release 2013.04.18

Although cool, that seems to break a lot of youtube videos.

This reverts commit a60b854d90.

README.md

@@ -20,8 +20,8 @@ which means you can modify it, redistribute it or use it however you like.
     -i, --ignore-errors        continue on download errors
     -r, --rate-limit LIMIT     maximum download rate (e.g. 50k or 44.6m)
     -R, --retries RETRIES      number of retries (default is 10)
-    --buffer-size SIZE       size of download buffer (e.g. 1024 or 16k) (default
-                             is 1024)
+    --buffer-size SIZE         size of download buffer (e.g. 1024 or 16k)
+                               (default is 1024)
     --no-resize-buffer         do not automatically adjust the buffer size. By
                                default, the buffer size is automatically resized
                                from an initial value of SIZE.
@@ -38,8 +38,8 @@ which means you can modify it, redistribute it or use it however you like.
     --reject-title REGEX       skip download for matching titles (regex or
                                caseless sub-string)
     --max-downloads NUMBER     Abort after downloading NUMBER files
-    --min-filesize SIZE      Do not download any videos smaller than SIZE (e.g.
-                             50k or 44.6m)
+    --min-filesize SIZE        Do not download any videos smaller than SIZE
+                               (e.g. 50k or 44.6m)
     --max-filesize SIZE        Do not download any videos larger than SIZE (e.g.
                                50k or 44.6m)
 
@@ -48,8 +48,8 @@ which means you can modify it, redistribute it or use it however you like.
     --id                       use video ID in file name
     -l, --literal              [deprecated] alias of --title
     -A, --auto-number          number downloaded files starting from 00000
-    -o, --output TEMPLATE    output filename template. Use %(title)s to get the
-                             title, %(uploader)s for the uploader name,
+    -o, --output TEMPLATE      output filename template. Use %(title)s to get
+                               the title, %(uploader)s for the uploader name,
                                %(uploader_id)s for the uploader nickname if
                                different, %(autonumber)s to get an automatically
                                incremented number, %(ext)s for the filename
@@ -57,9 +57,12 @@ which means you can modify it, redistribute it or use it however you like.
                                (YYYYMMDD), %(extractor)s for the provider
                                (youtube, metacafe, etc), %(id)s for the video id
                                and %% for a literal percent. Use - to output to
-                             stdout. Can also be used to download to a different
-                             directory, for example with -o '/my/downloads/%(upl
-                             oader)s/%(title)s-%(id)s.%(ext)s' .
+                               stdout. Can also be used to download to a
+                               different directory, for example with -o '/my/dow
+                               nloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+    --autonumber-size NUMBER   Specifies the number of digits in %(autonumber)s
+                               when it is present in output filename template or
+                               --autonumber option is given
     --restrict-filenames       Restrict filenames to only ASCII characters, and
                                avoid "&" and spaces in filenames
     -a, --batch-file FILE      file containing URLs to download ('-' for stdin)
@@ -69,15 +72,15 @@ which means you can modify it, redistribute it or use it however you like.
                                from beginning)
     --cookies FILE             file to read cookies from and dump cookie jar in
     --no-part                  do not use .part files
-    --no-mtime               do not use the Last-modified header to set the file
-                             modification time
+    --no-mtime                 do not use the Last-modified header to set the
+                               file modification time
     --write-description        write video description to a .description file
     --write-info-json          write video metadata to a .info.json file
 
 ## Verbosity / Simulation Options:
     -q, --quiet                activates quiet mode
-    -s, --simulate           do not download the video and do not write anything
-                             to disk
+    -s, --simulate             do not download the video and do not write
+                               anything to disk
     --skip-download            do not download the video
     -g, --get-url              simulate, quiet but print URL
     -e, --get-title            simulate, quiet but print title
@@ -89,22 +92,25 @@ which means you can modify it, redistribute it or use it however you like.
     --no-progress              do not print progress bar
     --console-title            display progress in console titlebar
     -v, --verbose              print various debugging information
+    --dump-intermediate-pages  print downloaded pages to debug problems(very
+                               verbose)
 
 ## Video Format Options:
     -f, --format FORMAT        video format code
     --all-formats              download all available video formats
-    --prefer-free-formats    prefer free video formats unless a specific one is
-                             requested
+    --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)
+    -F, --list-formats         list all available formats (currently youtube
+                               only)
     --write-sub                write subtitle file (currently youtube only)
     --only-sub                 downloads only the subtitles (no video)
-    --all-subs               downloads all the available subtitles of the video
-                             (currently youtube only)
+    --all-subs                 downloads all the available subtitles of the
+                               video (currently youtube only)
     --list-subs                lists all available subtitles for the video
                                (currently youtube only)
-    --sub-format LANG        subtitle format [srt/sbv] (default=srt) (currently
-                             youtube only)
+    --sub-format LANG          subtitle format [srt/sbv] (default=srt)
+                               (currently youtube only)
     --sub-lang LANG            language of the subtitles to download (optional)
                                use IETF language tags like 'en'
 
@@ -118,9 +124,9 @@ which means you can modify it, redistribute it or use it however you like.
                                ffmpeg or avconv and ffprobe or avprobe)
     --audio-format FORMAT      "best", "aac", "vorbis", "mp3", "m4a", "opus", or
                                "wav"; best by default
-    --audio-quality QUALITY  ffmpeg/avconv audio quality specification, insert a
-                             value between 0 (better) and 9 (worse) for VBR or a
-                             specific bitrate like 128K (default 5)
+    --audio-quality QUALITY    ffmpeg/avconv audio quality specification, insert
+                               a value between 0 (better) and 9 (worse) for VBR
+                               or a specific bitrate like 128K (default 5)
     --recode-video FORMAT      Encode the video to another format if necessary
                                (currently supported: mp4|flv|ogg|webm)
     -k, --keep-video           keeps the video file on disk after the post-

devscripts/gh-pages/update-feed.py

@@ -9,7 +9,7 @@ import json
 atom_template=textwrap.dedent("""\
 								<?xml version='1.0' encoding='utf-8'?>
 								<atom:feed xmlns:atom="http://www.w3.org/2005/Atom">
-									<atom:subtitle>Updates feed.</atom:subtitle>
+									<atom:title>youtube-dl releases</atom:title>
 									<atom:id>youtube-dl-updates-feed</atom:id>
 									<atom:updated>@TIMESTAMP@</atom:updated>
 									@ENTRIES@
@@ -19,7 +19,7 @@ entry_template=textwrap.dedent("""
 								<atom:entry>
 									<atom:id>youtube-dl-@VERSION@</atom:id>
 									<atom:title>New version @VERSION@</atom:title>
-									<atom:link href="http://rg3.github.com/youtube-dl" />
+									<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>
@@ -51,7 +51,7 @@ for v in versions:
 entries_str = textwrap.indent(''.join(entries), '\t')
 atom_template = atom_template.replace('@ENTRIES@', entries_str)
 
-with open('update/atom.atom','w',encoding='utf-8') as atom_file:
+with open('update/releases.atom','w',encoding='utf-8') as atom_file:
 	atom_file.write(atom_template)
 
 

devscripts/transition_helper_exe/youtube-dl.py

@@ -40,7 +40,7 @@ raw_input()
 
 filename = sys.argv[0]
 
-UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
+UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
 VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
 JSON_URL = UPDATE_URL + 'versions.json'
 UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)

test/test_download.py

@@ -58,6 +58,7 @@ with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
 
 
 class TestDownload(unittest.TestCase):
+    maxDiff = None
     def setUp(self):
         self.parameters = parameters
         self.defs = defs
@@ -81,9 +82,8 @@ def generator(test_case):
         params.update(test_case.get('params', {}))
 
         fd = FileDownloader(params)
-        fd.add_info_extractor(ie())
-        for ien in test_case.get('add_ie', []):
-            fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
+        for ie in youtube_dl.InfoExtractors.gen_extractors():
+            fd.add_info_extractor(ie)
         finished_hook_called = set()
         def _hook(status):
             if status['status'] == 'finished':
@@ -103,7 +103,7 @@ def generator(test_case):
                     if retry == RETRIES: raise
 
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (ZeroDivisionError, compat_urllib_error.URLError, socket.timeout):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
                         raise
 
                     print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry))

test/tests.json

@@ -76,8 +76,7 @@
     "name": "StanfordOpenClassroom",
     "md5":  "544a9468546059d4e80d76265b0443b8",
     "url":  "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
-    "file":  "PracticalUnix_intro-environment.mp4",
-    "skip": "Currently offline"
+    "file":  "PracticalUnix_intro-environment.mp4"
   },
   {
     "name": "XNXX",
@@ -328,5 +327,16 @@
     "info_dict": {
         "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! "
     }
+  },
+  {
+    "name": "ARD",
+    "url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640",
+    "file": "14077640.mp4",
+    "md5": "6ca8824255460c787376353f9e20bbd8",
+    "info_dict": {
+        "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+    },
+    "skip": "Requires rtmpdump"
   }
+
 ]

youtube_dl/FileDownloader.py

@@ -388,7 +388,11 @@ class FileDownloader(object):
             template_dict = dict(info_dict)
 
             template_dict['epoch'] = int(time.time())
-            template_dict['autonumber'] = u'%05d' % self._num_downloads
+            autonumber_size = self.params.get('autonumber_size')
+            if autonumber_size is None:
+                autonumber_size = 5
+            autonumber_templ = u'%0' + str(autonumber_size) + u'd'
+            template_dict['autonumber'] = autonumber_templ % self._num_downloads
 
             sanitize = lambda k,v: sanitize_filename(
                 u'NA' if v is None else compat_str(v),
@@ -422,6 +426,10 @@ class FileDownloader(object):
     def process_info(self, info_dict):
         """Process a single dictionary returned by an InfoExtractor."""
 
+        info_dict['fulltitle'] = info_dict['title']
+        if len(info_dict['title']) > 200:
+            info_dict['title'] = info_dict['title'][:197] + u'...'
+
         # Keep for backwards compatibility
         info_dict['stitle'] = info_dict['title']
 
@@ -485,6 +493,9 @@ class FileDownloader(object):
             subtitle = info_dict['subtitles'][0]
             (sub_error, sub_lang, sub) = subtitle
             sub_format = self.params.get('subtitlesformat')
+            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)
@@ -501,6 +512,9 @@ class FileDownloader(object):
             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)
@@ -623,7 +637,7 @@ class FileDownloader(object):
             except (IOError, OSError):
                 self.report_warning(u'Unable to remove downloaded video file')
 
-    def _download_with_rtmpdump(self, filename, url, player_url, page_url):
+    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
@@ -642,6 +656,8 @@ class FileDownloader(object):
             basic_args += ['-W', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
+        if play_path is not None:
+            basic_args += ['-y', play_path]
         args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
         if self.params.get('verbose', False):
             try:
@@ -696,7 +712,8 @@ class FileDownloader(object):
         if url.startswith('rtmp'):
             return self._download_with_rtmpdump(filename, url,
                                                 info_dict.get('player_url', None),
-                                                info_dict.get('page_url', None))
+                                                info_dict.get('page_url', None),
+                                                info_dict.get('play_path', None))
 
         tmpfilename = self.temp_name(filename)
         stream = None

youtube_dl/InfoExtractors.py

@@ -115,6 +115,7 @@ class InfoExtractor(object):
         """ Returns the response handle """
         if note is None:
             note = u'Downloading video webpage'
+        if note is not False:
             self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
         try:
             return compat_urllib_request.urlopen(url_or_request)
@@ -133,6 +134,14 @@ class InfoExtractor(object):
         else:
             encoding = 'utf-8'
         webpage_bytes = urlh.read()
+        if self._downloader.params.get('dump_intermediate_pages', False):
+            try:
+                url = url_or_request.get_full_url()
+            except AttributeError:
+                url = url_or_request
+            self._downloader.to_screen(u'Dumping request to ' + url)
+            dump = base64.b64encode(webpage_bytes).decode('ascii')
+            self._downloader.to_screen(dump)
         return webpage_bytes.decode(encoding, 'replace')
 
 
@@ -253,11 +262,11 @@ class YoutubeIE(InfoExtractor):
         try:
             sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
+            return (u'unable to download video subtitles: %s' % compat_str(err), None)
         sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
         sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
         if not sub_lang_list:
-            return (u'WARNING: video doesn\'t have subtitles', None)
+            return (u'video doesn\'t have subtitles', None)
         return sub_lang_list
 
     def _list_available_subtitles(self, video_id):
@@ -265,6 +274,10 @@ class YoutubeIE(InfoExtractor):
         self.report_video_subtitles_available(video_id, sub_lang_list)
 
     def _request_subtitle(self, sub_lang, sub_name, video_id, format):
+        """
+        Return tuple:
+        (error_message, sub_lang, sub)
+        """
         self.report_video_subtitles_request(video_id, sub_lang, format)
         params = compat_urllib_parse.urlencode({
             'lang': sub_lang,
@@ -276,14 +289,20 @@ class YoutubeIE(InfoExtractor):
         try:
             sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
+            return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
         if not sub:
-            return (u'WARNING: Did not fetch video subtitles', None)
+            return (u'Did not fetch video subtitles', None, None)
         return (None, sub_lang, sub)
 
     def _extract_subtitle(self, video_id):
+        """
+        Return a list with a tuple:
+        [(error_message, sub_lang, sub)]
+        """
         sub_lang_list = self._get_available_subtitles(video_id)
         sub_format = self._downloader.params.get('subtitlesformat')
+        if  isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+            return [(sub_lang_list[0], None, None)]
         if self._downloader.params.get('subtitleslang', False):
             sub_lang = self._downloader.params.get('subtitleslang')
         elif 'en' in sub_lang_list:
@@ -291,7 +310,7 @@ class YoutubeIE(InfoExtractor):
         else:
             sub_lang = list(sub_lang_list.keys())[0]
         if not sub_lang in sub_lang_list:
-            return (u'WARNING: no closed captions found in the specified language "%s"' % sub_lang, None)
+            return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
 
         subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
         return [subtitle]
@@ -299,6 +318,8 @@ class YoutubeIE(InfoExtractor):
     def _extract_all_subtitles(self, video_id):
         sub_lang_list = self._get_available_subtitles(video_id)
         sub_format = self._downloader.params.get('subtitlesformat')
+        if  isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+            return [(sub_lang_list[0], None, None)]
         subtitles = []
         for sub_lang in sub_lang_list:
             subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
@@ -451,18 +472,14 @@ class YoutubeIE(InfoExtractor):
         # Get video info
         self.report_video_info_webpage_download(video_id)
         for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
-            video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+            video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
                     % (video_id, el_type))
-            request = compat_urllib_request.Request(video_info_url)
-            try:
-                video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
-                video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
+            video_info_webpage = self._download_webpage(video_info_url, video_id,
+                                    note=False,
+                                    errnote='unable to download video info webpage')
             video_info = compat_parse_qs(video_info_webpage)
             if 'token' in video_info:
                 break
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                self._downloader.report_error(u'unable to download video info webpage: %s' % compat_str(err))
-                return
         if 'token' not in video_info:
             if 'reason' in video_info:
                 self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0])
@@ -532,14 +549,14 @@ class YoutubeIE(InfoExtractor):
             if video_subtitles:
                 (sub_error, sub_lang, sub) = video_subtitles[0]
                 if sub_error:
-                    self._downloader.trouble(sub_error)
+                    self._downloader.report_error(sub_error)
 
         if self._downloader.params.get('allsubtitles', False):
             video_subtitles = self._extract_all_subtitles(video_id)
             for video_subtitle in video_subtitles:
                 (sub_error, sub_lang, sub) = video_subtitle
                 if sub_error:
-                    self._downloader.trouble(sub_error)
+                    self._downloader.report_error(sub_error)
 
         if self._downloader.params.get('listsubtitles', False):
             sub_lang_list = self._list_available_subtitles(video_id)
@@ -1118,7 +1135,7 @@ class VimeoIE(InfoExtractor):
         # Extract video description
         video_description = get_element_by_attribute("itemprop", "description", webpage)
         if video_description: video_description = clean_html(video_description)
-        else: video_description = ''
+        else: video_description = u''
 
         # Extract upload date
         video_upload_date = None
@@ -1710,9 +1727,7 @@ class YoutubePlaylistIE(InfoExtractor):
                         (?:
                            (?:course|view_play_list|my_playlists|artist|playlist|watch)
                            \? (?:.*?&)*? (?:p|a|list)=
-                        |  user/.*?/user/
                         |  p/
-                        |  user/.*?#[pg]/c/
                         )
                         ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
                         .*
@@ -2146,7 +2161,7 @@ class FacebookIE(InfoExtractor):
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
-        BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n'
+        BEFORE = '{swf.addParam(param[0], param[1]);});\n'
         AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
         m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
         if not m:
@@ -2154,12 +2169,14 @@ class FacebookIE(InfoExtractor):
         data = dict(json.loads(m.group(1)))
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)
-        video_url = params['hd_src']
+        video_data = params['video_data'][0]
+        video_url = video_data.get('hd_src')
         if not video_url:
-            video_url = params['sd_src']
+            video_url = video_data['sd_src']
         if not video_url:
             raise ExtractorError(u'Cannot find video URL')
-        video_duration = int(params['video_duration'])
+        video_duration = int(video_data['video_duration'])
+        thumbnail = video_data['thumbnail_src']
 
         m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
         if not m:
@@ -2172,7 +2189,7 @@ class FacebookIE(InfoExtractor):
             'url': video_url,
             'ext': 'mp4',
             'duration': video_duration,
-            'thumbnail': params['thumbnail_src'],
+            'thumbnail': thumbnail,
         }
         return [info]
 
@@ -3686,6 +3703,8 @@ class FunnyOrDieIE(InfoExtractor):
         video_url = unescapeHTML(m.group('url'))
 
         m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
+        if not m:
+            m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
             if not m:
                 self._downloader.trouble(u'Cannot find video title')
         title = clean_html(m.group('title'))
@@ -4121,7 +4140,7 @@ class KeekIE(InfoExtractor):
         video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
         thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
-        m = re.search(r'<meta property="og:title" content="(?P<title>.+)"', webpage)
+        m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
         title = unescapeHTML(m.group('title'))
         m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
         uploader = clean_html(m.group('uploader'))
@@ -4346,6 +4365,46 @@ class LiveLeakIE(InfoExtractor):
 
         return [info]
 
+class ARDIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+    _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
+    _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+
+    def _real_extract(self, url):
+        # determine video id from url
+        m = re.match(self._VALID_URL, url)
+
+        numid = re.search(r'documentId=([0-9]+)', url)
+        if numid:
+            video_id = numid.group(1)
+        else:
+            video_id = m.group('video_id')
+
+        # determine title and media streams from webpage
+        html = self._download_webpage(url, video_id)
+        title = re.search(self._TITLE, html).group('title')
+        streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+        if not streams:
+            assert '"fsk"' in html
+            self._downloader.report_error(u'this video is only available after 8:00 pm')
+            return
+
+        # choose default media type and highest quality for now
+        stream = max([s for s in streams if int(s["media_type"]) == 0],
+                     key=lambda s: int(s["quality"]))
+
+        # there's two possibilities: RTMP stream or HTTP download
+        info = {'id': video_id, 'title': title, 'ext': 'mp4'}
+        if stream['rtmp_url']:
+            self._downloader.to_screen(u'[%s] RTMP download detected' % self.IE_NAME)
+            assert stream['video_url'].startswith('mp4:')
+            info["url"] = stream["rtmp_url"]
+            info["play_path"] = stream['video_url']
+        else:
+            assert stream["video_url"].endswith('.mp4')
+            info["url"] = stream["video_url"]
+        return [info]
+
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
@@ -4399,5 +4458,6 @@ def gen_extractors():
         MySpassIE(),
         SpiegelIE(),
         LiveLeakIE(),
+        ARDIE(),
         GenericIE()
     ]

youtube_dl/__init__.py

@@ -24,6 +24,7 @@ __authors__  = (
     'Jaime Marquínez Ferrándiz',
     'Jeff Crouse',
     'Osama Khalid',
+    'Michael Walter',
     )
 
 __license__ = 'Public Domain'
@@ -223,6 +224,9 @@ def parseOpts():
             help='display progress in console titlebar', default=False)
     verbosity.add_option('-v', '--verbose',
             action='store_true', dest='verbose', help='print various debugging information', default=False)
+    verbosity.add_option('--dump-intermediate-pages',
+            action='store_true', dest='dump_intermediate_pages', default=False,
+            help='print downloaded pages to debug problems(very verbose)')
 
     filesystem.add_option('-t', '--title',
             action='store_true', dest='usetitle', help='use title in file name', default=False)
@@ -235,6 +239,9 @@ def parseOpts():
             help='number downloaded files starting from 00000', default=False)
     filesystem.add_option('-o', '--output',
             dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')
+    filesystem.add_option('--autonumber-size',
+            dest='autonumber_size', metavar='NUMBER',
+            help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given')
     filesystem.add_option('--restrict-filenames',
             action='store_true', dest='restrictfilenames',
             help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
@@ -451,6 +458,7 @@ def _real_main():
         'format_limit': opts.format_limit,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
+        'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'ratelimit': opts.ratelimit,
@@ -480,6 +488,7 @@ def _real_main():
         'max_downloads': opts.max_downloads,
         'prefer_free_formats': opts.prefer_free_formats,
         'verbose': opts.verbose,
+        'dump_intermediate_pages': opts.dump_intermediate_pages,
         'test': opts.test,
         'keepvideo': opts.keepvideo,
         'min_filesize': opts.min_filesize,

youtube_dl/__main__.py

@@ -9,7 +9,8 @@ import sys
 if __package__ is None and not hasattr(sys, "frozen"):
     # direct call of __main__.py
     import os.path
-    sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+    path = os.path.realpath(os.path.abspath(__file__))
+    sys.path.append(os.path.dirname(os.path.dirname(path)))
 
 import youtube_dl
 

youtube_dl/update.py

@@ -37,7 +37,7 @@ def rsa_verify(message, signature, key):
 def update_self(to_screen, verbose, filename):
     """Update the program file with the latest version from the repository"""
 
-    UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
+    UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
     VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
     JSON_URL = UPDATE_URL + 'versions.json'
     UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2013.03.29'
+__version__ = '2013.04.18'