance whose next_value function (@returns {int[]}  16-Byte block)
+                               returns the next counter block
+    @returns {int[]}           decrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+    
+    decrypted_data=[]
+    for i in range(block_count):
+        counter_block = counter.next_value()
+        block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
+        block += [0]*(BLOCK_SIZE_BYTES - len(block))
+        
+        cipher_counter_block = aes_encrypt(counter_block, expanded_key)
+        decrypted_data += xor(block, cipher_counter_block)
+    decrypted_data = decrypted_data[:len(data)]
+    
+    return decrypted_data
+
+def key_expansion(data):
+    """
+    Generate key schedule
+    
+    @param {int[]} data  16/24/32-Byte cipher key
+    @returns {int[]}     176/208/240-Byte expanded key 
+    """
+    data = data[:] # copy
+    rcon_iteration = 1
+    key_size_bytes = len(data)
+    expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
+    
+    while len(data) < expanded_key_size_bytes:
+        temp = data[-4:]
+        temp = key_schedule_core(temp, rcon_iteration)
+        rcon_iteration += 1
+        data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        for _ in range(3):
+            temp = data[-4:]
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        if key_size_bytes == 32:
+            temp = data[-4:]
+            temp = sub_bytes(temp)
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        for _ in range(3 if key_size_bytes == 32  else 2 if key_size_bytes == 24 else 0):
+            temp = data[-4:]
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+    data = data[:expanded_key_size_bytes]
+    
+    return data
+
+def aes_encrypt(data, expanded_key):
+    """
+    Encrypt one block with aes
+    
+    @param {int[]} data          16-Byte state
+    @param {int[]} expanded_key  176/208/240-Byte expanded key 
+    @returns {int[]}             16-Byte cipher
+    """
+    rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
+    
+    data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
+    for i in range(1, rounds+1):
+        data = sub_bytes(data)
+        data = shift_rows(data)
+        if i != rounds:
+            data = mix_columns(data)
+        data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+    
+    return data
+
+def aes_decrypt_text(data, password, key_size_bytes):
+    """
+    Decrypt text
+    - The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter
+    - The cipher key is retrieved by encrypting the first 16 Byte of 'password'
+      with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
+    - Mode of operation is 'counter'
+    
+    @param {str} data                    Base64 encoded string
+    @param {str,unicode} password        Password (will be encoded with utf-8)
+    @param {int} key_size_bytes          Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
+    @returns {str}                       Decrypted data
+    """
+    NONCE_LENGTH_BYTES = 8
+    
+    data = bytes_to_intlist(base64.b64decode(data))
+    password = bytes_to_intlist(password.encode('utf-8'))
+    
+    key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password))
+    key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
+    
+    nonce = data[:NONCE_LENGTH_BYTES]
+    cipher = data[NONCE_LENGTH_BYTES:]
+    
+    class Counter:
+        __value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
+        def next_value(self):
+            temp = self.__value
+            self.__value = inc(self.__value)
+            return temp
+    
+    decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
+    plaintext = intlist_to_bytes(decrypted_data)
+    
+    return plaintext
+
+RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
+SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
+        0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
+        0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
+        0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
+        0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
+        0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
+        0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
+        0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
+        0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
+        0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
+        0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
+        0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
+        0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
+        0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
+        0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
+        0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
+MIX_COLUMN_MATRIX = ((2,3,1,1),
+                     (1,2,3,1),
+                     (1,1,2,3),
+                     (3,1,1,2))
+
+def sub_bytes(data):
+    return [SBOX[x] for x in data]
+
+def rotate(data):
+    return data[1:] + [data[0]]
+
+def key_schedule_core(data, rcon_iteration):
+    data = rotate(data)
+    data = sub_bytes(data)
+    data[0] = data[0] ^ RCON[rcon_iteration]
+    
+    return data
+
+def xor(data1, data2):
+    return [x^y for x, y in zip(data1, data2)]
+
+def mix_column(data):
+    data_mixed = []
+    for row in range(4):
+        mixed = 0
+        for column in range(4):
+            addend = data[column]
+            if MIX_COLUMN_MATRIX[row][column] in (2,3):
+                addend <<= 1
+                if addend > 0xff:
+                    addend &= 0xff
+                    addend ^= 0x1b
+                if MIX_COLUMN_MATRIX[row][column] == 3:
+                    addend ^= data[column]
+            mixed ^= addend & 0xff
+        data_mixed.append(mixed)
+    return data_mixed
+
+def mix_columns(data):
+    data_mixed = []
+    for i in range(4):
+        column = data[i*4 : (i+1)*4]
+        data_mixed += mix_column(column)
+    return data_mixed
+
+def shift_rows(data):
+    data_shifted = []
+    for column in range(4):
+        for row in range(4):
+            data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
+    return data_shifted
+
+def inc(data):
+    data = data[:] # copy
+    for i in range(len(data)-1,-1,-1):
+        if data[i] == 255:
+            data[i] = 0
+        else:
+            data[i] = data[i] + 1
+            break
+    return data

youtube_dl/extractor/__init__.py

@@ -1,51 +1,102 @@
+from .appletrailers import AppleTrailersIE
+from .addanime import AddAnimeIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE
 from .arte import ArteTvIE
 from .auengine import AUEngineIE
 from .bandcamp import BandcampIE
 from .bliptv import BlipTVIE, BlipTVUserIE
+from .bloomberg import BloombergIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
+from .c56 import C56IE
+from .canalplus import CanalplusIE
+from .canalc2 import Canalc2IE
+from .cnn import CNNIE
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE
+from .condenast import CondeNastIE
+from .criterion import CriterionIE
 from .cspan import CSpanIE
-from .dailymotion import DailymotionIE
+from .dailymotion import (
+    DailymotionIE,
+    DailymotionPlaylistIE,
+    DailymotionUserIE,
+)
+from .daum import DaumIE
 from .depositfiles import DepositFilesIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .defense import DefenseGouvFrIE
+from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .escapist import EscapistIE
+from .exfm import ExfmIE
 from .facebook import FacebookIE
+from .fktv import (
+    FKTVIE,
+    FKTVPosteckeIE,
+)
 from .flickr import FlickrIE
+from .francetv import (
+    PluzzIE,
+    FranceTvInfoIE,
+    France2IE,
+    GenerationQuoiIE
+)
+from .freesound import FreesoundIE
 from .funnyordie import FunnyOrDieIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .hark import HarkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .hypem import HypemIE
+from .ign import IGNIE, OneUPIE
 from .ina import InaIE
 from .infoq import InfoQIE
 from .instagram import InstagramIE
+from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
+from .kankan import KankanIE
+from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .liveleak import LiveLeakIE
+from .livestream import LivestreamIE
 from .metacafe import MetacafeIE
+from .metacritic import MetacriticIE
+from .mit import TechTVMITIE, MITIE
 from .mixcloud import MixcloudIE
 from .mtv import MTVIE
+from .muzu import MuzuTVIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
+from .naver import NaverIE
 from .nba import NBAIE
+from .nbc import NBCNewsIE
+from .newgrounds import NewgroundsIE
+from .ooyala import OoyalaIE
+from .orf import ORFIE
+from .pbs import PBSIE
 from .photobucket import PhotobucketIE
 from .pornotube import PornotubeIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
 from .ringtv import RingTVIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE
+from .ro220 import Ro220IE
+from .roxwel import RoxwelIE
+from .rtlnow import RTLnowIE
+from .sina import SinaIE
+from .slashdot import SlashdotIE
+from .slideshare import SlideshareIE
+from .sohu import SohuIE
+from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
+from .southparkstudios import SouthParkStudiosIE
 from .spiegel import SpiegelIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
@@ -53,17 +104,24 @@ from .steam import SteamIE
 from .teamcoco import TeamcocoIE
 from .ted import TEDIE
 from .tf1 import TF1IE
+from .thisav import ThisAVIE
 from .traileraddict import TrailerAddictIE
+from .trilulilu import TriluliluIE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
-from .ustream import UstreamIE
+from .unistra import UnistraIE
+from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
+from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vevo import VevoIE
-from .vimeo import VimeoIE
+from .vice import ViceIE
+from .videofyme import VideofyMeIE
+from .vimeo import VimeoIE, VimeoChannelIE
 from .vine import VineIE
 from .wat import WatIE
+from .weibo import WeiboIE
 from .wimp import WimpIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .xhamster import XHamsterIE
@@ -81,6 +139,9 @@ from .youtube import (
     YoutubeChannelIE,
     YoutubeShowIE,
     YoutubeSubscriptionsIE,
+    YoutubeRecommendedIE,
+    YoutubeWatchLaterIE,
+    YoutubeFavouritesIE,
 )
 from .zdf import ZDFIE
 
@@ -92,12 +153,14 @@ _ALL_CLASSES = [
 ]
 _ALL_CLASSES.append(GenericIE)
 
+
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
     """
     return [klass() for klass in _ALL_CLASSES]
 
+
 def get_info_extractor(ie_name):
     """Returns the info extractor class with the given ie_name"""
     return globals()[ie_name+'IE']

youtube_dl/extractor/addanime.py

@@ -0,0 +1,75 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_HTTPError,
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+
+    ExtractorError,
+)
+
+
+class AddAnimeIE(InfoExtractor):
+
+    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
+    IE_NAME = u'AddAnime'
+    _TEST = {
+        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+        u'file': u'24MR3YO5SAS9.flv',
+        u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1',
+        u'info_dict': {
+            u"description": u"One Piece 606",
+            u"title": u"One Piece 606"
+        }
+    }
+
+    def _real_extract(self, url):
+        try:
+            mobj = re.match(self._VALID_URL, url)
+            video_id = mobj.group('video_id')
+            webpage = self._download_webpage(url, video_id)
+        except ExtractorError as ee:
+            if not isinstance(ee.cause, compat_HTTPError):
+                raise
+
+            redir_webpage = ee.cause.read().decode('utf-8')
+            action = self._search_regex(
+                r'<form id="challenge-form" action="([^"]+)"',
+                redir_webpage, u'Redirect form')
+            vc = self._search_regex(
+                r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
+                redir_webpage, u'redirect vc value')
+            av = re.search(
+                r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
+                redir_webpage)
+            if av is None:
+                raise ExtractorError(u'Cannot find redirect math task')
+            av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
+
+            parsed_url = compat_urllib_parse_urlparse(url)
+            av_val = av_res + len(parsed_url.netloc)
+            confirm_url = (
+                parsed_url.scheme + u'://' + parsed_url.netloc +
+                action + '?' +
+                compat_urllib_parse.urlencode({
+                    'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
+            self._download_webpage(
+                confirm_url, video_id,
+                note=u'Confirming after redirect')
+            webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
+                                       webpage, u'video file URL')
+        video_title = self._og_search_title(webpage)
+        video_description = self._og_search_description(webpage)
+
+        return {
+            '_type': 'video',
+            'id':  video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': video_title,
+            'description': video_description
+        }

youtube_dl/extractor/appletrailers.py

@@ -0,0 +1,166 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class AppleTrailersIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+    _TEST = {
+        u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
+        u"playlist": [
+            {
+                u"file": u"manofsteel-trailer4.mov",
+                u"md5": u"11874af099d480cc09e103b189805d5f",
+                u"info_dict": {
+                    u"duration": 111,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
+                    u"title": u"Trailer 4",
+                    u"upload_date": u"20130523",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-trailer3.mov",
+                u"md5": u"07a0a262aae5afe68120eed61137ab34",
+                u"info_dict": {
+                    u"duration": 182,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
+                    u"title": u"Trailer 3",
+                    u"upload_date": u"20130417",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-trailer.mov",
+                u"md5": u"e401fde0813008e3307e54b6f384cff1",
+                u"info_dict": {
+                    u"duration": 148,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
+                    u"title": u"Trailer",
+                    u"upload_date": u"20121212",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-teaser.mov",
+                u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
+                u"info_dict": {
+                    u"duration": 93,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
+                    u"title": u"Teaser",
+                    u"upload_date": u"20120721",
+                    u"uploader_id": u"wb",
+                },
+            }
+        ]
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        movie = mobj.group('movie')
+        uploader_id = mobj.group('company')
+
+        playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
+        playlist_snippet = self._download_webpage(playlist_url, movie)
+        playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
+        playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+
+        size_cache = {}
+
+        doc = xml.etree.ElementTree.fromstring(playlist_html)
+        playlist = []
+        for li in doc.findall('./div/ul/li'):
+            title = li.find('.//h3').text
+            video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
+            thumbnail = li.find('.//img').attrib['src']
+
+            date_el = li.find('.//p')
+            upload_date = None
+            m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
+            if m:
+                upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
+            runtime_el = date_el.find('./br')
+            m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
+            duration = None
+            if m:
+                duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
+
+            formats = []
+            for formats_el in li.findall('.//a'):
+                if formats_el.attrib['class'] != 'OverlayPanel':
+                    continue
+                target = formats_el.attrib['target']
+
+                format_code = formats_el.text
+                if 'Automatic' in format_code:
+                    continue
+
+                size_q = formats_el.attrib['href']
+                size_id = size_q.rpartition('#videos-')[2]
+                if size_id not in size_cache:
+                    size_url = url + size_q
+                    sizepage_html = self._download_webpage(
+                        size_url, movie,
+                        note=u'Downloading size info %s' % size_id,
+                        errnote=u'Error while downloading size info %s' % size_id,
+                    )
+                    _doc = xml.etree.ElementTree.fromstring(sizepage_html)
+                    size_cache[size_id] = _doc
+
+                sizepage_doc = size_cache[size_id]
+                links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
+                for vid_a in links:
+                    href = vid_a.get('href')
+                    if not href.endswith(target):
+                        continue
+                    detail_q = href.partition('#')[0]
+                    detail_url = url + '/' + detail_q
+
+                    m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
+                    detail_id = m.group('detail_id')
+
+                    detail_html = self._download_webpage(
+                        detail_url, movie,
+                        note=u'Downloading detail %s %s' % (detail_id, size_id),
+                        errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
+                    )
+                    detail_doc = xml.etree.ElementTree.fromstring(detail_html)
+                    movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
+                    assert movie_link_el.get('class') == 'movieLink'
+                    movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
+                    ext = determine_ext(movie_link)
+                    assert ext == 'mov'
+
+                    formats.append({
+                        'format': format_code,
+                        'ext': ext,
+                        'url': movie_link,
+                    })
+
+            info = {
+                '_type': 'video',
+                'id': video_id,
+                'title': title,
+                'formats': formats,
+                'title': title,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'upload_date': upload_date,
+                'uploader_id': uploader_id,
+                'user_agent': 'QuickTime compatible (youtube-dl)',
+            }
+            # TODO: Remove when #980 has been merged
+            info['url'] = formats[-1]['url']
+            info['ext'] = formats[-1]['ext']
+
+            playlist.append(info)
+
+        return {
+            '_type': 'playlist',
+            'id': movie,
+            'entries': playlist,
+        }

youtube_dl/extractor/archiveorg.py

@@ -46,6 +46,8 @@ class ArchiveOrgIE(InfoExtractor):
             for fn,fdata in data['files'].items()
             if 'Video' in fdata['format']]
         formats.sort(key=lambda fdata: fdata['file_size'])
+        for f in formats:
+            f['ext'] = determine_ext(f['url'])
 
         info = {
             '_type': 'video',
@@ -61,7 +63,6 @@ class ArchiveOrgIE(InfoExtractor):
             info['thumbnail'] = thumbnail
 
         # TODO: Remove when #980 has been merged
-        info['url'] = formats[-1]['url']
-        info['ext'] = determine_ext(formats[-1]['url'])
+        info.update(formats[-1])
 
-        return info
+        return info

youtube_dl/extractor/arte.py

@@ -17,13 +17,14 @@ class ArteTvIE(InfoExtractor):
     """
     _EMISSION_URL = r'(?:http://)?www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
     _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
+    _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
     _LIVE_URL = r'index-[0-9]+\.html$'
 
     IE_NAME = u'arte.tv'
 
     @classmethod
     def suitable(cls, url):
-        return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL))
+        return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL, cls._LIVEWEB_URL))
 
     # TODO implement Live Stream
     # from ..utils import compat_urllib_parse
@@ -68,6 +69,12 @@ class ArteTvIE(InfoExtractor):
             lang = mobj.group('lang')
             return self._extract_video(url, id, lang)
 
+        mobj = re.match(self._LIVEWEB_URL, url)
+        if mobj is not None:
+            name = mobj.group('name')
+            lang = mobj.group('lang')
+            return self._extract_liveweb(url, name, lang)
+
         if re.search(self._LIVE_URL, video_id) is not None:
             raise ExtractorError(u'Arte live streams are not yet supported, sorry')
             # self.extractLiveStream(url)
@@ -85,7 +92,7 @@ class ArteTvIE(InfoExtractor):
 
         info_dict = {'id': player_info['VID'],
                      'title': player_info['VTI'],
-                     'description': player_info['VDE'],
+                     'description': player_info.get('VDE'),
                      'upload_date': unified_strdate(player_info['VDA'].split(' ')[0]),
                      'thumbnail': player_info['programImage'],
                      'ext': 'flv',
@@ -98,12 +105,14 @@ class ArteTvIE(InfoExtractor):
                 l = 'F'
             elif lang == 'de':
                 l = 'A'
-            regexes = [r'VO?%s' % l, r'V%s-ST.' % l]
+            regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
             return any(re.match(r, f['versionCode']) for r in regexes)
         # Some formats may not be in the same language as the url
         formats = filter(_match_lang, formats)
         # We order the formats by quality
         formats = sorted(formats, key=lambda f: int(f['height']))
+        # Prefer videos without subtitles in the same language
+        formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f['versionCode']) is None)
         # Pick the best quality
         format_info = formats[-1]
         if format_info['mediaType'] == u'rtmp':
@@ -144,3 +153,22 @@ class ArteTvIE(InfoExtractor):
                 'url': video_url,
                 'ext': 'flv',
                 }
+
+    def _extract_liveweb(self, url, name, lang):
+        """Extract form http://liveweb.arte.tv/"""
+        webpage = self._download_webpage(url, name)
+        video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
+        config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
+                                            video_id, u'Downloading information')
+        config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
+        event_doc = config_doc.find('event')
+        url_node = event_doc.find('video').find('urlHd')
+        if url_node is None:
+            url_node = video_doc.find('urlSd')
+
+        return {'id': video_id,
+                'title': event_doc.find('name%s' % lang.capitalize()).text,
+                'url': url_node.text.replace('MP4', 'mp4'),
+                'ext': 'flv',
+                'thumbnail': self._og_search_thumbnail(webpage),
+                }

youtube_dl/extractor/bloomberg.py

@@ -0,0 +1,27 @@
+import re
+
+from .common import InfoExtractor
+
+
+class BloombergIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html'
+
+    _TEST = {
+        u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
+        u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
+        u'info_dict': {
+            u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
+            u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
+        },
+        u'params': {
+            # Requires ffmpeg (m3u8 manifest)
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        webpage = self._download_webpage(url, name)
+        ooyala_url = self._og_search_video_url(webpage)
+        return self.url_result(ooyala_url, ie='Ooyala')

youtube_dl/extractor/breakcom.py

@@ -1,6 +1,8 @@
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
@@ -17,17 +19,20 @@ class BreakIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1).split("-")[-1]
-        webpage = self._download_webpage(url, video_id)
-        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
-        key = re.search(r"icon: '(.+?)',",webpage).group(1)
-        final_url = str(video_url)+"?"+str(key)
-        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
-        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
-        ext = video_url.split('.')[-1]
+        embed_url = 'http://www.break.com/embed/%s' % video_id
+        webpage = self._download_webpage(embed_url, video_id)
+        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
+                                       u'info json', flags=re.DOTALL)
+        info = json.loads(info_json)
+        video_url = info['videoUri']
+        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
+        if m_youtube is not None:
+            return self.url_result(m_youtube.group(1), 'Youtube')
+        final_url = video_url + '?' + info['AuthToken']
         return [{
             'id':        video_id,
             'url':       final_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
+            'ext':       determine_ext(final_url),
+            'title':     info['contentName'],
+            'thumbnail': info['thumbUri'],
         }]

youtube_dl/extractor/brightcove.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     find_xpath_attr,
+    compat_urlparse,
 )
 
 class BrightcoveIE(InfoExtractor):
@@ -39,15 +40,15 @@ class BrightcoveIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        query = mobj.group('query')
+        query_str = mobj.group('query')
+        query = compat_urlparse.parse_qs(query_str)
 
-        m_video_id = re.search(r'videoPlayer=(\d+)', query)
-        if m_video_id is not None:
-            video_id = m_video_id.group(1)
-            return self._get_video_info(video_id, query)
+        videoPlayer = query.get('@videoPlayer')
+        if videoPlayer:
+            return self._get_video_info(videoPlayer[0], query_str)
         else:
-            player_key = self._search_regex(r'playerKey=(.+?)(&|$)', query, 'playlist_id')
-            return self._get_playlist_info(player_key)
+            player_key = query['playerKey']
+            return self._get_playlist_info(player_key[0])
 
     def _get_video_info(self, video_id, query):
         request_url = self._FEDERATED_URL_TEMPLATE % query

youtube_dl/extractor/c56.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class C56IE(InfoExtractor):
+    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
+    IE_NAME = u'56.com'
+
+    _TEST ={
+        u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html',
+        u'file': u'93440716.flv',
+        u'md5': u'e59995ac63d0457783ea05f93f12a866',
+        u'info_dict': {
+            u'title': u'网事知多少 第32期：车怒',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        text_id = mobj.group('textid')
+        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
+                                           text_id, u'Downloading video info')
+        info = json.loads(info_page)['info']
+        best_format = sorted(info['rfiles'], key=lambda f: int(f['filesize']))[-1]
+        video_url = best_format['url']
+
+        return {'id': info['vid'],
+                'title': info['Subject'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': info.get('bimg') or info.get('img'),
+                }

youtube_dl/extractor/canalc2.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+
+
+class Canalc2IE(InfoExtractor):
+    IE_NAME = 'canalc2.tv'
+    _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
+
+    _TEST = {
+        u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        u'file': u'12163.mp4',
+        u'md5': u'060158428b650f896c542dfbb3d6487f',
+        u'info_dict': {
+            u'title': u'Terrasses du Numérique'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, video_id)
+        file_name = self._search_regex(
+            r"so\.addVariable\('file','(.*?)'\);",
+            webpage, 'file name')
+        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
+
+        title = self._html_search_regex(
+            r'class="evenement8">(.*?)</a>', webpage, u'title')
+        
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': title,
+                }

youtube_dl/extractor/canalplus.py

@@ -0,0 +1,54 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+class CanalplusIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
+    IE_NAME = u'canalplus.fr'
+
+    _TEST = {
+        u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+        u'file': u'922470.flv',
+        u'info_dict': {
+            u'title': u'Zapping - 26/08/13',
+            u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
+            u'upload_date': u'20130826',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        if video_id is None:
+            webpage = self._download_webpage(url, mobj.group('path'))
+            video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
+        info_url = self._VIDEO_INFO_TEMPLATE % video_id
+        info_page = self._download_webpage(info_url,video_id, 
+                                           u'Downloading video info')
+
+        self.report_extraction(video_id)
+        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
+        video_info = [video for video in doc if video.find('ID').text == video_id][0]
+        infos = video_info.find('INFOS')
+        media = video_info.find('MEDIA')
+        formats = [media.find('VIDEOS/%s' % format)
+            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
+        video_url = [format.text for format in formats if format is not None][-1]
+
+        return {'id': video_id,
+                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
+                                       infos.find('TITRAGE/SOUS_TITRE').text),
+                'url': video_url,
+                'ext': 'flv',
+                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
+                'thumbnail': media.find('IMAGES/GRAND').text,
+                'description': infos.find('DESCRIPTION').text,
+                'view_count': int(infos.find('NB_VUES').text),
+                }

youtube_dl/extractor/cnn.py

@@ -0,0 +1,58 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class CNNIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
+
+    _TESTS = [{
+        u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
+        u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
+        u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
+        u'info_dict': {
+            u'title': u'Nadal wins 8th French Open title',
+            u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
+        },
+    },
+    {
+        u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+        u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
+        u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
+        u"info_dict": {
+            u"title": "Student's epic speech stuns new freshmen",
+            u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        path = mobj.group('path')
+        page_title = mobj.group('title')
+        info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
+        info_xml = self._download_webpage(info_url, page_title)
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+
+        formats = []
+        for f in info.findall('files/file'):
+            mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
+            if mf is not None:
+                formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
+        formats = sorted(formats)
+        (_,_,_, video_path) = formats[-1]
+        video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
+
+        thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
+        thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
+
+        return {'id': info.attrib['id'],
+                'title': info.find('headline').text,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': thumbnails[-1][1],
+                'thumbnails': thumbs_dict,
+                'description': info.find('description').text,
+                }

youtube_dl/extractor/collegehumor.py

@@ -1,26 +1,36 @@
 import re
-import socket
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
     compat_urllib_parse_urlparse,
-    compat_urllib_request,
+    determine_ext,
 
     ExtractorError,
 )
 
 
 class CollegeHumorIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
 
-    def report_manifest(self, video_id):
-        """Report information extraction."""
-        self.to_screen(u'%s: Downloading XML manifest' % video_id)
+    _TESTS = [{
+        u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
+        u'file': u'6902724.mp4',
+        u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
+        u'info_dict': {
+            u'title': u'Comic-Con Cosplay Catastrophe',
+            u'description': u'Fans get creative this year at San Diego.  Too creative.  And yes, that\'s really Joss Whedon.',
+        },
+    },
+    {
+        u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
+        u'file': u'3505939.mp4',
+        u'md5': u'c51ca16b82bb456a4397987791a835f5',
+        u'info_dict': {
+            u'title': u'Font Conference',
+            u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -36,39 +46,42 @@ class CollegeHumorIE(InfoExtractor):
 
         self.report_extraction(video_id)
         xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
-        try:
-            metaXml = compat_urllib_request.urlopen(xmlUrl).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+        metaXml = self._download_webpage(xmlUrl, video_id,
+                                         u'Downloading info XML',
+                                         u'Unable to download video info XML')
 
         mdoc = xml.etree.ElementTree.fromstring(metaXml)
         try:
             videoNode = mdoc.findall('./video')[0]
+            youtubeIdNode = videoNode.find('./youtubeID')
+            if youtubeIdNode is not None:
+                return self.url_result(youtubeIdNode.text, 'Youtube')
             info['description'] = videoNode.findall('./description')[0].text
             info['title'] = videoNode.findall('./caption')[0].text
             info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
-            manifest_url = videoNode.findall('./file')[0].text
+            next_url = videoNode.findall('./file')[0].text
         except IndexError:
             raise ExtractorError(u'Invalid metadata XML file')
 
-        manifest_url += '?hdcore=2.10.3'
-        self.report_manifest(video_id)
-        try:
-            manifestXml = compat_urllib_request.urlopen(manifest_url).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+        if next_url.endswith(u'manifest.f4m'):
+            manifest_url = next_url + '?hdcore=2.10.3'
+            manifestXml = self._download_webpage(manifest_url, video_id,
+                                         u'Downloading XML manifest',
+                                         u'Unable to download video info XML')
 
-        adoc = xml.etree.ElementTree.fromstring(manifestXml)
-        try:
-            media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
-            node_id = media_node.attrib['url']
-            video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
-        except IndexError as err:
-            raise ExtractorError(u'Invalid manifest file')
+            adoc = xml.etree.ElementTree.fromstring(manifestXml)
+            try:
+                media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
+                node_id = media_node.attrib['url']
+                video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
+            except IndexError as err:
+                raise ExtractorError(u'Invalid manifest file')
+            url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
+            info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
+            info['ext'] = 'mp4'
+        else:
+            # Old-style direct links
+            info['url'] = next_url
+            info['ext'] = determine_ext(info['url'])
 
-        url_pr = compat_urllib_parse_urlparse(manifest_url)
-        url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
-
-        info['url'] = url
-        info['ext'] = 'f4f'
-        return [info]
+        return info

youtube_dl/extractor/comedycentral.py

@@ -24,7 +24,9 @@ class ComedyCentralIE(InfoExtractor):
                          (full-episodes/(?P<episode>.*)|
                           (?P<clip>
                               (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                          (?P<interview>
+                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
                      $"""
     _TEST = {
         u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
@@ -87,6 +89,9 @@ class ComedyCentralIE(InfoExtractor):
             else:
                 epTitle = mobj.group('cntitle')
             dlNewest = False
+        elif mobj.group('interview'):
+            epTitle = mobj.group('interview_title')
+            dlNewest = False
         else:
             dlNewest = not mobj.group('episode')
             if dlNewest:

youtube_dl/extractor/common.py

@@ -14,6 +14,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    unescapeHTML,
 )
 
 class InfoExtractor(object):
@@ -46,7 +47,8 @@ class InfoExtractor(object):
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     player_url:     SWF Player URL (used for rtmpdump).
-    subtitles:      The subtitle file contents.
+    subtitles:      The subtitle file contents as a dictionary in the format
+                    {language: subtitles}.
     view_count:     How many users have watched the video on the platform.
     urlhandle:      [internal] The urlHandle to be used to download the file,
                     like returned by urllib.request.urlopen
@@ -76,7 +78,13 @@ class InfoExtractor(object):
     @classmethod
     def suitable(cls, url):
         """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url) is not None
+
+        # This does not use has/getattr intentionally - we want to know whether
+        # we have cached the regexp for *this* class, whereas getattr would also
+        # match the superclass
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        return cls._VALID_URL_RE.match(url) is not None
 
     @classmethod
     def working(cls):
@@ -106,6 +114,11 @@ class InfoExtractor(object):
         """Real extraction process. Redefine in subclasses."""
         pass
 
+    @classmethod
+    def ie_key(cls):
+        """A string for getting the InfoExtractor with get_info_extractor"""
+        return cls.__name__[:-2]
+
     @property
     def IE_NAME(self):
         return type(self).__name__[:-2]
@@ -121,18 +134,28 @@ class InfoExtractor(object):
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is None:
                 errnote = u'Unable to download webpage'
-            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
         """ Returns a tuple (page content as string, URL handle) """
+
+        # Strip hashes from the URL (#1038)
+        if isinstance(url_or_request, (compat_str, str)):
+            url_or_request = url_or_request.partition('#')[0]
+
         urlh = self._request_webpage(url_or_request, video_id, note, errnote)
         content_type = urlh.headers.get('Content-Type', '')
+        webpage_bytes = urlh.read()
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
         else:
-            encoding = 'utf-8'
-        webpage_bytes = urlh.read()
+            m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
+                          webpage_bytes[:1024])
+            if m:
+                encoding = m.group(1).decode('ascii')
+            else:
+                encoding = 'utf-8'
         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()
@@ -257,6 +280,31 @@ class InfoExtractor(object):
         
         return (username, password)
 
+    # Helper functions for extracting OpenGraph info
+    @staticmethod
+    def _og_regex(prop):
+        return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+
+    def _og_search_property(self, prop, html, name=None, **kargs):
+        if name is None:
+            name = 'OpenGraph %s' % prop
+        escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+        return unescapeHTML(escaped)
+
+    def _og_search_thumbnail(self, html, **kargs):
+        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+
+    def _og_search_description(self, html, **kargs):
+        return self._og_search_property('description', html, fatal=False, **kargs)
+
+    def _og_search_title(self, html, **kargs):
+        return self._og_search_property('title', html, **kargs)
+
+    def _og_search_video_url(self, html, name='video url', **kargs):
+        return self._html_search_regex([self._og_regex('video:secure_url'),
+                                        self._og_regex('video')],
+                                       html, name, **kargs)
+
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.

youtube_dl/extractor/condenast.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    orderedSet,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+
+
+class CondeNastIE(InfoExtractor):
+    """
+    Condé Nast is a media group, some of its sites use a custom HTML5 player
+    that works the same in all of them.
+    """
+
+    # The keys are the supported sites and the values are the name to be shown
+    # to the user and in the extractor description.
+    _SITES = {'wired': u'WIRED',
+              'gq': u'GQ',
+              'vogue': u'Vogue',
+              'glamour': u'Glamour',
+              'wmagazine': u'W Magazine',
+              'vanityfair': u'Vanity Fair',
+              }
+
+    _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
+    IE_DESC = u'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
+
+    _TEST = {
+        u'url': u'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
+        u'file': u'5171b343c2b4c00dd0c1ccb3.mp4',
+        u'md5': u'1921f713ed48aabd715691f774c451f7',
+        u'info_dict': {
+            u'title': u'3D Printed Speakers Lit With LED',
+            u'description': u'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+        }
+    }
+
+    def _extract_series(self, url, webpage):
+        title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
+                                        webpage, u'series title', flags=re.DOTALL)
+        url_object = compat_urllib_parse_urlparse(url)
+        base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
+        m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
+                              webpage, flags=re.DOTALL)
+        paths = orderedSet(m.group(1) for m in m_paths)
+        build_url = lambda path: compat_urlparse.urljoin(base_url, path)
+        entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
+        return self.playlist_result(entries, playlist_title=title)
+
+    def _extract_video(self, webpage):
+        description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
+                                               r'<div class="video-post-content">(.+?)</div>',
+                                               ],
+                                              webpage, u'description',
+                                              fatal=False, flags=re.DOTALL)
+        params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
+                                    u'player params', flags=re.DOTALL)
+        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id')
+        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id')
+        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target')
+        data = compat_urllib_parse.urlencode({'videoId': video_id,
+                                              'playerId': player_id,
+                                              'target': target,
+                                              })
+        base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
+                                           webpage, u'base info url',
+                                           default='http://player.cnevids.com/player/loader.js?')
+        info_url = base_info_url + data
+        info_page = self._download_webpage(info_url, video_id,
+                                           u'Downloading video info')
+        video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info')
+        video_info = json.loads(video_info)
+
+        def _formats_sort_key(f):
+            type_ord = 1 if f['type'] == 'video/mp4' else 0
+            quality_ord = 1 if f['quality'] == 'high' else 0
+            return (quality_ord, type_ord)
+        best_format = sorted(video_info['sources'][0], key=_formats_sort_key)[-1]
+
+        return {'id': video_id,
+                'url': best_format['src'],
+                'ext': best_format['type'].split('/')[-1],
+                'title': video_info['title'],
+                'thumbnail': video_info['poster_frame'],
+                'description': description,
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        site = mobj.group('site')
+        url_type = mobj.group('type')
+        id = mobj.group('id')
+
+        self.to_screen(u'Extracting from %s with the Condé Nast extractor' % self._SITES[site])
+        webpage = self._download_webpage(url, id)
+
+        if url_type == 'series':
+            return self._extract_series(url, webpage)
+        else:
+            return self._extract_video(webpage)

youtube_dl/extractor/criterion.py

@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class CriterionIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
+    _TEST = {
+        u'url': u'http://www.criterion.com/films/184-le-samourai',
+        u'file': u'184.mp4',
+        u'md5': u'bc51beba55685509883a9a7830919ec3',
+        u'info_dict': {
+            u"title": u"Le Samouraï",
+            u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+
+        final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
+                                webpage, 'video url')
+        title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
+                                webpage, 'video title')
+        description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
+                                webpage, 'video description')
+        thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+                                webpage, 'thumbnail url')
+
+        return {'id': video_id,
+                'url' : final_url,
+                'title': title,
+                'ext': determine_ext(final_url),
+                'description': description,
+                'thumbnail': thumbnail,
+                }

youtube_dl/extractor/cspan.py

@@ -34,8 +34,6 @@ class CSpanIE(InfoExtractor):
         description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
                                               webpage, 'description',
                                               flags=re.MULTILINE|re.DOTALL)
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"',
-                                            webpage, 'thumbnail')
 
         url = self._search_regex(r'<string name="URL">(.*?)</string>',
                                  video_info, 'video url')
@@ -49,5 +47,5 @@ class CSpanIE(InfoExtractor):
                 'url': url,
                 'play_path': path,
                 'description': description,
-                'thumbnail': thumbnail,
+                'thumbnail': self._og_search_thumbnail(webpage),
                 }

youtube_dl/extractor/dailymotion.py

@@ -1,24 +1,31 @@
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
+
 from ..utils import (
     compat_urllib_request,
+    compat_str,
+    get_element_by_attribute,
+    get_element_by_id,
 
     ExtractorError,
 )
 
-class DailymotionIE(InfoExtractor):
+
+class DailymotionIE(SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
-    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
+    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
     IE_NAME = u'dailymotion'
     _TEST = {
         u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
         u'file': u'x33vw9.mp4',
         u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
         u'info_dict': {
-            u"uploader": u"Alex and Van .", 
+            u"uploader": u"Amphora Alex and Van .", 
             u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
         }
     }
@@ -30,6 +37,7 @@ class DailymotionIE(InfoExtractor):
         video_id = mobj.group(1).split('_')[0].split('?')[0]
 
         video_extension = 'mp4'
+        url = 'http://www.dailymotion.com/video/%s' % video_id
 
         # Retrieve video webpage to extract further information
         request = compat_urllib_request.Request(url)
@@ -39,9 +47,6 @@ class DailymotionIE(InfoExtractor):
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.*?)" />',
-                                              webpage, 'title')
-
         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
                                              # Looking for official user
                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
@@ -55,8 +60,12 @@ class DailymotionIE(InfoExtractor):
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
                                             u'Downloading embed page')
-        info = self._search_regex(r'var info = ({.*?}),', embed_page, 'video info')
+        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
+            'video info', flags=re.MULTILINE)
         info = json.loads(info)
+        if info.get('error') is not None:
+            msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
+            raise ExtractorError(msg, expected=True)
 
         # TODO: support choosing qualities
 
@@ -71,12 +80,88 @@ class DailymotionIE(InfoExtractor):
             raise ExtractorError(u'Unable to extract video URL')
         video_url = info[max_quality]
 
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id)
+            return
+
         return [{
             'id':       video_id,
             'url':      video_url,
             'uploader': video_uploader,
             'upload_date':  video_upload_date,
-            'title':    video_title,
+            'title':    self._og_search_title(webpage),
             'ext':      video_extension,
+            'subtitles':    video_subtitles,
             'thumbnail': info['thumbnail_url']
         }]
+
+    def _get_available_subtitles(self, video_id):
+        try:
+            sub_list = self._download_webpage(
+                'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
+                video_id, note=False)
+        except ExtractorError as err:
+            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            return {}
+        info = json.loads(sub_list)
+        if (info['total'] > 0):
+            sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
+            return sub_lang_list
+        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        return {}
+
+
+class DailymotionPlaylistIE(InfoExtractor):
+    IE_NAME = u'dailymotion:playlist'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
+    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+    _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+
+    def _extract_entries(self, id):
+        video_ids = []
+        for pagenum in itertools.count(1):
+            webpage = self._download_webpage(self._PAGE_TEMPLATE % (id, pagenum),
+                                             id, u'Downloading page %s' % pagenum)
+
+            playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
+            video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
+
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+        return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                   for video_id in video_ids]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        webpage = self._download_webpage(url, playlist_id)
+
+        return {'_type': 'playlist',
+                'id': playlist_id,
+                'title': get_element_by_id(u'playlist_name', webpage),
+                'entries': self._extract_entries(playlist_id),
+                }
+
+
+class DailymotionUserIE(DailymotionPlaylistIE):
+    IE_NAME = u'dailymotion:user'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
+    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
+    _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        user = mobj.group('user')
+        webpage = self._download_webpage(url, user)
+        full_user = self._html_search_regex(
+            r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
+            webpage, u'user', flags=re.DOTALL)
+
+        return {
+            '_type': 'playlist',
+            'id': user,
+            'title': full_user,
+            'entries': self._extract_entries(user),
+        }

youtube_dl/extractor/daum.py

@@ -0,0 +1,74 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    determine_ext,
+)
+
+
+class DaumIE(InfoExtractor):
+    _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    IE_NAME = u'daum.net'
+
+    _TEST = {
+        u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        u'file': u'52554690.mp4',
+        u'info_dict': {
+            u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
+            u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
+            u'upload_date': u'20130831',
+            u'duration': 3868,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
+        webpage = self._download_webpage(canonical_url, video_id)
+        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
+            webpage, u'full id')
+        query = compat_urllib_parse.urlencode({'vid': full_id})
+        info_xml = self._download_webpage(
+            'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
+            u'Downloading video info')
+        urls_xml = self._download_webpage(
+            'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
+            video_id, u'Downloading video formats info')
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+
+        self.to_screen(u'%s: Getting video urls' % video_id)
+        formats = []
+        for format_el in urls.findall('result/output_list/output_list'):
+            profile = format_el.attrib['profile']
+            format_query = compat_urllib_parse.urlencode({
+                'vid': full_id,
+                'profile': profile,
+            })
+            url_xml = self._download_webpage(
+                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
+                video_id, note=False)
+            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
+            format_url = url_doc.find('result/url').text
+            formats.append({
+                'url': format_url,
+                'ext': determine_ext(format_url),
+                'format_id': profile,
+            })
+
+        info = {
+            'id': video_id,
+            'title': info.find('TITLE').text,
+            'formats': formats,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': info.find('CONTENTS').text,
+            'duration': int(info.find('DURATION').text),
+            'upload_date': info.find('REGDTTM').text[:8],
+        }
+        # TODO: Remove when #980 has been merged
+        info.update(formats[-1])
+        return info

youtube_dl/extractor/defense.py

@@ -0,0 +1,39 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class DefenseGouvFrIE(InfoExtractor):
+    _IE_NAME = 'defense.gouv.fr'
+    _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
+        r'ligthboxvideo/base-de-medias/webtv/(.*)')
+
+    _TEST = {
+        u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/'
+        u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'),
+        u'file': u'11213.mp4',
+        u'md5': u'75bba6124da7e63d2d60b5244ec9430c',
+        "info_dict": {
+            "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+        }
+    }
+
+    def _real_extract(self, url):
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        video_id = self._search_regex(
+            r"flashvars.pvg_id=\"(\d+)\";",
+            webpage, 'ID')
+        
+        json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
+            + video_id)
+        info = self._download_webpage(json_url, title,
+                                                  'Downloading JSON config')
+        video_url = json.loads(info)['renditions'][0]['url']
+        
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': title,
+                }

youtube_dl/extractor/dreisat.py

@@ -54,6 +54,7 @@ class DreiSatIE(InfoExtractor):
             'width': int(fe.find('./width').text),
             'height': int(fe.find('./height').text),
             'url': fe.find('./url').text,
+            'ext': determine_ext(fe.find('./url').text),
             'filesize': int(fe.find('./filesize').text),
             'video_bitrate': int(fe.find('./videoBitrate').text),
             '3sat_qualityname': fe.find('./quality').text,
@@ -79,7 +80,6 @@ class DreiSatIE(InfoExtractor):
         }
 
         # TODO: Remove when #980 has been merged
-        info['url'] = formats[-1]['url']
-        info['ext'] = determine_ext(formats[-1]['url'])
+        info.update(formats[-1])
 
-        return info
+        return info

youtube_dl/extractor/ebaumsworld.py

@@ -0,0 +1,37 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class EbaumsWorldIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.ebaumsworld.com/video/watch/83367677/',
+        u'file': u'83367677.mp4',
+        u'info_dict': {
+            u'title': u'A Giant Python Opens The Door',
+            u'description': u'This is how nightmares start...',
+            u'uploader': u'jihadpizza',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        config_xml = self._download_webpage(
+            'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
+        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
+        video_url = config.find('file').text
+
+        return {
+            'id': video_id,
+            'title': config.find('title').text,
+            'url': video_url,
+            'ext': determine_ext(video_url),
+            'description': config.find('description').text,
+            'thumbnail': config.find('image').text,
+            'uploader': config.find('username').text,
+        }

youtube_dl/extractor/ehow.py

@@ -28,14 +28,9 @@ class EHowIE(InfoExtractor):
         video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
             webpage, u'video URL')
         final_url = compat_urllib_parse.unquote(video_url)        
-        thumbnail_url = self._search_regex(r'<meta property="og:image" content="(.+?)" />',
-            webpage, u'thumbnail URL')
         uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
             webpage, u'uploader')
-        title = self._search_regex(r'<meta property="og:title" content="(.+?)" />',
-            webpage, u'Video title').replace(' | eHow', '')
-        description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
-            webpage, u'video description')
+        title = self._og_search_title(webpage).replace(' | eHow', '')
         ext = determine_ext(final_url)
 
         return {
@@ -44,8 +39,8 @@ class EHowIE(InfoExtractor):
             'url':         final_url,
             'ext':         ext,
             'title':       title,
-            'thumbnail':   thumbnail_url,
-            'description': description,
+            'thumbnail':   self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
             'uploader':    uploader,
         }
 

youtube_dl/extractor/escapist.py

@@ -36,11 +36,7 @@ class EscapistIE(InfoExtractor):
         videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
             webpage, u'description', fatal=False)
 
-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
-
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
+        playerUrl = self._og_search_video_url(webpage, name='player url')
 
         title = self._html_search_regex('<meta name="title" content="([^"]*)"',
             webpage, u'player url').split(' : ')[-1]
@@ -70,7 +66,7 @@ class EscapistIE(InfoExtractor):
             'upload_date': None,
             'title': title,
             'ext': 'mp4',
-            'thumbnail': imgUrl,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'description': videoDesc,
             'player_url': playerUrl,
         }

youtube_dl/extractor/exfm.py

@@ -0,0 +1,54 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class ExfmIE(InfoExtractor):
+    IE_NAME = u'exfm'
+    IE_DESC = u'ex.fm'
+    _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
+    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
+    _TESTS = [
+        {
+            u'url': u'http://ex.fm/song/1bgtzg',
+            u'file': u'95223130.mp3',
+            u'md5': u'8a7967a3fef10e59a1d6f86240fd41cf',
+            u'info_dict': {
+                u"title": u"We Can't Stop - Miley Cyrus",
+                u"uploader": u"Miley Cyrus",
+                u'upload_date': u'20130603',
+                u'description': u'Download "We Can\'t Stop" \r\niTunes: http://smarturl.it/WeCantStop?IQid=SC\r\nAmazon: http://smarturl.it/WeCantStopAMZ?IQid=SC',
+            },
+            u'note': u'Soundcloud song',
+        },
+        {
+            u'url': u'http://ex.fm/song/wddt8',
+            u'file': u'wddt8.mp3',
+            u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
+            u'info_dict': {
+                u'title': u'Safe and Sound',
+                u'uploader': u'Capital Cities',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        song_id = mobj.group(1)
+        info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
+        webpage = self._download_webpage(info_url, song_id)
+        info = json.loads(webpage)
+        song_url = info['song']['url']
+        if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
+            self.to_screen('Soundcloud song detected')
+            return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
+        return [{
+            'id':          song_id,
+            'url':         song_url,
+            'ext':         'mp3',
+            'title':       info['song']['title'],
+            'thumbnail':   info['song']['image']['large'],
+            'uploader':    info['song']['artist'],
+            'view_count':  info['song']['loved_count'],
+        }]

youtube_dl/extractor/facebook.py

@@ -106,8 +106,8 @@ class FacebookIE(InfoExtractor):
         video_duration = int(video_data['video_duration'])
         thumbnail = video_data['thumbnail_src']
 
-        video_title = self._html_search_regex('<h2 class="uiHeaderTitle">([^<]+)</h2>',
-            webpage, u'title')
+        video_title = self._html_search_regex(
+            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, u'title')
 
         info = {
             'id': video_id,

youtube_dl/extractor/fktv.py

@@ -0,0 +1,79 @@
+import re
+import random
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    get_element_by_id,
+    clean_html,
+)
+
+
+class FKTVIE(InfoExtractor):
+    IE_NAME = u'fernsehkritik.tv'
+    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+
+    _TEST = {
+        u'url': u'http://fernsehkritik.tv/folge-1',
+        u'file': u'00011.flv',
+        u'info_dict': {
+            u'title': u'Folge 1 vom 10. April 2007',
+            u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        episode = int(mobj.group('ep'))
+
+        server = random.randint(2, 4)
+        video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
+        start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
+            episode)
+        playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
+            u'playlist', flags=re.DOTALL)
+        files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
+        # TODO: return a single multipart video
+        videos = []
+        for i, _ in enumerate(files, 1):
+            video_id = '%04d%d' % (episode, i)
+            video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
+            video_title = 'Fernsehkritik %d.%d' % (episode, i)
+            videos.append({
+                'id': video_id,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'title': clean_html(get_element_by_id('eptitle', start_webpage)),
+                'description': clean_html(get_element_by_id('contentlist', start_webpage)),
+                'thumbnail': video_thumbnail
+            })
+        return videos
+
+
+class FKTVPosteckeIE(InfoExtractor):
+    IE_NAME = u'fernsehkritik.tv:postecke'
+    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
+    _TEST = {
+        u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
+        u'file': u'0120.flv',
+        u'md5': u'262f0adbac80317412f7e57b4808e5c4',
+        u'info_dict': {
+            u"title": u"Postecke 120"
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        episode = int(mobj.group('ep'))
+
+        server = random.randint(2, 4)
+        video_id = '%04d' % episode
+        video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
+        video_title = 'Postecke %d' % episode
+        return {
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      determine_ext(video_url),
+            'title':    video_title,
+        }

youtube_dl/extractor/flickr.py

@@ -47,21 +47,12 @@ class FlickrIE(InfoExtractor):
             raise ExtractorError(u'Unable to extract video url')
         video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'video title')
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'description', fatal=False)
-
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'thumbnail', fatal=False)
-
         return [{
             'id':          video_id,
             'url':         video_url,
             'ext':         'mp4',
-            'title':       video_title,
-            'description': video_description,
-            'thumbnail':   thumbnail,
+            'title':       self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail':   self._og_search_thumbnail(webpage),
             'uploader_id': video_uploader_id,
         }]

youtube_dl/extractor/francetv.py

@@ -0,0 +1,117 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+)
+
+
+class FranceTVBaseInfoExtractor(InfoExtractor):
+    def _extract_video(self, video_id):
+        xml_desc = self._download_webpage(
+            'http://www.francetvinfo.fr/appftv/webservices/video/'
+            'getInfosOeuvre.php?id-diffusion='
+            + video_id, video_id, 'Downloading XML config')
+        info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
+
+        manifest_url = info.find('videos/video/url').text
+        video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
+        video_url = video_url.replace('/z/', '/i/')
+        thumbnail_path = info.find('image').text
+
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': info.find('titre').text,
+                'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
+                'description': info.find('synopsis').text,
+                }
+
+
+class PluzzIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'pluzz.francetv.fr'
+    _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
+
+    # Can't use tests, videos expire in 7 days
+
+    def _real_extract(self, url):
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        video_id = self._search_regex(
+            r'data-diffusion="(\d+)"', webpage, 'ID')
+        return self._extract_video(video_id)
+
+
+class FranceTvInfoIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'francetvinfo.fr'
+    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
+
+    _TEST = {
+        u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        u'file': u'84981923.mp4',
+        u'info_dict': {
+            u'title': u'Soir 3',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_title = mobj.group('title')
+        webpage = self._download_webpage(url, page_title)
+        video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+        return self._extract_video(video_id)
+
+
+class France2IE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'france2.fr'
+    _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+        u'file': u'75540104.mp4',
+        u'info_dict': {
+            u'title': u'13h15, le samedi...',
+            u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        return self._extract_video(video_id)
+
+
+class GenerationQuoiIE(InfoExtractor):
+    IE_NAME = u'http://generation-quoi.france2.fr'
+    _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
+
+    _TEST = {
+        u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+        u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
+        u'info_dict': {
+            u'title': u'Génération Quoi - Garde à Vous',
+            u'uploader': u'Génération Quoi',
+        },
+        u'params': {
+            # It uses Dailymotion
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
+        info_json = self._download_webpage(info_url, name)
+        info = json.loads(info_json)
+        return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
+            ie='Dailymotion')

youtube_dl/extractor/freesound.py

@@ -0,0 +1,36 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class FreesoundIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _TEST = {
+        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
+        u'file': u'194503.mp3',
+        u'md5': u'12280ceb42c81f19a515c745eae07650',
+        u'info_dict': {
+            u"title": u"gulls in the city.wav",
+            u"uploader" : u"miklovan",
+            u'description': u'the sounds of seagulls in the city',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        music_id = mobj.group('id')
+        webpage = self._download_webpage(url, music_id)
+        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+                                webpage, 'music title', flags=re.DOTALL)
+        music_url = self._og_search_property('audio', webpage, 'music url')
+        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
+                                webpage, 'description', fatal=False, flags=re.DOTALL)
+
+        return [{
+            'id':       music_id,
+            'title':    title,            
+            'url':      music_url,
+            'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
+            'ext':      determine_ext(music_url),
+            'description': description,
+        }]

youtube_dl/extractor/funnyordie.py

@@ -21,20 +21,15 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
+        video_url = self._search_regex(
+            [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
             webpage, u'video URL', flags=re.DOTALL)
 
-        title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
-            r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
-            webpage, u'description', fatal=False, flags=re.DOTALL)
-
         info = {
             'id': video_id,
             'url': video_url,
             'ext': 'mp4',
-            'title': title,
-            'description': video_description,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
         }
         return [info]

youtube_dl/extractor/gamespot.py

@@ -14,7 +14,7 @@ class GameSpotIE(InfoExtractor):
         u"file": u"6410818.mp4",
         u"md5": u"b2a30deaa8654fcccd43713a6b6a4825",
         u"info_dict": {
-            u"title": u"Arma III - Community Guide: SITREP I",
+            u"title": u"Arma 3 - Community Guide: SITREP I",
             u"upload_date": u"20130627", 
         }
     }

youtube_dl/extractor/gametrailers.py

@@ -1,63 +1,36 @@
 import re
-import xml.etree.ElementTree
 
-from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
+from .mtv import MTVIE, _media_xml_tag
 
-    ExtractorError,
-)
-
-class GametrailersIE(InfoExtractor):
+class GametrailersIE(MTVIE):
+    """
+    Gametrailers use the same videos system as MTVIE, it just changes the feed
+    url, where the uri is and the method to get the thumbnails.
+    """
     _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
         u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.flv',
-        u'md5': u'c3edbc995ab4081976e16779bd96a878',
+        u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
+        u'md5': u'4c8e67681a0ea7ec241e8c09b3ea8cf7',
         u'info_dict': {
-            u"title": u"E3 2013: Debut Trailer"
+            u'title': u'E3 2013: Debut Trailer',
+            u'description': u'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
         },
-        u'skip': u'Requires rtmpdump'
     }
+    # Overwrite MTVIE properties we don't want
+    _TESTS = []
+
+    _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+        return itemdoc.find(search_path).attrib['url']
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         mgid = self._search_regex([r'data-video="(?P<mgid>mgid:.*?)"',
                                    r'data-contentId=\'(?P<mgid>mgid:.*?)\''],
                                   webpage, u'mgid')
-
-        data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
-        info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
-                                           video_id, u'Downloading video info')
-        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
-        default_thumb = doc.find('./channel/image/url').text
-
-        media_namespace = {'media': 'http://search.yahoo.com/mrss/'}
-        parts = [{
-            'title': video_doc.find('title').text,
-            'ext': 'flv',
-            'id': video_doc.find('guid').text.rpartition(':')[2],
-            # Videos are actually flv not mp4
-            'url': self._get_video_url(video_doc.find('media:group/media:content', media_namespace).attrib['url'], video_id),
-            # The thumbnail may not be defined, it would be ''
-            'thumbnail': video_doc.find('media:group/media:thumbnail', media_namespace).attrib['url'] or default_thumb,
-            'description': video_doc.find('description').text,
-        } for video_doc in doc.findall('./channel/item')]
-        return parts
-
-    def _get_video_url(self, mediagen_url, video_id):
-        if 'acceptMethods' not in mediagen_url:
-            mediagen_url += '&acceptMethods=fms'
-        links_webpage = self._download_webpage(mediagen_url,
-                                               video_id, u'Downloading video urls info')
-        doc = xml.etree.ElementTree.fromstring(links_webpage)
-        urls = list(doc.iter('src'))
-        if len(urls) == 0:
-            raise ExtractorError(u'Unable to extract video url')
-        # They are sorted from worst to best quality
-        return urls[-1].text
-
+        return self._get_videos_info(mgid)

youtube_dl/extractor/generic.py

@@ -8,11 +8,13 @@ from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+    compat_urlparse,
 
     ExtractorError,
 )
 from .brightcove import BrightcoveIE
 
+
 class GenericIE(InfoExtractor):
     IE_DESC = u'Generic downloader that works on some sites'
     _VALID_URL = r'.*'
@@ -23,7 +25,7 @@ class GenericIE(InfoExtractor):
             u'file': u'13601338388002.mp4',
             u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89',
             u'info_dict': {
-                u"uploader": u"www.hodiho.fr", 
+                u"uploader": u"www.hodiho.fr",
                 u"title": u"R\u00e9gis plante sa Jeep"
             }
         },
@@ -107,8 +109,18 @@ class GenericIE(InfoExtractor):
         return new_url
 
     def _real_extract(self, url):
-        new_url = self._test_redirect(url)
-        if new_url: return [self.url_result(new_url)]
+        parsed_url = compat_urlparse.urlparse(url)
+        if not parsed_url.scheme:
+            self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+            return self.url_result('http://' + url)
+
+        try:
+            new_url = self._test_redirect(url)
+            if new_url:
+                return [self.url_result(new_url)]
+        except compat_urllib_error.HTTPError:
+            # This may be a stupid server that doesn't like HEAD, our UA, or so
+            pass
 
         video_id = url.split('/')[-1]
         try:
@@ -119,8 +131,8 @@ class GenericIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         self.report_extraction(video_id)
-        # Look for BrigthCove:
-        m_brightcove = re.search(r'<object.+?class=".*?BrightcoveExperience.*?".+?</object>', webpage, re.DOTALL)
+        # Look for BrightCove:
+        m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
         if m_brightcove is not None:
             self.to_screen(u'Brightcove video detected.')
             bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group())
@@ -144,6 +156,9 @@ class GenericIE(InfoExtractor):
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
                 mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if mobj is None:
+            # HTML5 video
+            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
@@ -152,8 +167,9 @@ class GenericIE(InfoExtractor):
         if mobj.group(1) is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
-        video_url = compat_urllib_parse.unquote(mobj.group(1))
-        video_id = os.path.basename(video_url)
+        video_url = mobj.group(1)
+        video_url = compat_urlparse.urljoin(url, video_url)
+        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
         # here's a fun little line of code for you:
         video_extension = os.path.splitext(video_id)[1][1:]

youtube_dl/extractor/googleplus.py

@@ -40,7 +40,8 @@ class GooglePlusIE(InfoExtractor):
         self.report_extraction(video_id)
 
         # Extract update date
-        upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>',
+        upload_date = self._html_search_regex(
+            ['title="Timestamp">(.*?)</a>', r'<a.+?class="g-M.+?>(.+?)</a>'],
             webpage, u'upload date', fatal=False)
         if upload_date:
             # Convert timestring to a format suitable for filename
@@ -57,8 +58,8 @@ class GooglePlusIE(InfoExtractor):
             webpage, 'title', default=u'NA')
 
         # Step 2, Simulate clicking the image box to launch video
-        DOMAIN = 'https://plus.google.com'
-        video_page = self._search_regex(r'<a href="((?:%s)?/photos/.*?)"' % re.escape(DOMAIN),
+        DOMAIN = 'https://plus.google.com/'
+        video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
             webpage, u'video page URL')
         if not video_page.startswith(DOMAIN):
             video_page = DOMAIN + video_page

youtube_dl/extractor/hark.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class HarkIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
+    _TEST = {
+        u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
+        u'file': u'mmbzyhkgny.mp3',
+        u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
+        u'info_dict': {
+            u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
+            u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
+            u'duration': 11,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        json_url = "http://www.hark.com/clips/%s.json" %(video_id)
+        info_json = self._download_webpage(json_url, video_id)
+        info = json.loads(info_json)
+        final_url = info['url']
+
+        return {'id': video_id,
+                'url' : final_url,
+                'title': info['name'],
+                'ext': determine_ext(final_url),
+                'description': info['description'],
+                'thumbnail': info['image_original'],
+                'duration': info['duration'],
+                }

youtube_dl/extractor/hotnewhiphop.py

@@ -7,11 +7,11 @@ from .common import InfoExtractor
 class HotNewHipHopIE(InfoExtractor):
     _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
     _TEST = {
-        u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html'",
+        u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html",
         u'file': u'1435540.mp3',
         u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
         u'info_dict': {
-            u"title": u"Freddie Gibbs Songs - Lay It Down"
+            u"title": u"Freddie Gibbs - Lay It Down"
         }
     }
 
@@ -33,16 +33,12 @@ class HotNewHipHopIE(InfoExtractor):
 
         video_title = self._html_search_regex(r"<title>(.*)</title>",
             webpage_src, u'title')
-        
-        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
-        thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
-            webpage_src, u'thumbnail', fatal=False)
 
         results = [{
                     'id': video_id,
                     'url' : video_url,
                     'title' : video_title,
-                    'thumbnail' : thumbnail,
+                    'thumbnail' : self._og_search_thumbnail(webpage_src),
                     'ext' : 'mp3',
                     }]
-        return results
+        return results

youtube_dl/extractor/howcast.py

@@ -19,8 +19,7 @@ class HowcastIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
-        webpage_url = 'http://www.howcast.com/videos/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
         self.report_extraction(video_id)
 

youtube_dl/extractor/ign.py

@@ -0,0 +1,95 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class IGNIE(InfoExtractor):
+    """
+    Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
+    Some videos of it.ign.com are also supported
+    """
+
+    _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
+    IE_NAME = u'ign.com'
+
+    _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
+    _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>',
+                       r'id="my_show_video">.*?<p>(.*?)</p>',
+                       ]
+
+    _TEST = {
+        u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
+        u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
+        u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
+        u'info_dict': {
+            u'title': u'The Last of Us Review',
+            u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
+        }
+    }
+
+    def _find_video_id(self, webpage):
+        res_id = [r'data-video-id="(.+?)"',
+                  r'<object id="vid_(.+?)"',
+                  r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+                  ]
+        return self._search_regex(res_id, webpage, 'video id')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name_or_id = mobj.group('name_or_id')
+        page_type = mobj.group('type')
+        webpage = self._download_webpage(url, name_or_id)
+        if page_type == 'articles':
+            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
+            return self.url_result(video_url, ie='IGN')
+        video_id = self._find_video_id(webpage)
+        result = self._get_video_info(video_id)
+        description = self._html_search_regex(self._DESCRIPTION_RE,
+                                              webpage, 'video description',
+                                              flags=re.DOTALL)
+        result['description'] = description
+        return result
+
+    def _get_video_info(self, video_id):
+        config_url = self._CONFIG_URL_TEMPLATE % video_id
+        config = json.loads(self._download_webpage(config_url, video_id,
+                            u'Downloading video info'))
+        media = config['playlist']['media']
+        video_url = media['url']
+
+        return {'id': media['metadata']['videoId'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'title': media['metadata']['title'],
+                'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
+                }
+
+
+class OneUPIE(IGNIE):
+    """Extractor for 1up.com, it uses the ign videos system."""
+
+    _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
+    IE_NAME = '1up.com'
+
+    _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
+
+    _TEST = {
+        u'url': u'http://gamevideos.1up.com/video/id/34976',
+        u'file': u'34976.mp4',
+        u'md5': u'68a54ce4ebc772e4b71e3123d413163d',
+        u'info_dict': {
+            u'title': u'Sniper Elite V2 - Trailer',
+            u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        id = mobj.group('name_or_id')
+        result = super(OneUPIE, self)._real_extract(url)
+        result['id'] = id
+        return result

youtube_dl/extractor/ina.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 class InaIE(InfoExtractor):
     """Information Extractor for Ina.fr"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
     _TEST = {
         u'url': u'www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         u'file': u'I12055569.mp4',

youtube_dl/extractor/instagram.py

@@ -5,12 +5,13 @@ from .common import InfoExtractor
 class InstagramIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
     _TEST = {
-        u'url': u'http://instagram.com/p/aye83DjauH/#',
+        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
         u'file': u'aye83DjauH.mp4',
         u'md5': u'0d2da106a9d2631273e192b372806516',
         u'info_dict': {
             u"uploader_id": u"naomipq", 
-            u"title": u"Video by naomipq"
+            u"title": u"Video by naomipq",
+            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
     }
 
@@ -18,25 +19,17 @@ class InstagramIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_regex(
-            r'<meta property="og:video" content="(.+?)"',
-            webpage, u'video URL')
-        thumbnail_url = self._html_search_regex(
-            r'<meta property="og:image" content="(.+?)" />',
-            webpage, u'thumbnail URL', fatal=False)
-        html_title = self._html_search_regex(
-            r'<title>(.+?)</title>',
-            webpage, u'title', flags=re.DOTALL)
-        title = re.sub(u'(?: *\(Videos?\))? \u2022 Instagram$', '', html_title).strip()
-        uploader_id = self._html_search_regex(r'content="(.*?)\'s video on Instagram',
-            webpage, u'uploader name', fatal=False)
-        ext = 'mp4'
+        uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
+            webpage, u'uploader id', fatal=False)
+        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
+            fatal=False)
 
         return [{
             'id':        video_id,
-            'url':       video_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
-            'uploader_id' : uploader_id
+            'url':       self._og_search_video_url(webpage),
+            'ext':       'mp4',
+            'title':     u'Video by %s' % uploader_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader_id' : uploader_id,
+            'description': desc,
         }]

youtube_dl/extractor/jeuxvideo.py

@@ -0,0 +1,47 @@
+# coding: utf-8
+
+import json
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+class JeuxVideoIE(InfoExtractor):
+    _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
+
+    _TEST = {
+        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        u'file': u'5182.mp4',
+        u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
+        u'info_dict': {
+            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
+
+        xml_link = m_download.group(1)
+        
+        id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
+
+        xml_config = self._download_webpage(xml_link, title,
+                                                  'Downloading XML config')
+        config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
+        info = re.search(r'<format\.json>(.*?)</format\.json>',
+                         xml_config, re.MULTILINE|re.DOTALL).group(1)
+        info = json.loads(info)['versions'][0]
+        
+        video_url = 'http://video720.jeuxvideo.com/' + info['file']
+
+        return {'id': id,
+                'title' : config.find('titre_video').text,
+                'ext' : 'mp4',
+                'url' : video_url,
+                'description': self._og_search_description(webpage),
+                'thumbnail': config.find('image').text,
+                }

youtube_dl/extractor/kankan.py

@@ -0,0 +1,39 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class KankanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
+    
+    _TEST = {
+        u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml',
+        u'file': u'48863.flv',
+        u'md5': u'29aca1e47ae68fc28804aca89f29507e',
+        u'info_dict': {
+            u'title': u'Ready To Go',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
+        surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
+        gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
+        gcid = gcids[-1]
+
+        video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
+                                                 video_id, u'Downloading video url info')
+        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
+        path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
+        video_url = 'http://%s%s' % (ip, path)
+
+        return {'id': video_id,
+                'title': title,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                }

youtube_dl/extractor/keek.py

@@ -4,10 +4,10 @@ from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
     IE_NAME = u'keek'
     _TEST = {
-        u'url': u'http://www.keek.com/ytdl/keeks/NODfbab',
+        u'url': u'https://www.keek.com/ytdl/keeks/NODfbab',
         u'file': u'NODfbab.mp4',
         u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
         u'info_dict': {
@@ -24,8 +24,7 @@ class KeekIE(InfoExtractor):
         thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title')
+        video_title = self._og_search_title(webpage)
 
         uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
             webpage, u'uploader', fatal=False)

youtube_dl/extractor/kickstarter.py

@@ -0,0 +1,37 @@
+import re
+
+from .common import InfoExtractor
+
+
+class KickStarterIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*'
+    _TEST = {
+        u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
+        u"file": u"1404461844.mp4",
+        u"md5": u"c81addca81327ffa66c642b5d8b08cab",
+        u"info_dict": {
+            u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling",
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+        webpage_src = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(r'data-video="(.*?)">',
+            webpage_src, u'video URL')
+        if 'mp4' in video_url:
+            ext = 'mp4'
+        else:
+            ext = 'flv'
+        video_title = self._html_search_regex(r"<title>(.*?)</title>",
+            webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip()
+
+        results = [{
+                    'id': video_id,
+                    'url': video_url,
+                    'title': video_title,
+                    'ext': ext,
+                    }]
+        return results

youtube_dl/extractor/liveleak.py

@@ -33,11 +33,9 @@ class LiveLeakIE(InfoExtractor):
         video_url = self._search_regex(r'file: "(.*?)",',
             webpage, u'video URL')
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title').replace('LiveLeak.com -', '').strip()
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
 
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
-            webpage, u'description', fatal=False)
+        video_description = self._og_search_description(webpage)
 
         video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
             webpage, u'uploader', fatal=False)

youtube_dl/extractor/livestream.py

@@ -0,0 +1,60 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+    get_meta_content,
+    ExtractorError,
+)
+
+
+class LivestreamIE(InfoExtractor):
+    _VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _TEST = {
+        u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
+        u'file': u'4719370.mp4',
+        u'md5': u'0d2186e3187d185a04b3cdd02b828836',
+        u'info_dict': {
+            u'title': u'Live from Webster Hall NYC',
+            u'upload_date': u'20121012',
+        }
+    }
+
+    def _extract_video_info(self, video_data):
+        video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
+        return {'id': video_data['id'],
+                'url': video_url,
+                'ext': 'mp4',
+                'title': video_data['caption'],
+                'thumbnail': video_data['thumbnail_url'],
+                'upload_date': video_data['updated_at'].replace('-','')[:8],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        event_name = mobj.group('event_name')
+        webpage = self._download_webpage(url, video_id or event_name)
+
+        if video_id is None:
+            # This is an event page:
+            player = get_meta_content('twitter:player', webpage)
+            if player is None:
+                raise ExtractorError('Couldn\'t extract event api url')
+            api_url = player.replace('/player', '')
+            api_url = re.sub(r'^(https?://)(new\.)', r'\1api.\2', api_url)
+            info = json.loads(self._download_webpage(api_url, event_name,
+                                                     u'Downloading event info'))
+            videos = [self._extract_video_info(video_data['data'])
+                for video_data in info['feed']['data'] if video_data['type'] == u'video']
+            return self.playlist_result(videos, info['id'], info['full_name'])
+        else:
+            og_video = self._og_search_video_url(webpage, name=u'player url')
+            query_str = compat_urllib_parse_urlparse(og_video).query
+            query = compat_urlparse.parse_qs(query_str)
+            api_url = query['play_url'][0].replace('.smil', '')
+            info = json.loads(self._download_webpage(api_url, video_id,
+                                                     u'Downloading video info'))
+            return self._extract_video_info(info)

youtube_dl/extractor/metacafe.py

@@ -9,7 +9,7 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_str,
-
+    determine_ext,
     ExtractorError,
 )
 
@@ -20,7 +20,7 @@ class MetacafeIE(InfoExtractor):
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = u'metacafe'
-    _TEST = {
+    _TESTS = [{
         u"add_ie": ["Youtube"],
         u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
         u"file":  u"_aUehQsCQtM.flv",
@@ -31,7 +31,16 @@ class MetacafeIE(InfoExtractor):
             u"uploader": u"PBS",
             u"uploader_id": u"PBS"
         }
-    }
+    },
+    {
+        u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
+        u"file": u"an-dVVXnuY7Jh77J.mp4",
+        u"info_dict": {
+            u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
+            u"uploader": u"anyclip",
+            u"description": u"md5:38c711dd98f5bb87acf973d573442e67"
+        }
+    }]
 
 
     def report_disclaimer(self):
@@ -73,14 +82,16 @@ class MetacafeIE(InfoExtractor):
             return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
 
         # Retrieve video webpage to extract further information
-        webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
+        req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
+        req.headers['Cookie'] = 'flashVersion=0;'
+        webpage = self._download_webpage(req, video_id)
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-            video_extension = mediaURL[-3:]
+            video_ext = mediaURL[-3:]
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
@@ -90,34 +101,37 @@ class MetacafeIE(InfoExtractor):
                 gdaKey = mobj.group(1)
                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
         else:
-            mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
-            if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
-            vardict = compat_parse_qs(mobj.group(1))
-            if 'mediaData' not in vardict:
-                raise ExtractorError(u'Unable to extract media URL')
-            mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
-            if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
-            mediaURL = mobj.group('mediaURL').replace('\\/', '/')
-            video_extension = mediaURL[-3:]
-            video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
+            mobj = re.search(r'<video src="([^"]+)"', webpage)
+            if mobj:
+                video_url = mobj.group(1)
+                video_ext = 'mp4'
+            else:
+                mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+                if mobj is None:
+                    raise ExtractorError(u'Unable to extract media URL')
+                vardict = compat_parse_qs(mobj.group(1))
+                if 'mediaData' not in vardict:
+                    raise ExtractorError(u'Unable to extract media URL')
+                mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
+                if mobj is None:
+                    raise ExtractorError(u'Unable to extract media URL')
+                mediaURL = mobj.group('mediaURL').replace('\\/', '/')
+                video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
+                video_ext = determine_ext(video_url)
 
-        mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract title')
-        video_title = mobj.group(1).decode('utf-8')
+        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
+        description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+                r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
+                webpage, u'uploader nickname', fatal=False)
 
-        mobj = re.search(r'submitter=(.*?);', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract uploader nickname')
-        video_uploader = mobj.group(1)
-
-        return [{
-            'id':       video_id.decode('utf-8'),
-            'url':      video_url.decode('utf-8'),
-            'uploader': video_uploader.decode('utf-8'),
+        return {
+            '_type':    'video',
+            'id':       video_id,
+            'url':      video_url,
+            'description': description,
+            'uploader': video_uploader,
             'upload_date':  None,
             'title':    video_title,
-            'ext':      video_extension.decode('utf-8'),
-        }]
+            'ext':      video_ext,
+        }

youtube_dl/extractor/metacritic.py

@@ -0,0 +1,55 @@
+import re
+import xml.etree.ElementTree
+import operator
+
+from .common import InfoExtractor
+
+
+class MetacriticIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
+        u'file': u'3698222.mp4',
+        u'info_dict': {
+            u'title': u'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors',
+            u'description': u'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.',
+            u'duration': 221,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        # The xml is not well formatted, there are raw '&'
+        info_xml = self._download_webpage('http://www.metacritic.com/video_data?video=' + video_id,
+            video_id, u'Downloading info xml').replace('&', '&amp;')
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+
+        clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
+        formats = []
+        for videoFile in clip.findall('httpURI/videoFile'):
+            rate_str = videoFile.find('rate').text
+            video_url = videoFile.find('filePath').text
+            formats.append({
+                'url': video_url,
+                'ext': 'mp4',
+                'format_id': rate_str,
+                'rate': int(rate_str),
+            })
+        formats.sort(key=operator.itemgetter('rate'))
+
+        description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>',
+            webpage, u'description', flags=re.DOTALL)
+
+        info = {
+            'id': video_id,
+            'title': clip.find('title').text,
+            'formats': formats,
+            'description': description,
+            'duration': int(clip.find('duration').text),
+        }
+        # TODO: Remove when #980 has been merged
+        info.update(formats[-1])
+        return info

youtube_dl/extractor/mit.py

@@ -0,0 +1,74 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    get_element_by_id,
+)
+
+
+class TechTVMITIE(InfoExtractor):
+    IE_NAME = u'techtv.mit.edu'
+    _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+        u'file': u'25418.mp4',
+        u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
+        u'info_dict': {
+            u'title': u'MIT DNA Learning Center Set',
+            u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        raw_page = self._download_webpage(
+            'http://techtv.mit.edu/videos/%s' % video_id, video_id)
+        clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+
+        base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
+            raw_page, u'base url')
+        formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
+            u'video formats')
+        formats = json.loads(formats_json)
+        formats = sorted(formats, key=lambda f: f['bitrate'])
+
+        title = get_element_by_id('edit-title', clean_page)
+        description = clean_html(get_element_by_id('edit-description', clean_page))
+        thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
+            raw_page, u'thumbnail', flags=re.DOTALL)
+
+        return {'id': video_id,
+                'title': title,
+                'url': base_url + formats[-1]['url'].replace('mp4:', ''),
+                'ext': 'mp4',
+                'description': description,
+                'thumbnail': thumbnail,
+                }
+
+
+class MITIE(TechTVMITIE):
+    IE_NAME = u'video.mit.edu'
+    _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
+
+    _TEST = {
+        u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+        u'file': u'21783.mp4',
+        u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
+        u'info_dict': {
+            u'title': u'The Government is Profiling You',
+            u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_title = mobj.group('title')
+        webpage = self._download_webpage(url, page_title)
+        self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
+        embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
+            u'embed url')
+        return self.url_result(embed_url, ie='TechTVMIT')

youtube_dl/extractor/mixcloud.py

@@ -5,34 +5,27 @@ import socket
 from .common import InfoExtractor
 from ..utils import (
     compat_http_client,
-    compat_str,
     compat_urllib_error,
     compat_urllib_request,
-
-    ExtractorError,
+    unified_strdate,
 )
 
 
 class MixcloudIE(InfoExtractor):
-    _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
     IE_NAME = u'mixcloud'
 
-    def report_download_json(self, file_id):
-        """Report JSON download."""
-        self.to_screen(u'Downloading json')
-
-    def get_urls(self, jsonData, fmt, bitrate='best'):
-        """Get urls from 'audio_formats' section in json"""
-        try:
-            bitrate_list = jsonData[fmt]
-            if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
-                bitrate = max(bitrate_list) # select highest
-
-            url_list = jsonData[fmt][bitrate]
-        except TypeError: # we have no bitrate info.
-            url_list = jsonData[fmt]
-        return url_list
+    _TEST = {
+        u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/',
+        u'file': u'dholbach-cryptkeeper.mp3',
+        u'info_dict': {
+            u'title': u'Cryptkeeper',
+            u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
+            u'uploader': u'Daniel Holbach',
+            u'uploader_id': u'dholbach',
+            u'upload_date': u'20111115',
+        },
+    }
 
     def check_urls(self, url_list):
         """Returns 1st active url from list"""
@@ -45,71 +38,32 @@ class MixcloudIE(InfoExtractor):
 
         return None
 
-    def _print_formats(self, formats):
-        print('Available formats:')
-        for fmt in formats.keys():
-            for b in formats[fmt]:
-                try:
-                    ext = formats[fmt][b][0]
-                    print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
-                except TypeError: # we have no bitrate info
-                    ext = formats[fmt][0]
-                    print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
-                    break
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        # extract uploader & filename from url
-        uploader = mobj.group(1).decode('utf-8')
-        file_id = uploader + "-" + mobj.group(2).decode('utf-8')
 
-        # construct API request
-        file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
-        # retrieve .json file with links to files
-        request = compat_urllib_request.Request(file_url)
-        try:
-            self.report_download_json(file_url)
-            jsonData = compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
+        uploader = mobj.group(1)
+        cloudcast_name = mobj.group(2)
+        track_id = '-'.join((uploader, cloudcast_name))
+        api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
+        webpage = self._download_webpage(url, track_id)
+        json_data = self._download_webpage(api_url, track_id,
+            u'Downloading cloudcast info')
+        info = json.loads(json_data)
 
-        # parse JSON
-        json_data = json.loads(jsonData)
-        player_url = json_data['player_swf_url']
-        formats = dict(json_data['audio_formats'])
+        preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
+        song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
+        template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
+        final_song_url = self.check_urls(template_url % i for i in range(30))
 
-        req_format = self._downloader.params.get('format', None)
-
-        if self._downloader.params.get('listformats', None):
-            self._print_formats(formats)
-            return
-
-        if req_format is None or req_format == 'best':
-            for format_param in formats.keys():
-                url_list = self.get_urls(formats, format_param)
-                # check urls
-                file_url = self.check_urls(url_list)
-                if file_url is not None:
-                    break # got it!
-        else:
-            if req_format not in formats:
-                raise ExtractorError(u'Format is not available')
-
-            url_list = self.get_urls(formats, req_format)
-            file_url = self.check_urls(url_list)
-            format_param = req_format
-
-        return [{
-            'id': file_id.decode('utf-8'),
-            'url': file_url.decode('utf-8'),
-            'uploader': uploader.decode('utf-8'),
-            'upload_date': None,
-            'title': json_data['name'],
-            'ext': file_url.split('.')[-1].decode('utf-8'),
-            'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
-            'thumbnail': json_data['thumbnail_url'],
-            'description': json_data['description'],
-            'player_url': player_url.decode('utf-8'),
-        }]
+        return {
+            'id': track_id,
+            'title': info['name'],
+            'url': final_song_url,
+            'ext': 'mp3',
+            'description': info['description'],
+            'thumbnail': info['pictures'].get('extra_large'),
+            'uploader': info['user']['name'],
+            'uploader_id': info['user']['username'],
+            'upload_date': unified_strdate(info['created_time']),
+            'view_count': info['play_count'],
+        }

youtube_dl/extractor/mtv.py

@@ -1,28 +1,110 @@
 import re
-import socket
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_request,
-
+    compat_urllib_parse,
     ExtractorError,
 )
 
+def _media_xml_tag(tag):
+    return '{http://search.yahoo.com/mrss/}%s' % tag
 
 class MTVIE(InfoExtractor):
-    _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
-    _WORKING = False
+    _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
+
+    _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
+
+    _TESTS = [
+        {
+            u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
+            u'file': u'853555.mp4',
+            u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
+            u'info_dict': {
+                u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
+                u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+            },
+        },
+        {
+            u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
+            u'file': u'USCJY1331283.mp4',
+            u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
+            u'info_dict': {
+                u'title': u'Everything Has Changed',
+                u'upload_date': u'20130606',
+                u'uploader': u'Taylor Swift',
+            },
+            u'skip': u'VEVO is only available in some countries',
+        },
+    ]
+
+    @staticmethod
+    def _id_from_uri(uri):
+        return uri.split(':')[-1]
+
+    # This was originally implemented for ComedyCentral, but it also works here
+    @staticmethod
+    def _transform_rtmp_url(rtmp_video_url):
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
+        if not m:
+            raise ExtractorError(u'Cannot transform RTMP url')
+        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+        return base + m.group('finalid')
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        return 'http://mtv.mtvnimages.com/uri/' + uri
+
+    def _extract_video_url(self, metadataXml):
+        if '/error_country_block.swf' in metadataXml:
+            raise ExtractorError(u'This video is not available from your country.', expected=True)
+        mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
+        renditions = mdoc.findall('.//rendition')
+
+        # For now, always pick the highest quality.
+        rendition = renditions[-1]
+
+        try:
+            _,_,ext = rendition.attrib['type'].partition('/')
+            format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
+            rtmp_video_url = rendition.find('./src').text
+        except KeyError:
+            raise ExtractorError('Invalid rendition field.')
+        video_url = self._transform_rtmp_url(rtmp_video_url)
+        return {'ext': ext, 'url': video_url, 'format': format}
+
+    def _get_video_info(self, itemdoc):
+        uri = itemdoc.find('guid').text
+        video_id = self._id_from_uri(uri)
+        self.report_extraction(video_id)
+        mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
+        if 'acceptMethods' not in mediagen_url:
+            mediagen_url += '&acceptMethods=fms'
+        mediagen_page = self._download_webpage(mediagen_url, video_id,
+                                               u'Downloading video urls')
+        video_info = self._extract_video_url(mediagen_page)
+
+        description_node = itemdoc.find('description')
+        if description_node is not None:
+            description = description_node.text
+        else:
+            description = None
+        video_info.update({'title': itemdoc.find('title').text,
+                           'id': video_id,
+                           'thumbnail': self._get_thumbnail_url(uri, itemdoc),
+                           'description': description,
+                           })
+        return video_info
+
+    def _get_videos_info(self, uri):
+        video_id = self._id_from_uri(uri)
+        data = compat_urllib_parse.urlencode({'uri': uri})
+        infoXml = self._download_webpage(self._FEED_URL +'?' + data, video_id,
+                                         u'Downloading info')
+        idoc = xml.etree.ElementTree.fromstring(infoXml.encode('utf-8'))
+        return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        if not mobj.group('proto'):
-            url = 'http://' + url
         video_id = mobj.group('videoid')
 
         webpage = self._download_webpage(url, video_id)
@@ -35,46 +117,5 @@ class MTVIE(InfoExtractor):
             self.to_screen(u'Vevo video detected: %s' % vevo_id)
             return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 
-        #song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
-        #    webpage, u'song name', fatal=False)
-
-        video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
-            webpage, u'title')
-
-        mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
-            webpage, u'mtvn_uri', fatal=False)
-
-        content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
-            webpage, u'content id', fatal=False)
-
-        videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
-        self.report_extraction(video_id)
-        request = compat_urllib_request.Request(videogen_url)
-        try:
-            metadataXml = compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
-
-        mdoc = xml.etree.ElementTree.fromstring(metadataXml)
-        renditions = mdoc.findall('.//rendition')
-
-        # For now, always pick the highest quality.
-        rendition = renditions[-1]
-
-        try:
-            _,_,ext = rendition.attrib['type'].partition('/')
-            format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
-            video_url = rendition.find('./src').text
-        except KeyError:
-            raise ExtractorError('Invalid rendition field.')
-
-        info = {
-            'id': video_id,
-            'url': video_url,
-            'upload_date': None,
-            'title': video_title,
-            'ext': ext,
-            'format': format,
-        }
-
-        return [info]
+        uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+        return self._get_videos_info(uri)

youtube_dl/extractor/muzu.py

@@ -0,0 +1,64 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    determine_ext,
+)
+
+
+class MuzuTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)'
+    IE_NAME = u'muzu.tv'
+
+    _TEST = {
+        u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
+        u'file': u'1981454.mp4',
+        u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000',
+        u'info_dict': {
+            u'title': u'Cat Walk (Original Mix)',
+            u'description': u'md5:90e868994de201b2570e4e5854e19420',
+            u'uploader': u'MarcAshken featuring SOS',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        info_data = compat_urllib_parse.urlencode({'format': 'json',
+                                                   'url': url,
+                                                   })
+        video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data,
+                                                 video_id, u'Downloading video info')
+        info = json.loads(video_info_page)
+
+        player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
+                                                  video_id, u'Downloading player info')
+        video_info = json.loads(player_info_page)['videos'][0]
+        for quality in ['1080' , '720', '480', '360']:
+            if video_info.get('v%s' % quality):
+                break
+
+        data = compat_urllib_parse.urlencode({'ai': video_id,
+                                              # Even if each time you watch a video the hash changes,
+                                              # it seems to work for different videos, and it will work
+                                              # even if you use any non empty string as a hash
+                                              'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k',
+                                              'device': 'web',
+                                              'qv': quality,
+                                              })
+        video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data,
+                                                video_id, u'Downloading video url')
+        video_url_info = json.loads(video_url_page)
+        video_url = video_url_info['url']
+
+        return {'id': video_id,
+                'title': info['title'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': info['thumbnail_url'],
+                'description': info['description'],
+                'uploader': info['author_name'],
+                }

youtube_dl/extractor/myvideo.py

@@ -2,11 +2,13 @@ import binascii
 import base64
 import hashlib
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import (
     compat_ord,
     compat_urllib_parse,
+    compat_urllib_request,
 
     ExtractorError,
 )
@@ -16,7 +18,7 @@ from ..utils import (
 class MyVideoIE(InfoExtractor):
     """Information Extractor for myvideo.de."""
 
-    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/([0-9]+)/([^?/]+).*'
     IE_NAME = u'myvideo'
     _TEST = {
         u'url': u'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
@@ -85,6 +87,20 @@ class MyVideoIE(InfoExtractor):
                 'ext':      video_ext,
             }]
 
+        mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
+        if mobj is not None:
+            request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
+            response = self._download_webpage(request, video_id,
+                                              u'Downloading video info')
+            info = json.loads(base64.b64decode(response).decode('utf-8'))
+            return {'id': video_id,
+                    'title': info['title'],
+                    'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
+                    'play_path': info['filename'],
+                    'ext': 'flv',
+                    'thumbnail': info['thumbnail'][0]['url'],
+                    }
+
         # try encxml
         mobj = re.search('var flashvars={(.+?)}', webpage)
         if mobj is None:

youtube_dl/extractor/naver.py

@@ -0,0 +1,73 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    ExtractorError,
+)
+
+
+class NaverIE(InfoExtractor):
+    _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://tvcast.naver.com/v/81652',
+        u'file': u'81652.mp4',
+        u'info_dict': {
+            u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
+            u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
+            u'upload_date': u'20130903',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
+            webpage)
+        if m_id is None:
+            raise ExtractorError(u'couldn\'t extract vid and key')
+        vid = m_id.group(1)
+        key = m_id.group(2)
+        query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
+        query_urls = compat_urllib_parse.urlencode({
+            'masterVid': vid,
+            'protocol': 'p2p',
+            'inKey': key,
+        })
+        info_xml = self._download_webpage(
+            'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
+            video_id, u'Downloading video info')
+        urls_xml = self._download_webpage(
+            'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
+            video_id, u'Downloading video formats info')
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+
+        formats = []
+        for format_el in urls.findall('EncodingOptions/EncodingOption'):
+            domain = format_el.find('Domain').text
+            if domain.startswith('rtmp'):
+                continue
+            formats.append({
+                'url': domain + format_el.find('uri').text,
+                'ext': 'mp4',
+                'width': int(format_el.find('width').text),
+                'height': int(format_el.find('height').text),
+            })
+
+        info = {
+            'id': video_id,
+            'title': info.find('Subject').text,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'upload_date': info.find('WriteDate').text.replace('.', ''),
+            'view_count': int(info.find('PlayCount').text),
+        }
+        # TODO: Remove when #980 has been merged
+        info.update(formats[-1])
+        return info

youtube_dl/extractor/nba.py

@@ -30,8 +30,7 @@ class NBAIE(InfoExtractor):
         video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
-        title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
-            webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
+        title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
 
         # It isn't there in the HTML it returns to us
         # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)

youtube_dl/extractor/nbc.py

@@ -0,0 +1,33 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr, compat_str
+
+
+class NBCNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
+        u'file': u'52753292.flv',
+        u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
+        u'info_dict': {
+            u'title': u'Crew emerges after four-month Mars food study',
+            u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+
+        return {'id': video_id,
+                'title': info.find('headline').text,
+                'ext': 'flv',
+                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+                'description': compat_str(info.find('caption').text),
+                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+                }

youtube_dl/extractor/newgrounds.py

@@ -0,0 +1,38 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class NewgroundsIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
+    _TEST = {
+        u'url': u'http://www.newgrounds.com/audio/listen/549479',
+        u'file': u'549479.mp3',
+        u'md5': u'fe6033d297591288fa1c1f780386f07a',
+        u'info_dict': {
+            u"title": u"B7 - BusMode",
+            u"uploader": u"Burn7",
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        music_id = mobj.group('id')
+        webpage = self._download_webpage(url, music_id)
+        
+        title = self._html_search_regex(r',"name":"([^"]+)",', webpage, u'music title')
+        uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, u'music uploader')
+        
+        music_url_json_string = self._html_search_regex(r'({"url":"[^"]+"),', webpage, u'music url') + '}'
+        music_url_json = json.loads(music_url_json_string)
+        music_url = music_url_json['url']
+
+        return {
+            'id':       music_id,
+            'title':    title,
+            'url':      music_url,
+            'uploader': uploader,
+            'ext':      determine_ext(music_url),
+        }

youtube_dl/extractor/ooyala.py

@@ -0,0 +1,58 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import unescapeHTML
+
+class OoyalaIE(InfoExtractor):
+    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
+
+    _TEST = {
+        # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
+        u'url': u'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+        u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4',
+        u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c',
+        u'info_dict': {
+            u'title': u'Explaining Data Recovery from Hard Drives and SSDs',
+            u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+        },
+    }
+
+    @staticmethod
+    def _url_for_embed_code(embed_code):
+        return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+
+    def _extract_result(self, info, more_info):
+        return {'id': info['embedCode'],
+                'ext': 'mp4',
+                'title': unescapeHTML(info['title']),
+                'url': info.get('ipad_url') or info['url'],
+                'description': unescapeHTML(more_info['description']),
+                'thumbnail': more_info['promo'],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        embedCode = mobj.group('id')
+        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
+        player = self._download_webpage(player_url, embedCode)
+        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
+                                        player, u'mobile player url')
+        mobile_player = self._download_webpage(mobile_url, embedCode)
+        videos_info = self._search_regex(
+            r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
+            mobile_player, u'info').replace('\\"','"')
+        videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
+        videos_info = json.loads(videos_info)
+        videos_more_info =json.loads(videos_more_info)
+
+        if videos_more_info.get('lineup'):
+            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
+            return {'_type': 'playlist',
+                    'id': embedCode,
+                    'title': unescapeHTML(videos_more_info['title']),
+                    'entries': videos,
+                    }
+        else:
+            return self._extract_result(videos_info[0], videos_more_info)
+        

youtube_dl/extractor/orf.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    ExtractorError,
+    find_xpath_attr,
+)
+
+class ORFIE(InfoExtractor):
+    _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        webpage = self._download_webpage(url, playlist_id)
+
+        flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml')
+        flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0]
+        flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8'))
+        playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"')
+        playlist = json.loads(playlist_json)
+
+        videos = []
+        ns = '{http://tempuri.org/XMLSchema.xsd}'
+        xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns}
+        webpage_description = self._og_search_description(webpage)
+        for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1):
+            # Get best quality url
+            rtmp_url = None
+            for q in ['Q6A', 'Q4A', 'Q1A']:
+                video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q)
+                if video_url is not None:
+                    rtmp_url = video_url.text
+                    break
+            if rtmp_url is None:
+                raise ExtractorError(u'Couldn\'t get video url: %s' % info['id'])
+            description = self._html_search_regex(
+                r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage,
+                u'description', default=webpage_description, flags=re.DOTALL)
+            videos.append({
+                '_type': 'video',
+                'id': info['id'],
+                'title': info['title'],
+                'url': rtmp_url,
+                'ext': 'flv',
+                'description': description,
+                })
+
+        return videos

youtube_dl/extractor/pbs.py

@@ -0,0 +1,34 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class PBSIE(InfoExtractor):
+    _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
+
+    _TEST = {
+        u'url': u'http://video.pbs.org/video/2365006249/',
+        u'file': u'2365006249.mp4',
+        u'md5': 'ce1888486f0908d555a8093cac9a7362',
+        u'info_dict': {
+            u'title': u'A More Perfect Union',
+            u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
+            u'duration': 3190,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
+        info_page = self._download_webpage(info_url, video_id)
+        info =json.loads(info_page)
+        return {'id': video_id,
+                'title': info['title'],
+                'url': info['alternate_encoding']['url'],
+                'ext': 'mp4',
+                'description': info['program'].get('description'),
+                'thumbnail': info.get('image_url'),
+                'duration': info.get('duration'),
+                }

youtube_dl/extractor/ro220.py

@@ -0,0 +1,42 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    compat_parse_qs,
+)
+
+
+class Ro220IE(InfoExtractor):
+    IE_NAME = '220.ro'
+    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
+    _TEST = {
+        u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
+        u'file': u'LYV6doKo7f.mp4',
+        u'md5': u'03af18b73a07b4088753930db7a34add',
+        u'info_dict': {
+            u"title": u"Luati-le Banii sez 4 ep 1",
+            u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+
+        webpage = self._download_webpage(url, video_id)
+        flashVars_str = self._search_regex(
+            r'<param name="flashVars" value="([^"]+)"',
+            webpage, u'flashVars')
+        flashVars = compat_parse_qs(flashVars_str)
+
+        info = {
+            '_type': 'video',
+            'id': video_id,
+            'ext': 'mp4',
+            'url': flashVars['videoURL'][0],
+            'title': flashVars['title'][0],
+            'description': clean_html(flashVars['desc'][0]),
+            'thumbnail': flashVars['preview'][0],
+        }
+        return info

youtube_dl/extractor/roxwel.py

@@ -0,0 +1,49 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import unified_strdate, determine_ext
+
+
+class RoxwelIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
+
+    _TEST = {
+        u'url': u'http://www.roxwel.com/player/passionpittakeawalklive.html',
+        u'file': u'passionpittakeawalklive.flv',
+        u'md5': u'd9dea8360a1e7d485d2206db7fe13035',
+        u'info_dict': {
+            u'title': u'Take A Walk (live)',
+            u'uploader': u'Passion Pit',
+            u'description': u'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ',
+        },
+        u'skip': u'Requires rtmpdump',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        filename = mobj.group('filename')
+        info_url = 'http://www.roxwel.com/api/videos/%s' % filename
+        info_page = self._download_webpage(info_url, filename,
+                                           u'Downloading video info')
+
+        self.report_extraction(filename)
+        info = json.loads(info_page)
+        rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')])
+        best_rate = rtmp_rates[-1]
+        url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate)
+        rtmp_url = self._download_webpage(url_page_url, filename, u'Downloading video url')
+        ext = determine_ext(rtmp_url)
+        if ext == 'f4v':
+            rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename)
+
+        return {'id': filename,
+                'title': info['title'],
+                'url': rtmp_url,
+                'ext': 'flv',
+                'description': info['description'],
+                'thumbnail': info.get('player_image_url') or info.get('image_url_large'),
+                'uploader': info['artist'],
+                'uploader_id': info['artistname'],
+                'upload_date': unified_strdate(info['dbdate']),
+                }

youtube_dl/extractor/rtlnow.py

@@ -0,0 +1,126 @@
+# encoding: utf-8
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError,
+)
+
+class RTLnowIE(InfoExtractor):
+    """Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW"""
+    _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
+    _TESTS = [{
+        u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
+        u'file': u'90419.flv',
+        u'info_dict': {
+            u'upload_date': u'20070416', 
+            u'title': u'Ahornallee - Folge 1 - Der Einzug',
+            u'description': u'Folge 1 - Der Einzug',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+        u'skip': u'Only works from Germany',
+    },
+    {
+        u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
+        u'file': u'69756.flv',
+        u'info_dict': {
+            u'upload_date': u'20120519', 
+            u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
+            u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
+            u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+        u'skip': u'Only works from Germany',
+    },
+    {
+        u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
+        u'file': u'13883.flv',
+        u'info_dict': {
+            u'upload_date': u'20090627', 
+            u'title': u'Voxtours - Südafrika-Reporter II',
+            u'description': u'Südafrika-Reporter II',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    },
+    {
+        u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
+        u'file': u'99205.flv',
+        u'info_dict': {
+            u'upload_date': u'20080928', 
+            u'title': u'Medicopter 117 - Angst!',
+            u'description': u'Angst!',
+            u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        webpage_url = u'http://' + mobj.group('url')
+        video_page_url = u'http://' + mobj.group('base_url')
+        video_id = mobj.group(u'video_id')
+
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        note_m = re.search(r'''(?sx)
+            <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
+            <div[ ]id="playerteaser">''', webpage)
+        if note_m:
+            msg = clean_html(note_m.group(1))
+            raise ExtractorError(msg)
+
+        video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
+            webpage, u'title')
+        playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
+            webpage, u'playerdata_url')
+
+        playerdata = self._download_webpage(playerdata_url, video_id)
+        mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
+        if mobj:
+            video_description = mobj.group(u'description')
+            if mobj.group('upload_date_Y'):
+                video_upload_date = mobj.group('upload_date_Y')
+            else:
+                video_upload_date = u'20' + mobj.group('upload_date_y')
+            video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
+        else:
+            video_description = None
+            video_upload_date = None
+            self._downloader.report_warning(u'Unable to extract description and upload date')
+
+        # Thumbnail: not every video has an thumbnail
+        mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
+        if mobj:
+            video_thumbnail = mobj.group(u'thumbnail')
+        else:
+            video_thumbnail = None
+
+        mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract media URL')
+        video_url = mobj.group(u'url')
+        video_play_path = u'mp4:' + mobj.group(u'play_path')
+        video_player_url = video_page_url + u'includes/vodplayer.swf'
+
+        return [{
+            'id':          video_id,
+            'url':         video_url,
+            'play_path':   video_play_path,
+            'page_url':    video_page_url,
+            'player_url':  video_player_url,
+            'ext':         'flv',
+            'title':       video_title,
+            'description': video_description,
+            'upload_date': video_upload_date,
+            'thumbnail':   video_thumbnail,
+        }]

youtube_dl/extractor/sina.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class SinaIE(InfoExtractor):
+    _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
+                        (
+                            (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=))(?P<id>\d+?)($|&))))
+                            |
+                            # This is used by external sites like Weibo
+                            (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
+                        )
+                  '''
+
+    _TEST = {
+        u'url': u'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
+        u'file': u'110028898.flv',
+        u'md5': u'd65dd22ddcf44e38ce2bf58a10c3e71f',
+        u'info_dict': {
+            u'title': u'《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
+        }
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
+
+    def _extract_video(self, video_id):
+        data = compat_urllib_parse.urlencode({'vid': video_id})
+        url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data,
+            video_id, u'Downloading video url')
+        image_page = self._download_webpage(
+            'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
+            video_id, u'Downloading thumbnail info')
+        url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8'))
+
+        return {'id': video_id,
+                'url': url_doc.find('./durl/url').text,
+                'ext': 'flv',
+                'title': url_doc.find('./vname').text,
+                'thumbnail': image_page.split('=')[1],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        video_id = mobj.group('id')
+        if mobj.group('token') is not None:
+            # The video id is in the redirected url
+            self.to_screen(u'Getting video id')
+            request = compat_urllib_request.Request(url)
+            request.get_method = lambda: 'HEAD'
+            (_, urlh) = self._download_webpage_handle(request, 'NA', False)
+            return self._real_extract(urlh.geturl())
+        elif video_id is None:
+            pseudo_id = mobj.group('pseudo_id')
+            webpage = self._download_webpage(url, pseudo_id)
+            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, u'video id')
+
+        return self._extract_video(video_id)

youtube_dl/extractor/slashdot.py

@@ -0,0 +1,23 @@
+import re
+
+from .common import InfoExtractor
+
+
+class SlashdotIE(InfoExtractor):
+    _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
+
+    _TEST = {
+        u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
+        u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
+        u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
+        u'info_dict': {
+            u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
+        return self.url_result(ooyala_url, 'Ooyala')

youtube_dl/extractor/slideshare.py

@@ -0,0 +1,47 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    ExtractorError,
+)
+
+
+class SlideshareIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
+
+    _TEST = {
+        u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
+        u'file': u'25665706.mp4',
+        u'info_dict': {
+            u'title': u'Managing Scale and Complexity',
+            u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_title = mobj.group('title')
+        webpage = self._download_webpage(url, page_title)
+        slideshare_obj = self._search_regex(
+            r'var slideshare_object =  ({.*?}); var user_info =',
+            webpage, u'slideshare object')
+        info = json.loads(slideshare_obj)
+        if info['slideshow']['type'] != u'video':
+            raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
+
+        doc = info['doc']
+        bucket = info['jsplayer']['video_bucket']
+        ext = info['jsplayer']['video_extension']
+        video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
+
+        return {
+            '_type': 'video',
+            'id': info['slideshow']['id'],
+            'title': info['slideshow']['title'],
+            'ext': ext,
+            'url': video_url,
+            'thumbnail': info['slideshow']['pin_image_url'],
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/sohu.py

@@ -0,0 +1,94 @@
+# encoding: utf-8
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class SohuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
+
+    _TEST = {
+        u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
+        u'file': u'382479172.mp4',
+        u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        u'info_dict': {
+            u'title': u'MV：Far East Movement《The Illest》',
+        },
+    }
+
+    def _real_extract(self, url):
+
+        def _fetch_data(vid_id, mytv=False):
+            if mytv:
+                base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
+            else:
+                base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+            data_url = base_data_url + str(vid_id)
+            data_json = self._download_webpage(
+                data_url, video_id,
+                note=u'Downloading JSON data for ' + str(vid_id))
+            return json.loads(data_json)
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        mytv = mobj.group('mytv') is not None
+
+        webpage = self._download_webpage(url, video_id)
+        raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
+                                            webpage, u'video title')
+        title = raw_title.partition('-')[0].strip()
+
+        vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
+                                      u'video path')
+        data = _fetch_data(vid, mytv)
+
+        QUALITIES = ('ori', 'super', 'high', 'nor')
+        vid_ids = [data['data'][q + 'Vid']
+                   for q in QUALITIES
+                   if data['data'][q + 'Vid'] != 0]
+        if not vid_ids:
+            raise ExtractorError(u'No formats available for this video')
+
+        # For now, we just pick the highest available quality
+        vid_id = vid_ids[-1]
+
+        format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
+        part_count = format_data['data']['totalBlocks']
+        allot = format_data['allot']
+        prot = format_data['prot']
+        clipsURL = format_data['data']['clipsURL']
+        su = format_data['data']['su']
+
+        playlist = []
+        for i in range(part_count):
+            part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
+                        (allot, prot, clipsURL[i], su[i]))
+            part_str = self._download_webpage(
+                part_url, video_id,
+                note=u'Downloading part %d of %d' % (i+1, part_count))
+
+            part_info = part_str.split('|')
+            video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+            video_info = {
+                'id': '%s_part%02d' % (video_id, i + 1),
+                'title': title,
+                'url': video_url,
+                'ext': 'mp4',
+            }
+            playlist.append(video_info)
+
+        if len(playlist) == 1:
+            info = playlist[0]
+            info['id'] = video_id
+        else:
+            info = {
+                '_type': 'playlist',
+                'entries': playlist,
+                'id': video_id,
+            }
+
+        return info

youtube_dl/extractor/soundcloud.py

@@ -1,9 +1,12 @@
 import json
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
+    compat_urlparse,
+    compat_urllib_parse,
 
     ExtractorError,
     unified_strdate,
@@ -19,7 +22,12 @@ class SoundcloudIE(InfoExtractor):
        of the stream token and uid
      """
 
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)(?:[?].*)?$'
+    _VALID_URL = r'''^(?:https?://)?
+                    (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
+                       |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
+                       |(?P<widget>w.soundcloud.com/player/?.*?url=.*)
+                    )
+                    '''
     IE_NAME = u'soundcloud'
     _TEST = {
         u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
@@ -33,59 +41,69 @@ class SoundcloudIE(InfoExtractor):
         }
     }
 
+    _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
+
+    @classmethod
+    def suitable(cls, url):
+        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
+
     def report_resolve(self, video_id):
         """Report information extraction."""
         self.to_screen(u'%s: Resolving id' % video_id)
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+    @classmethod
+    def _resolv_url(cls, url):
+        return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
 
-        # extract uploader (which is in the url)
-        uploader = mobj.group(1)
-        # extract simple title (uploader + slug of song title)
-        slug_title =  mobj.group(2)
-        full_title = '%s/%s' % (uploader, slug_title)
-
-        self.report_resolve(full_title)
-
-        url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
-        resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-        info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
-
-        info = json.loads(info_json)
+    def _extract_info_dict(self, info, full_title=None, quiet=False):
         video_id = info['id']
-        self.report_extraction(full_title)
+        name = full_title or video_id
+        if quiet == False:
+            self.report_extraction(name)
 
-        streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-        stream_json = self._download_webpage(streams_url, full_title,
-                                             u'Downloading stream definitions',
-                                             u'unable to download stream definitions')
-
-        streams = json.loads(stream_json)
-        mediaURL = streams['http_mp3_128_url']
-        upload_date = unified_strdate(info['created_at'])
-
-        return [{
+        thumbnail = info['artwork_url']
+        if thumbnail is not None:
+            thumbnail = thumbnail.replace('-large', '-t500x500')
+        return {
             'id':       info['id'],
-            'url':      mediaURL,
+            'url':      info['stream_url'] + '?client_id=' + self._CLIENT_ID,
             'uploader': info['user']['username'],
-            'upload_date': upload_date,
+            'upload_date': unified_strdate(info['created_at']),
             'title':    info['title'],
             'ext':      u'mp3',
             'description': info['description'],
-        }]
+            'thumbnail': thumbnail,
+        }
 
-class SoundcloudSetIE(InfoExtractor):
-    """Information extractor for soundcloud.com sets
-       To access the media, the uid of the song and a stream token
-       must be extracted from the page source and the script must make
-       a request to media.soundcloud.com/crossdomain.xml. Then
-       the media can be grabbed by requesting from an url composed
-       of the stream token and uid
-     """
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
 
+        track_id = mobj.group('track_id')
+        if track_id is not None:
+            info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
+            full_title = track_id
+        elif mobj.group('widget'):
+            query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            return self.url_result(query['url'][0], ie='Soundcloud')
+        else:
+            # extract uploader (which is in the url)
+            uploader = mobj.group(1)
+            # extract simple title (uploader + slug of song title)
+            slug_title =  mobj.group(2)
+            full_title = '%s/%s' % (uploader, slug_title)
+    
+            self.report_resolve(full_title)
+    
+            url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+            info_json_url = self._resolv_url(url)
+        info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
+
+        info = json.loads(info_json)
+        return self._extract_info_dict(info, full_title)
+
+class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
     IE_NAME = u'soundcloud:set'
     _TEST = {
@@ -153,10 +171,6 @@ class SoundcloudSetIE(InfoExtractor):
         ]
     }
 
-    def report_resolve(self, video_id):
-        """Report information extraction."""
-        self.to_screen(u'%s: Resolving id' % video_id)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
@@ -171,7 +185,7 @@ class SoundcloudSetIE(InfoExtractor):
         self.report_resolve(full_title)
 
         url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
-        resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+        resolv_url = self._resolv_url(url)
         info_json = self._download_webpage(resolv_url, full_title)
 
         videos = []
@@ -182,23 +196,46 @@ class SoundcloudSetIE(InfoExtractor):
             return
 
         self.report_extraction(full_title)
-        for track in info['tracks']:
-            video_id = track['id']
+        return {'_type': 'playlist',
+                'entries': [self._extract_info_dict(track) for track in info['tracks']],
+                'id': info['id'],
+                'title': info['title'],
+                }
 
-            streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-            stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
 
-            self.report_extraction(video_id)
-            streams = json.loads(stream_json)
-            mediaURL = streams['http_mp3_128_url']
+class SoundcloudUserIE(SoundcloudIE):
+    _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+    IE_NAME = u'soundcloud:user'
 
-            videos.append({
-                'id':       video_id,
-                'url':      mediaURL,
-                'uploader': track['user']['username'],
-                'upload_date':  unified_strdate(track['created_at']),
-                'title':    track['title'],
-                'ext':      u'mp3',
-                'description': track['description'],
-            })
-        return videos
+    # it's in tests/test_playlists.py
+    _TEST = None
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        uploader = mobj.group('user')
+
+        url = 'http://soundcloud.com/%s/' % uploader
+        resolv_url = self._resolv_url(url)
+        user_json = self._download_webpage(resolv_url, uploader,
+            u'Downloading user info')
+        user = json.loads(user_json)
+
+        tracks = []
+        for i in itertools.count():
+            data = compat_urllib_parse.urlencode({'offset': i*50,
+                                                  'client_id': self._CLIENT_ID,
+                                                  })
+            tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data
+            response = self._download_webpage(tracks_url, uploader, 
+                u'Downloading tracks page %s' % (i+1))
+            new_tracks = json.loads(response)
+            tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks)
+            if len(new_tracks) < 50:
+                break
+
+        return {
+            '_type': 'playlist',
+            'id': compat_str(user['id']),
+            'title': user['username'],
+            'entries': tracks,
+        }

youtube_dl/extractor/southparkstudios.py

@@ -0,0 +1,38 @@
+import re
+
+from .mtv import MTVIE, _media_xml_tag
+
+
+class SouthParkStudiosIE(MTVIE):
+    IE_NAME = u'southparkstudios.com'
+    _VALID_URL = r'https?://www\.southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$)'
+
+    _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
+
+    _TEST = {
+        u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
+        u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
+        u'info_dict': {
+            u'title': u'Bat Daded',
+            u'description': u'Randy disqualifies South Park by getting into a fight with Bat Dad.',
+        },
+    }
+
+    # Overwrite MTVIE properties we don't want
+    _TESTS = []
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+        thumb_node = itemdoc.find(search_path)
+        if thumb_node is None:
+            return None
+        else:
+            return thumb_node.attrib['url']
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
+                                  webpage, u'mgid')
+        return self._get_videos_info(mgid)

youtube_dl/extractor/statigram.py

@@ -5,25 +5,19 @@ from .common import InfoExtractor
 class StatigramIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
     _TEST = {
-        u'url': u'http://statigr.am/p/484091715184808010_284179915',
-        u'file': u'484091715184808010_284179915.mp4',
-        u'md5': u'deda4ff333abe2e118740321e992605b',
+        u'url': u'http://statigr.am/p/522207370455279102_24101272',
+        u'file': u'522207370455279102_24101272.mp4',
+        u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
         u'info_dict': {
-            u"uploader_id": u"videoseconds", 
-            u"title": u"Instagram photo by @videoseconds"
-        }
+            u'uploader_id': u'aguynamedpatrick',
+            u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+        },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_regex(
-            r'<meta property="og:video:secure_url" content="(.+?)">',
-            webpage, u'video URL')
-        thumbnail_url = self._html_search_regex(
-            r'<meta property="og:image" content="(.+?)" />',
-            webpage, u'thumbnail URL', fatal=False)
         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
             webpage, u'title')
@@ -34,9 +28,9 @@ class StatigramIE(InfoExtractor):
 
         return [{
             'id':        video_id,
-            'url':       video_url,
+            'url':       self._og_search_video_url(webpage),
             'ext':       ext,
             'title':     title,
-            'thumbnail': thumbnail_url,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id' : uploader_id
         }]

youtube_dl/extractor/subtitles.py

@@ -0,0 +1,91 @@
+from .common import InfoExtractor
+
+from ..utils import (
+    compat_str,
+    ExtractorError,
+)
+
+
+class SubtitlesInfoExtractor(InfoExtractor):
+    @property
+    def _have_to_download_any_subtitles(self):
+        return any([self._downloader.params.get('writesubtitles', False),
+                    self._downloader.params.get('writeautomaticsub')])
+
+    def _list_available_subtitles(self, video_id, webpage=None):
+        """ outputs the available subtitles for the video """
+        sub_lang_list = self._get_available_subtitles(video_id)
+        auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
+        sub_lang = ",".join(list(sub_lang_list.keys()))
+        self.to_screen(u'%s: Available subtitles for video: %s' %
+                       (video_id, sub_lang))
+        auto_lang = ",".join(auto_captions_list.keys())
+        self.to_screen(u'%s: Available automatic captions for video: %s' %
+                       (video_id, auto_lang))
+
+    def extract_subtitles(self, video_id, video_webpage=None):
+        """
+        returns {sub_lang: sub} ,{} if subtitles not found or None if the
+        subtitles aren't requested.
+        """
+        if not self._have_to_download_any_subtitles:
+            return None
+        available_subs_list = {}
+        if self._downloader.params.get('writeautomaticsub', False):
+            available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage))
+        if self._downloader.params.get('writesubtitles', False):
+            available_subs_list.update(self._get_available_subtitles(video_id))
+
+        if not available_subs_list:  # error, it didn't get the available subtitles
+            return {}
+        if self._downloader.params.get('allsubtitles', False):
+            sub_lang_list = available_subs_list
+        else:
+            if self._downloader.params.get('subtitleslangs', False):
+                requested_langs = self._downloader.params.get('subtitleslangs')
+            elif 'en' in available_subs_list:
+                requested_langs = ['en']
+            else:
+                requested_langs = [list(available_subs_list.keys())[0]]
+
+            sub_lang_list = {}
+            for sub_lang in requested_langs:
+                if not sub_lang in available_subs_list:
+                    self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+                    continue
+                sub_lang_list[sub_lang] = available_subs_list[sub_lang]
+
+        subtitles = {}
+        for sub_lang, url in sub_lang_list.items():
+            subtitle = self._request_subtitle_url(sub_lang, url)
+            if subtitle:
+                subtitles[sub_lang] = subtitle
+        return subtitles
+
+    def _request_subtitle_url(self, sub_lang, url):
+        """ makes the http request for the subtitle """
+        try:
+            sub = self._download_webpage(url, None, note=False)
+        except ExtractorError as err:
+            self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
+            return
+        if not sub:
+            self._downloader.report_warning(u'Did not fetch video subtitles')
+            return
+        return sub
+
+    def _get_available_subtitles(self, video_id):
+        """
+        returns {sub_lang: url} or {} if not available
+        Must be redefined by the subclasses
+        """
+        pass
+
+    def _get_available_automatic_caption(self, video_id, webpage):
+        """
+        returns {sub_lang: url} or {} if not available
+        Must be redefined by the subclasses that support automatic captions,
+        otherwise it will return {}
+        """
+        self._downloader.report_warning(u'Automatic Captions not supported by this server')
+        return {}

youtube_dl/extractor/teamcoco.py

@@ -30,26 +30,17 @@ class TeamcocoIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
-            webpage, u'title')
-
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
-            webpage, u'thumbnail', fatal=False)
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
-            webpage, u'description', fatal=False)
-
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
         data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
 
-        video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
+        video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>',
             data, u'video URL')
 
         return [{
             'id':          video_id,
             'url':         video_url,
             'ext':         'mp4',
-            'title':       video_title,
-            'thumbnail':   thumbnail,
-            'description': video_description,
+            'title':       self._og_search_title(webpage),
+            'thumbnail':   self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
         }]

youtube_dl/extractor/ted.py

@@ -67,7 +67,7 @@ class TEDIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name)
         self.report_extraction(video_name)
         # If the url includes the language we get the title translated
-        title = self._html_search_regex(r'<span id="altHeadline" >(?P<title>.*)</span>',
+        title = self._html_search_regex(r'<span .*?id="altHeadline".+?>(?P<title>.*)</span>',
                                         webpage, 'title')
         json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>',
                                     webpage, 'json data')

youtube_dl/extractor/tf1.py

@@ -6,19 +6,17 @@ import re
 from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
-    """
-    TF1 uses the wat.tv player, currently it can only download videos with the
-    html5 player enabled, it cannot download HD videos.
-    """
+    """TF1 uses the wat.tv player."""
     _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
     _TEST = {
         u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         u'file': u'10635995.mp4',
-        u'md5': u'66789d3e91278d332f75e1feb7aea327',
+        u'md5': u'2e378cc28b9957607d5e88f274e637d8',
         u'info_dict': {
             u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
             u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
-        }
+        },
+        u'skip': u'Sometimes wat serves the whole file with the --test option',
     }
 
     def _real_extract(self, url):