release 2016.06.20

This reverts commit 7c05097633.

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.03*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.20*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.03**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.20**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.06.03
+[debug] youtube-dl version 2016.06.20
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -173,3 +173,5 @@ Kevin Deldycke
 inondle
 Tomáš Čech
 Déstin Reed
+Roman Tsiupa
+Artur Krysiak

CONTRIBUTING.md

@@ -142,9 +142,9 @@ After you have ensured this site is distributing it's content legally, you can f
     ```
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
-8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
+8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L148-L252) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
-9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
+9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
 10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py

README.md

@@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 
 To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
-    sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo curl -L https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
     sudo chmod a+rx /usr/local/bin/youtube-dl
 
 If you do not have curl, you can alternatively use a recent wget:
@@ -27,18 +27,24 @@ If you do not have curl, you can alternatively use a recent wget:
 
 Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
 
-OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/).
+You can also use pip:
+
+    sudo pip install --upgrade youtube-dl
+    
+This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
+
+OS X users can install youtube-dl with [Homebrew](http://brew.sh/):
 
     brew install youtube-dl
 
-You can also use pip:
+Or with [MacPorts](https://www.macports.org/):
 
-    sudo pip install youtube-dl
+    sudo port install youtube-dl
 
 Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
-**youtube-dl** is a small command-line program to download videos from
+**youtube-dl** is a command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
 your Unix box, on Windows or on Mac OS X. It is released to the public domain,
@@ -249,7 +255,7 @@ which means you can modify it, redistribute it or use it however you like.
     --write-info-json                Write video metadata to a .info.json file
     --write-annotations              Write video annotations to a
                                      .annotations.xml file
-    --load-info FILE                 JSON file containing the video information
+    --load-info-json FILE            JSON file containing the video information
                                      (created with the "--write-info-json"
                                      option)
     --cookies FILE                   File to read cookies from and dump cookie
@@ -505,6 +511,9 @@ The basic usage is not to set any template arguments when downloading a single f
  - `autonumber`: Five-digit number that will be increased with each download, starting at zero
  - `playlist`: Name or id of the playlist that contains the video
  - `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
+ - `playlist_id`: Playlist identifier
+ - `playlist_title`: Playlist title
+
 
 Available for the video that belongs to some logical chapter or section:
  - `chapter`: Name or title of the chapter the video belongs to
@@ -544,6 +553,10 @@ The current default template is `%(title)s-%(id)s.%(ext)s`.
 
 In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
 
+#### Output template and Windows batch files
+
+If you are using output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`.
+
 #### Output template examples
 
 Note on Windows you may need to use double quotes instead of single.
@@ -842,6 +855,12 @@ It is *not* possible to detect whether a URL is supported or not. That's because
 
 If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
 
+# Why do I need to go through that much red tape when filing bugs?
+
+Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was alrady reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl.
+
+youtube-dl is an open-source project manned by too few volunteers, so we'd rather spend time fixing bugs where we are certain none of those simple problems apply, and where we can be reasonably confident to be able to reproduce the issue without asking the reporter repeatedly. As such, the output of `youtube-dl -v YOUR_URL_HERE` is really all that's required to file an issue. The issue template also guides you through some basic steps you can do, such as checking that your version of youtube-dl is current.
+
 # DEVELOPER INSTRUCTIONS
 
 Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
@@ -916,9 +935,9 @@ After you have ensured this site is distributing it's content legally, you can f
     ```
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
-8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
+8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L148-L252) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
-9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
+9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
 10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py
@@ -945,7 +964,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 

devscripts/buildserver.py

@@ -13,6 +13,7 @@ import os.path
 
 sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__)))))
 from youtube_dl.compat import (
+    compat_input,
     compat_http_server,
     compat_str,
     compat_urlparse,
@@ -30,11 +31,6 @@ try:
 except ImportError:  # Python 2
     import SocketServer as compat_socketserver
 
-try:
-    compat_input = raw_input
-except NameError:  # Python 3
-    compat_input = input
-
 
 class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer):
     allow_reuse_address = True

devscripts/create-github-release.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import base64
+import json
+import mimetypes
+import netrc
+import optparse
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.compat import (
+    compat_basestring,
+    compat_input,
+    compat_getpass,
+    compat_print,
+    compat_urllib_request,
+)
+from youtube_dl.utils import (
+    make_HTTPS_handler,
+    sanitized_Request,
+)
+
+
+class GitHubReleaser(object):
+    _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases'
+    _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s'
+    _NETRC_MACHINE = 'github.com'
+
+    def __init__(self, debuglevel=0):
+        self._init_github_account()
+        https_handler = make_HTTPS_handler({}, debuglevel=debuglevel)
+        self._opener = compat_urllib_request.build_opener(https_handler)
+
+    def _init_github_account(self):
+        try:
+            info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+            if info is not None:
+                self._username = info[0]
+                self._password = info[2]
+                compat_print('Using GitHub credentials found in .netrc...')
+                return
+            else:
+                compat_print('No GitHub credentials found in .netrc')
+        except (IOError, netrc.NetrcParseError):
+            compat_print('Unable to parse .netrc')
+        self._username = compat_input(
+            'Type your GitHub username or email address and press [Return]: ')
+        self._password = compat_getpass(
+            'Type your GitHub password and press [Return]: ')
+
+    def _call(self, req):
+        if isinstance(req, compat_basestring):
+            req = sanitized_Request(req)
+        # Authorizing manually since GitHub does not response with 401 with
+        # WWW-Authenticate header set (see
+        # https://developer.github.com/v3/#basic-authentication)
+        b64 = base64.b64encode(
+            ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii')
+        req.add_header('Authorization', 'Basic %s' % b64)
+        response = self._opener.open(req).read().decode('utf-8')
+        return json.loads(response)
+
+    def list_releases(self):
+        return self._call(self._API_URL)
+
+    def create_release(self, tag_name, name=None, body='', draft=False, prerelease=False):
+        data = {
+            'tag_name': tag_name,
+            'target_commitish': 'master',
+            'name': name,
+            'body': body,
+            'draft': draft,
+            'prerelease': prerelease,
+        }
+        req = sanitized_Request(self._API_URL, json.dumps(data).encode('utf-8'))
+        return self._call(req)
+
+    def create_asset(self, release_id, asset):
+        asset_name = os.path.basename(asset)
+        url = self._UPLOADS_URL % (release_id, asset_name)
+        # Our files are small enough to be loaded directly into memory.
+        data = open(asset, 'rb').read()
+        req = sanitized_Request(url, data)
+        mime_type, _ = mimetypes.guess_type(asset_name)
+        req.add_header('Content-Type', mime_type or 'application/octet-stream')
+        return self._call(req)
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH')
+    options, args = parser.parse_args()
+    if len(args) != 2:
+        parser.error('Expected a version and a build directory')
+
+    version, build_path = args
+
+    releaser = GitHubReleaser()
+
+    new_release = releaser.create_release(version, name='youtube-dl %s' % version)
+    release_id = new_release['id']
+
+    for asset in os.listdir(build_path):
+        compat_print('Uploading %s...' % asset)
+        releaser.create_asset(release_id, os.path.join(build_path, asset))
+
+
+if __name__ == '__main__':
+    main()

devscripts/release.sh

@@ -15,6 +15,7 @@
 set -e
 
 skip_tests=true
+gpg_sign_commits=""
 buildserver='localhost:8142'
 
 while true
@@ -24,6 +25,10 @@ case "$1" in
         skip_tests=false
         shift
     ;;
+    --gpg-sign-commits|-S)
+        gpg_sign_commits="-S"
+        shift
+    ;;
     --buildserver)
         buildserver="$2"
         shift 2
@@ -69,7 +74,7 @@ sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 /bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
 make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
 git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py
-git commit -m "release $version"
+git commit $gpg_sign_commits -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
 git tag -s -m "Release $version" "$version"
@@ -95,15 +100,16 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
 
-/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
+/bin/echo -e "\n### Signing and uploading the new binaries to GitHub..."
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
-scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
+
-ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
+ROOT=$(pwd)
+python devscripts/create-github-release.py $version "$ROOT/build/$version"
+
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 
 /bin/echo -e "\n### Now switching to gh-pages..."
 git clone --branch gh-pages --single-branch . build/gh-pages
-ROOT=$(pwd)
 (
     set -e
     ORIGIN_URL=$(git config --get remote.origin.url)
@@ -115,7 +121,7 @@ ROOT=$(pwd)
     "$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 commit $gpg_sign_commits -m "release $version"
     git push "$ROOT" gh-pages
     git push "$ORIGIN_URL" gh-pages
 )

docs/supportedsites.md

@@ -28,6 +28,7 @@
  - **AdobeTVVideo**
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
+ - **AfreecaTV**: afreecatv.com
  - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
@@ -73,6 +74,8 @@
  - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
  - **bbc.co.uk:article**: BBC articles
+ - **bbc.co.uk:iplayer:playlist**
+ - **bbc.co.uk:playlist**
  - **BeatportPro**
  - **Beeg**
  - **BehindKink**
@@ -103,6 +106,8 @@
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
  - **Canvas**
+ - **CarambaTV**
+ - **CarambaTVPage**
  - **CBC**
  - **CBCPlayer**
  - **CBS**
@@ -123,6 +128,7 @@
  - **cliphunter**
  - **ClipRs**
  - **Clipsyndicate**
+ - **CloserToTruth**
  - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
@@ -253,6 +259,7 @@
  - **Globo**
  - **GloboArticle**
  - **GodTube**
+ - **GodTV**
  - **GoldenMoustache**
  - **Golem**
  - **GoogleDrive**
@@ -430,6 +437,7 @@
  - **nhl.com:videocenter**
  - **nhl.com:videocenter:category**: NHL videocenter category
  - **nick.com**
+ - **nick.de**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
  - **njoy**: N-JOY
@@ -514,6 +522,7 @@
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
  - **R7**
+ - **R7Article**
  - **radio.de**
  - **radiobremen**
  - **radiocanada**
@@ -533,6 +542,7 @@
  - **revision3:embed**
  - **RICE**
  - **RingTV**
+ - **RockstarGames**
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
@@ -645,6 +655,7 @@
  - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
+ - **Telewebion**
  - **TF1**
  - **TheIntercept**
  - **ThePlatform**
@@ -696,6 +707,7 @@
  - **TVPlay**: TV3Play and related services
  - **Tweakers**
  - **twitch:chapter**
+ - **twitch:clips**
  - **twitch:past_broadcasts**
  - **twitch:profile**
  - **twitch:stream**
@@ -738,6 +750,7 @@
  - **VideoPremium**
  - **VideoTt**: video.tt - Your True Tube (Currently broken)
  - **videoweed**: VideoWeed
+ - **Vidio**
  - **vidme**
  - **vidme:user**
  - **vidme:user:likes**
@@ -773,7 +786,6 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
- - **vulture.com**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**
@@ -781,10 +793,8 @@
  - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
- - **WDRMaus**: Sendung mit der Maus
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
- - **Weibo**
  - **WeiqiTV**: WQTV
  - **wholecloud**: WholeCloud
  - **Wimp**
@@ -792,10 +802,11 @@
  - **WNL**
  - **WorldStarHipHop**
  - **wrzuta.pl**
+ - **wrzuta.pl:playlist**
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To
+ - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE
  - **XHamster**
  - **XHamsterEmbed**
  - **xiami:album**: 虾米音乐 - 专辑
@@ -820,6 +831,7 @@
  - **Ynet**
  - **YouJizz**
  - **youku**: 优酷
+ - **youku:show**
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com

setup.py

@@ -122,6 +122,7 @@ setup(
         "Programming Language :: Python :: 3.2",
         "Programming Language :: Python :: 3.3",
         "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.5",
     ],
 
     cmdclass={'build_lazy_extractors': build_lazy_extractors},

test/test_utils.py

@@ -249,6 +249,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unescapeHTML('/'), '/')
         self.assertEqual(unescapeHTML('é'), 'é')
         self.assertEqual(unescapeHTML('�'), '�')
+        # HTML5 entities
+        self.assertEqual(unescapeHTML('.''), '.\'')
 
     def test_date_from_str(self):
         self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
@@ -638,6 +640,9 @@ class TestUtil(unittest.TestCase):
             "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
         }''')
 
+        inp = '''{"foo":101}'''
+        self.assertEqual(js_to_json(inp), '''{"foo":101}''')
+
     def test_js_to_json_edgecases(self):
         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})

youtube_dl/YoutubeDL.py

@@ -1223,6 +1223,10 @@ class YoutubeDL(object):
         if 'title' not in info_dict:
             raise ExtractorError('Missing "title" field in extractor result')
 
+        if not isinstance(info_dict['id'], compat_str):
+            self.report_warning('"id" field is not a string - forcing string conversion')
+            info_dict['id'] = compat_str(info_dict['id'])
+
         if 'playlist' not in info_dict:
             # It isn't part of a playlist
             info_dict['playlist'] = None

youtube_dl/__init__.py

@@ -18,7 +18,6 @@ from .options import (
 from .compat import (
     compat_expanduser,
     compat_getpass,
-    compat_print,
     compat_shlex_split,
     workaround_optparse_bug9161,
 )
@@ -76,7 +75,7 @@ def _real_main(argv=None):
 
     # Dump user agent
     if opts.dump_user_agent:
-        compat_print(std_headers['User-Agent'])
+        write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
         sys.exit(0)
 
     # Batch file verification
@@ -101,10 +100,10 @@ def _real_main(argv=None):
 
     if opts.list_extractors:
         for ie in list_extractors(opts.age_limit):
-            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+            write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
-                compat_print('  ' + mu)
+                write_string('  ' + mu + '\n', out=sys.stdout)
         sys.exit(0)
     if opts.list_extractor_descriptions:
         for ie in list_extractors(opts.age_limit):
@@ -117,7 +116,7 @@ def _real_main(argv=None):
                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
-            compat_print(desc)
+            write_string(desc + '\n', out=sys.stdout)
         sys.exit(0)
 
     # Conflicting, missing and erroneous options

youtube_dl/downloader/external.py

@@ -85,7 +85,7 @@ class ExternalFD(FileDownloader):
             cmd, stderr=subprocess.PIPE)
         _, stderr = p.communicate()
         if p.returncode != 0:
-            self.to_stderr(stderr)
+            self.to_stderr(stderr.decode('utf-8', 'replace'))
         return p.returncode
 
 
@@ -210,6 +210,7 @@ class FFmpegFD(ExternalFD):
             # args += ['-http_proxy', proxy]
             env = os.environ.copy()
             compat_setenv('HTTP_PROXY', proxy, env=env)
+            compat_setenv('http_proxy', proxy, env=env)
 
         protocol = info_dict.get('protocol')
 

youtube_dl/downloader/hls.py

@@ -2,14 +2,24 @@ from __future__ import unicode_literals
 
 import os.path
 import re
+import binascii
+try:
+    from Crypto.Cipher import AES
+    can_decrypt_frag = True
+except ImportError:
+    can_decrypt_frag = False
 
 from .fragment import FragmentFD
 from .external import FFmpegFD
 
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_urlparse,
+    compat_struct_pack,
+)
 from ..utils import (
     encodeFilename,
     sanitize_open,
+    parse_m3u8_attributes,
 )
 
 
@@ -21,19 +31,27 @@ class HlsFD(FragmentFD):
     @staticmethod
     def can_download(manifest):
         UNSUPPORTED_FEATURES = (
-            r'#EXT-X-KEY:METHOD=(?!NONE)',  # encrypted streams [1]
+            r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
+
             # Live streams heuristic does not always work (e.g. geo restricted to Germany
             # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
             # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)',  # live streams [3]
-            r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+
-                                            # event media playlists [4]
+            # This heuristic also is not correct since segments may not be appended as well.
+            # Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite
+            # no segments will definitely be appended to the end of the playlist.
+            # r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+            #                                 # event media playlists [4]
+
             # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
             # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
             # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
             # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
         )
-        return all(not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
+        check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
+        check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
+        return all(check_results)
 
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
@@ -51,36 +69,60 @@ class HlsFD(FragmentFD):
                 fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
-        fragment_urls = []
+        total_frags = 0
         for line in s.splitlines():
             line = line.strip()
             if line and not line.startswith('#'):
-                segment_url = (
+                total_frags += 1
-                    line
-                    if re.match(r'^https?://', line)
-                    else compat_urlparse.urljoin(man_url, line))
-                fragment_urls.append(segment_url)
-                # We only download the first fragment during the test
-                if self.params.get('test', False):
-                    break
 
         ctx = {
             'filename': filename,
-            'total_frags': len(fragment_urls),
+            'total_frags': total_frags,
         }
 
         self._prepare_and_start_frag_download(ctx)
 
+        i = 0
+        media_sequence = 0
+        decrypt_info = {'METHOD': 'NONE'}
         frags_filenames = []
-        for i, frag_url in enumerate(fragment_urls):
+        for line in s.splitlines():
-            frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+            line = line.strip()
-            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+            if line:
-            if not success:
+                if not line.startswith('#'):
-                return False
+                    frag_url = (
-            down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+                        line
-            ctx['dest_stream'].write(down.read())
+                        if re.match(r'^https?://', line)
-            down.close()
+                        else compat_urlparse.urljoin(man_url, line))
-            frags_filenames.append(frag_sanitized)
+                    frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+                    success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                    if not success:
+                        return False
+                    down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+                    frag_content = down.read()
+                    down.close()
+                    if decrypt_info['METHOD'] == 'AES-128':
+                        iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
+                        frag_content = AES.new(
+                            decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
+                    ctx['dest_stream'].write(frag_content)
+                    frags_filenames.append(frag_sanitized)
+                    # We only download the first fragment during the test
+                    if self.params.get('test', False):
+                        break
+                    i += 1
+                    media_sequence += 1
+                elif line.startswith('#EXT-X-KEY'):
+                    decrypt_info = parse_m3u8_attributes(line[11:])
+                    if decrypt_info['METHOD'] == 'AES-128':
+                        if 'IV' in decrypt_info:
+                            decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:])
+                        if not re.match(r'^https?://', decrypt_info['URI']):
+                            decrypt_info['URI'] = compat_urlparse.urljoin(
+                                man_url, decrypt_info['URI'])
+                        decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
+                elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
+                    media_sequence = int(line[22:])
 
         self._finish_frag_download(ctx)
 

youtube_dl/extractor/adobetv.py

@@ -156,7 +156,10 @@ class AdobeTVVideoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(url + '?format=json', video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        video_data = self._parse_json(self._search_regex(
+            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
 
         formats = [{
             'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),

youtube_dl/extractor/afreecatv.py

@@ -0,0 +1,133 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    xpath_element,
+    xpath_text,
+)
+
+
+class AfreecaTVIE(InfoExtractor):
+    IE_DESC = 'afreecatv.com'
+    _VALID_URL = r'''(?x)^
+        https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
+        (?:
+            /app/(?:index|read_ucc_bbs)\.cgi|
+            /player/[Pp]layer\.(?:swf|html))
+        \?.*?\bnTitleNo=(?P<id>\d+)'''
+    _TESTS = [{
+        'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
+        'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
+        'info_dict': {
+            'id': '36164052',
+            'ext': 'mp4',
+            'title': '데일리 에이프릴 요정들의 시상식!',
+            'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+            'uploader': 'dailyapril',
+            'uploader_id': 'dailyapril',
+            'upload_date': '20160503',
+        }
+    }, {
+        'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
+        'info_dict': {
+            'id': '36153164',
+            'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
+            'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+            'uploader': 'dailyapril',
+            'uploader_id': 'dailyapril',
+        },
+        'playlist_count': 2,
+        'playlist': [{
+            'md5': 'd8b7c174568da61d774ef0203159bf97',
+            'info_dict': {
+                'id': '36153164_1',
+                'ext': 'mp4',
+                'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
+                'upload_date': '20160502',
+            },
+        }, {
+            'md5': '58f2ce7f6044e34439ab2d50612ab02b',
+            'info_dict': {
+                'id': '36153164_2',
+                'ext': 'mp4',
+                'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
+                'upload_date': '20160502',
+            },
+        }],
+    }, {
+        'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def parse_video_key(key):
+        video_key = {}
+        m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
+        if m:
+            video_key['upload_date'] = m.group('upload_date')
+            video_key['part'] = m.group('part')
+        return video_key
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        parsed_url = compat_urllib_parse_urlparse(url)
+        info_url = compat_urlparse.urlunparse(parsed_url._replace(
+            netloc='afbbs.afreecatv.com:8080',
+            path='/api/video/get_video_info.php'))
+        video_xml = self._download_xml(info_url, video_id)
+
+        if xpath_element(video_xml, './track/video/file') is None:
+            raise ExtractorError('Specified AfreecaTV video does not exist',
+                                 expected=True)
+
+        title = xpath_text(video_xml, './track/title', 'title')
+        uploader = xpath_text(video_xml, './track/nickname', 'uploader')
+        uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
+        duration = int_or_none(xpath_text(video_xml, './track/duration',
+                                          'duration'))
+        thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
+
+        entries = []
+        for i, video_file in enumerate(video_xml.findall('./track/video/file')):
+            video_key = self.parse_video_key(video_file.get('key', ''))
+            if not video_key:
+                continue
+            entries.append({
+                'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
+                'title': title,
+                'upload_date': video_key.get('upload_date'),
+                'duration': int_or_none(video_file.get('duration')),
+                'url': video_file.text,
+            })
+
+        info = {
+            'id': video_id,
+            'title': title,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }
+
+        if len(entries) > 1:
+            info['_type'] = 'multi_video'
+            info['entries'] = entries
+        elif len(entries) == 1:
+            info['url'] = entries[0]['url']
+            info['upload_date'] = entries[0].get('upload_date')
+        else:
+            raise ExtractorError(
+                'No files found for the specified AfreecaTV video, either'
+                ' the URL is incorrect or the video has been made private.',
+                expected=True)
+
+        return info

youtube_dl/extractor/aftonbladet.py

@@ -24,10 +24,10 @@ class AftonbladetIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         # find internal video meta data
-        meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+        meta_url = 'http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json'
         player_config = self._parse_json(self._html_search_regex(
             r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
-        internal_meta_id = player_config['videoId']
+        internal_meta_id = player_config['aptomaVideoId']
         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')

youtube_dl/extractor/ard.py

@@ -8,7 +8,6 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
-    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
@@ -274,41 +273,3 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
-
-
-class SportschauIE(ARDMediathekIE):
-    IE_NAME = 'Sportschau'
-    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
-    _TESTS = [{
-        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
-        'info_dict': {
-            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
-            'ext': 'mp4',
-            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        base_url = mobj.group('baseurl')
-
-        webpage = self._download_webpage(url, video_id)
-        title = get_element_by_attribute('class', 'headline', webpage)
-        description = self._html_search_meta('description', webpage, 'description')
-
-        info = self._extract_media_info(
-            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
-
-        info.update({
-            'title': title,
-            'description': description,
-        })
-
-        return info

youtube_dl/extractor/arte.py

@@ -180,11 +180,14 @@ class ArteTVBaseIE(InfoExtractor):
 
 class ArteTVPlus7IE(ArteTVBaseIE):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
         'only_matching': True,
+    }, {
+        'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -240,10 +243,10 @@ class ArteTVPlus7IE(ArteTVBaseIE):
             return self._extract_from_json_url(json_url, video_id, lang, title=title)
         # Different kind of embed URL (e.g.
         # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
-        embed_url = self._search_regex(
+        entries = [
-            r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1',
+            self.url_result(url)
-            webpage, 'embed url', group='url')
+            for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
-        return self.url_result(embed_url)
+        return self.playlist_result(entries)
 
 
 # It also uses the arte_vp_url url from the webpage to extract the information
@@ -252,22 +255,17 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
     _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
-        'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
+        'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
         'info_dict': {
-            'id': '72176',
+            'id': '057405-001-A',
             'ext': 'mp4',
-            'title': 'Folge 2 - Corporate Design',
+            'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
-            'upload_date': '20131004',
+            'upload_date': '20150716',
         },
     }, {
         'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
-        'info_dict': {
+        'playlist_count': 11,
-            'id': '160676',
+        'add_ie': ['Youtube'],
-            'ext': 'mp4',
-            'title': 'Monty Python live (mostly)',
-            'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n',
-            'upload_date': '20140805',
-        }
     }, {
         'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
         'only_matching': True,
@@ -349,14 +347,13 @@ class ArteTVCinemaIE(ArteTVPlus7IE):
     _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
 
     _TESTS = [{
-        'url': 'http://cinema.arte.tv/de/node/38291',
+        'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
-        'md5': '6b275511a5107c60bacbeeda368c3aa1',
+        'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
         'info_dict': {
-            'id': '055876-000_PWA12025-D',
+            'id': '062494-000-A',
             'ext': 'mp4',
-            'title': 'Tod auf dem Nil',
+            'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
-            'upload_date': '20160122',
+            'upload_date': '20150807',
-            'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
         },
     }]
 

youtube_dl/extractor/audiomack.py

@@ -6,6 +6,7 @@ import time
 
 from .common import InfoExtractor
 from .soundcloud import SoundcloudIE
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     url_basename,
@@ -136,7 +137,7 @@ class AudiomackAlbumIE(InfoExtractor):
                         result[resultkey] = api_response[apikey]
                 song_id = url_basename(api_response['url']).rpartition('.')[0]
                 result['entries'].append({
-                    'id': api_response.get('id', song_id),
+                    'id': compat_str(api_response.get('id', song_id)),
                     'uploader': api_response.get('artist'),
                     'title': api_response.get('title', song_id),
                     'url': api_response['url'],

youtube_dl/extractor/azubu.py

@@ -46,6 +46,7 @@ class AzubuIE(InfoExtractor):
                 'uploader_id': 272749,
                 'view_count': int,
             },
+            'skip': 'Channel offline',
         },
     ]
 
@@ -56,22 +57,26 @@ class AzubuIE(InfoExtractor):
             'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
 
         title = data['title'].strip()
-        description = data['description']
+        description = data.get('description')
-        thumbnail = data['thumbnail']
+        thumbnail = data.get('thumbnail')
-        view_count = data['view_count']
+        view_count = data.get('view_count')
-        uploader = data['user']['username']
+        user = data.get('user', {})
-        uploader_id = data['user']['id']
+        uploader = user.get('username')
+        uploader_id = user.get('id')
 
         stream_params = json.loads(data['stream_params'])
 
-        timestamp = float_or_none(stream_params['creationDate'], 1000)
+        timestamp = float_or_none(stream_params.get('creationDate'), 1000)
-        duration = float_or_none(stream_params['length'], 1000)
+        duration = float_or_none(stream_params.get('length'), 1000)
 
         renditions = stream_params.get('renditions') or []
         video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
         if video:
             renditions.append(video)
 
+        if not renditions and not user.get('channel', {}).get('is_live', True):
+            raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True)
+
         formats = [{
             'url': fmt['url'],
             'width': fmt['frameWidth'],

youtube_dl/extractor/bbc.py

@@ -31,7 +31,7 @@ class BBCCoUkIE(InfoExtractor):
                             music/clips[/#]|
                             radio/player/
                         )
-                        (?P<id>%s)
+                        (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
                     ''' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
@@ -192,6 +192,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'Now it\'s really geo-restricted',
         }, {
             # compact player (https://github.com/rg3/youtube-dl/issues/8147)
             'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
@@ -698,7 +699,9 @@ class BBCIE(BBCCoUkIE):
 
     @classmethod
     def suitable(cls, url):
-        return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
+        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
+        return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
+                else super(BBCIE, cls).suitable(url))
 
     def _extract_from_media_meta(self, media_meta, video_id):
         # Direct links to media in media metadata (e.g.
@@ -975,3 +978,72 @@ class BBCCoUkArticleIE(InfoExtractor):
             r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
 
         return self.playlist_result(entries, playlist_id, title, description)
+
+
+class BBCCoUkPlaylistBaseIE(InfoExtractor):
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+            for video_id in re.findall(
+                self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
+
+        title, description = self._extract_title_and_description(webpage)
+
+        return self.playlist_result(entries, playlist_id, title, description)
+
+
+class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:playlist'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+    _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
+    _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
+        'info_dict': {
+            'id': 'b05rcz9v',
+            'title': 'The Disappearance',
+            'description': 'French thriller serial about a missing teenager.',
+        },
+        'playlist_mincount': 6,
+    }
+
+    def _extract_title_and_description(self, webpage):
+        title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
+        description = self._search_regex(
+            r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
+            webpage, 'description', fatal=False, group='value')
+        return title, description
+
+
+class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:playlist'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
+    _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
+    _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
+    _TESTS = [{
+        'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
+        'info_dict': {
+            'id': 'b05rcz9v',
+            'title': 'The Disappearance - Clips - BBC Four',
+            'description': 'French thriller serial about a missing teenager.',
+        },
+        'playlist_mincount': 7,
+    }, {
+        'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
+        'only_matching': True,
+    }]
+
+    def _extract_title_and_description(self, webpage):
+        title = self._og_search_title(webpage, fatal=False)
+        description = self._og_search_description(webpage)
+        return title, description

youtube_dl/extractor/bet.py

@@ -1,31 +1,27 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .mtv import MTVServicesInfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..utils import unified_strdate
-from ..utils import (
+from ..compat import compat_urllib_parse_urlencode
-    xpath_text,
-    xpath_with_ns,
-    int_or_none,
-    parse_iso8601,
-)
 
 
-class BetIE(InfoExtractor):
+class BetIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
     _TESTS = [
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': 'news/national/2014/a-conversation-with-president-obama',
+                'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
                 'title': 'A Conversation With President Obama',
-                'description': 'md5:699d0652a350cf3e491cd15cc745b5da',
+                'description': 'President Obama urges persistence in confronting racism and bias.',
                 'duration': 1534,
-                'timestamp': 1418075340,
                 'upload_date': '20141208',
-                'uploader': 'admin',
                 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -35,16 +31,17 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': 'news/national/2014/justice-for-ferguson-a-community-reacts',
+                'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
                 'description': 'A BET News special.',
                 'duration': 1696,
-                'timestamp': 1416942360,
                 'upload_date': '20141125',
-                'uploader': 'admin',
                 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -53,57 +50,32 @@ class BetIE(InfoExtractor):
         }
     ]
 
+    _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
+
+    def _get_feed_query(self, uri):
+        return compat_urllib_parse_urlencode({
+            'uuid': uri,
+        })
+
+    def _extract_mgid(self, webpage):
+        return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
+
         webpage = self._download_webpage(url, display_id)
+        mgid = self._extract_mgid(webpage)
+        videos_info = self._get_videos_info(mgid)
 
-        media_url = compat_urllib_parse_unquote(self._search_regex(
+        info_dict = videos_info['entries'][0]
-            [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
-            webpage, 'media URL'))
 
-        video_id = self._search_regex(
+        upload_date = unified_strdate(self._html_search_meta('date', webpage))
-            r'/video/(.*)/_jcr_content/', media_url, 'video id')
+        description = self._html_search_meta('description', webpage)
 
-        mrss = self._download_xml(media_url, display_id)
+        info_dict.update({
-
-        item = mrss.find('./channel/item')
-
-        NS_MAP = {
-            'dc': 'http://purl.org/dc/elements/1.1/',
-            'media': 'http://search.yahoo.com/mrss/',
-            'ka': 'http://kickapps.com/karss',
-        }
-
-        title = xpath_text(item, './title', 'title')
-        description = xpath_text(
-            item, './description', 'description', fatal=False)
-
-        timestamp = parse_iso8601(xpath_text(
-            item, xpath_with_ns('./dc:date', NS_MAP),
-            'upload date', fatal=False))
-        uploader = xpath_text(
-            item, xpath_with_ns('./dc:creator', NS_MAP),
-            'uploader', fatal=False)
-
-        media_content = item.find(
-            xpath_with_ns('./media:content', NS_MAP))
-        duration = int_or_none(media_content.get('duration'))
-        smil_url = media_content.get('url')
-
-        thumbnail = media_content.find(
-            xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
-
-        formats = self._extract_smil_formats(smil_url, display_id)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
             'display_id': display_id,
-            'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'upload_date': upload_date,
-            'timestamp': timestamp,
+        })
-            'uploader': uploader,
+
-            'duration': duration,
+        return info_dict
-            'formats': formats,
-        }

youtube_dl/extractor/bilibili.py

@@ -102,6 +102,22 @@ class BiliBiliIE(InfoExtractor):
                 'uploader_id': '151066',
             },
         }],
+    }, {
+        # Missing upload time
+        'url': 'http://www.bilibili.com/video/av1867637/',
+        'info_dict': {
+            'id': '2880301',
+            'ext': 'flv',
+            'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
+            'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
+            'uploader': '黑夜为猫',
+            'uploader_id': '610729',
+        },
+        'params': {
+            # Just to test metadata extraction
+            'skip_download': True,
+        },
+        'expected_warnings': ['upload time'],
     }]
 
     # BiliBili blocks keys from time to time. The current key is extracted from
@@ -172,6 +188,7 @@ class BiliBiliIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
         datetime_str = self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
+        timestamp = None
         if datetime_str:
             timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
 

youtube_dl/extractor/br.py

@@ -29,7 +29,8 @@ class BRIE(InfoExtractor):
                 'duration': 180,
                 'uploader': 'Reinhard Weber',
                 'upload_date': '20150422',
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
@@ -40,7 +41,8 @@ class BRIE(InfoExtractor):
                 'title': 'Manfred Schreiber ist tot',
                 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
                 'duration': 26,
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
@@ -51,7 +53,8 @@ class BRIE(InfoExtractor):
                 'title': 'Kurzweilig und sehr bewegend',
                 'description': 'md5:0351996e3283d64adeb38ede91fac54e',
                 'duration': 296,
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',

youtube_dl/extractor/canalplus.py

@@ -4,11 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     ExtractorError,
     HEADRequest,
     unified_strdate,
-    url_basename,
     qualities,
     int_or_none,
 )
@@ -16,24 +16,38 @@ from ..utils import (
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
-    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                (?:
+                                    (?:(?:www|m)\.)?canalplus\.fr|
+                                    (?:www\.)?piwiplus\.fr|
+                                    (?:www\.)?d8\.tv|
+                                    (?:www\.)?d17\.tv|
+                                    (?:www\.)?itele\.fr
+                                )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
+                                player\.canalplus\.fr/#/(?P<id>\d+)
+                            )
+
+                    '''
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
     _SITE_ID_MAP = {
-        'canalplus.fr': 'cplus',
+        'canalplus': 'cplus',
-        'piwiplus.fr': 'teletoon',
+        'piwiplus': 'teletoon',
-        'd8.tv': 'd8',
+        'd8': 'd8',
-        'itele.fr': 'itele',
+        'd17': 'd17',
+        'itele': 'itele',
     }
 
     _TESTS = [{
-        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
-        'md5': '12164a6f14ff6df8bd628e8ba9b10b78',
+        'md5': '41f438a4904f7664b91b4ed0dec969dc',
         'info_dict': {
-            'id': '1263092',
+            'id': '1192814',
             'ext': 'mp4',
-            'title': 'Le Zapping - 13/05/15',
+            'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
-            'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+            'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
-            'upload_date': '20150513',
+            'upload_date': '20150105',
         },
     }, {
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
@@ -46,35 +60,45 @@ class CanalplusIE(InfoExtractor):
         },
         'skip': 'Only works from France',
     }, {
-        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
         'info_dict': {
-            'id': '966289',
+            'id': '1390231',
-            'ext': 'flv',
-            'title': 'Campagne intime - Documentaire exceptionnel',
-            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
-            'upload_date': '20131108',
-        },
-        'skip': 'videos get deleted after a while',
-    }, {
-        'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
-        'info_dict': {
-            'id': '1213714',
             'ext': 'mp4',
-            'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
+            'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
-            'description': 'md5:8216206ec53426ea6321321f3b3c16db',
+            'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
-            'upload_date': '20150211',
+            'upload_date': '20160512',
         },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
+        'info_dict': {
+            'id': '1398334',
+            'ext': 'mp4',
+            'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
+            'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
+            'upload_date': '20160607',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://m.canalplus.fr/?vid=1398231',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.groupdict().get('id')
+        video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
 
-        site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
+        site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 
         # Beware, some subclasses do not define an id group
-        display_id = url_basename(mobj.group('path'))
+        display_id = mobj.group('display_id') or video_id
 
         if video_id is None:
             webpage = self._download_webpage(url, display_id)

youtube_dl/extractor/carambatv.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    try_get,
+)
+
+
+class CarambaTVIE(InfoExtractor):
+    _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://video1.carambatv.ru/v/191910501',
+        'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
+        'info_dict': {
+            'id': '191910501',
+            'ext': 'mp4',
+            'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 2678.31,
+        },
+    }, {
+        'url': 'carambatv:191910501',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
+            video_id)
+
+        title = video['title']
+
+        base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
+
+        formats = [{
+            'url': base_url + f['fn'],
+            'height': int_or_none(f.get('height')),
+            'format_id': '%sp' % f['height'] if f.get('height') else None,
+        } for f in video['qualities'] if f.get('fn')]
+        self._sort_formats(formats)
+
+        thumbnail = video.get('splash')
+        duration = float_or_none(try_get(
+            video, lambda x: x['annotations'][0]['end_time'], compat_str))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class CarambaTVPageIE(InfoExtractor):
+    _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
+        'md5': '',
+        'info_dict': {
+            'id': '191910501',
+            'ext': 'mp4',
+            'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 2678.31,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._og_search_property('video:iframe', webpage, default=None)
+
+        if not video_url:
+            video_id = self._search_regex(
+                r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
+                webpage, 'video id')
+            video_url = 'carambatv:%s' % video_id
+
+        return self.url_result(video_url, CarambaTVIE.ie_key())

youtube_dl/extractor/cbs.py

@@ -2,16 +2,14 @@ from __future__ import unicode_literals
 
 import re
 
-from .theplatform import ThePlatformIE
+from .theplatform import ThePlatformFeedIE
 from ..utils import (
-    xpath_text,
-    xpath_element,
     int_or_none,
     find_xpath_attr,
 )
 
 
-class CBSBaseIE(ThePlatformIE):
+class CBSBaseIE(ThePlatformFeedIE):
     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
         closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
         return {
@@ -21,9 +19,22 @@ class CBSBaseIE(ThePlatformIE):
             }]
         } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
 
+    def _extract_video_info(self, filter_query, video_id):
+        return self._extract_feed_info(
+            'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: {
+                'series': entry.get('cbs$SeriesTitle'),
+                'season_number': int_or_none(entry.get('cbs$SeasonNumber')),
+                'episode': entry.get('cbs$EpisodeTitle'),
+                'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')),
+            }, {
+                'StreamPack': {
+                    'manifest': 'm3u',
+                }
+            })
+
 
 class CBSIE(CBSBaseIE):
-    _VALID_URL = r'(?:cbs:(?P<content_id>\w+)|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<display_id>[^/]+))'
+    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
@@ -38,25 +49,7 @@ class CBSIE(CBSBaseIE):
             'upload_date': '20131127',
             'uploader': 'CBSI-NEW',
         },
-        'params': {
+        'expected_warnings': ['Failed to download m3u8 information'],
-            # rtmp download
-            'skip_download': True,
-        },
-        '_skip': 'Blocked outside the US',
-    }, {
-        'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
-        'info_dict': {
-            'id': 'WWF_5KqY3PK1',
-            'display_id': 'st-vincent',
-            'ext': 'flv',
-            'title': 'Live on Letterman - St. Vincent',
-            'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
-            'duration': 3221,
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
         '_skip': 'Blocked outside the US',
     }, {
         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
@@ -68,44 +61,5 @@ class CBSIE(CBSBaseIE):
     TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
 
     def _real_extract(self, url):
-        content_id, display_id = re.match(self._VALID_URL, url).groups()
+        content_id = self._match_id(url)
-        if not content_id:
+        return self._extract_video_info('byGuid=%s' % content_id, content_id)
-            webpage = self._download_webpage(url, display_id)
-            content_id = self._search_regex(
-                [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
-                webpage, 'content id')
-        items_data = self._download_xml(
-            'http://can.cbs.com/thunder/player/videoPlayerService.php',
-            content_id, query={'partner': 'cbs', 'contentId': content_id})
-        video_data = xpath_element(items_data, './/item')
-        title = xpath_text(video_data, 'videoTitle', 'title', True)
-
-        subtitles = {}
-        formats = []
-        for item in items_data.findall('.//item'):
-            pid = xpath_text(item, 'pid')
-            if not pid:
-                continue
-            tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
-            if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
-                tp_release_url += '&manifest=m3u'
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
-        info.update({
-            'id': content_id,
-            'display_id': display_id,
-            'title': title,
-            'series': xpath_text(video_data, 'seriesTitle'),
-            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
-            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
-            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
-            'thumbnail': xpath_text(video_data, 'previewImageURL'),
-            'formats': formats,
-            'subtitles': subtitles,
-        })
-        return info

youtube_dl/extractor/cbsnews.py

@@ -30,9 +30,12 @@ class CBSNewsIE(CBSBaseIE):
         {
             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
             'info_dict': {
-                'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
+                'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
                 'ext': 'mp4',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
+                'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
+                'upload_date': '19700101',
+                'uploader': 'CBSI-NEW',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
                 'subtitles': {
@@ -58,30 +61,8 @@ class CBSNewsIE(CBSBaseIE):
             webpage, 'video JSON info'), video_id)
 
         item = video_info['item'] if 'item' in video_info else video_info
-        title = item.get('articleTitle') or item.get('hed')
+        guid = item['mpxRefId']
-        duration = item.get('duration')
+        return self._extract_video_info('byGuid=%s' % guid, guid)
-        thumbnail = item.get('mediaImage') or item.get('thumbnail')
-
-        subtitles = {}
-        formats = []
-        for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
-            pid = item.get('media' + format_id)
-            if not pid:
-                continue
-            release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
 
 
 class CBSNewsLiveVideoIE(InfoExtractor):

youtube_dl/extractor/cbssports.py

@@ -1,30 +1,28 @@
 from __future__ import unicode_literals
 
-import re
+from .cbs import CBSBaseIE
-
-from .common import InfoExtractor
 
 
-class CBSSportsIE(InfoExtractor):
+class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
-        'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',
+        'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
         'info_dict': {
-            'id': '_d5_GbO8p1sT',
+            'id': '708337219968',
-            'ext': 'flv',
+            'ext': 'mp4',
-            'title': 'US Open flashbacks: 1990s',
+            'title': 'Ben Simmons the next LeBron? Not so fast',
-            'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.',
+            'description': 'md5:854294f627921baba1f4b9a990d87197',
+            'timestamp': 1466293740,
+            'upload_date': '20160618',
+            'uploader': 'CBSI-NEW',
         },
-    }
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        section = mobj.group('section')
+        return self._extract_video_info('byId=%s' % video_id, video_id)
-        video_id = mobj.group('id')
-        all_videos = self._download_json(
-            'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section,
-            video_id)
-        # The json file contains the info of all the videos in the section
-        video_info = next(v for v in all_videos if v['pcid'] == video_id)
-        return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform')

youtube_dl/extractor/cda.py

@@ -58,7 +58,8 @@ class CDAIE(InfoExtractor):
         def extract_format(page, version):
             unpacked = decode_packed_codes(page)
             format_url = self._search_regex(
-                r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False)
+                r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked,
+                '%s url' % version, fatal=False, group='url')
             if not format_url:
                 return
             f = {
@@ -75,7 +76,8 @@ class CDAIE(InfoExtractor):
             info_dict['formats'].append(f)
             if not info_dict['duration']:
                 info_dict['duration'] = parse_duration(self._search_regex(
-                    r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False))
+                    r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1",
+                    unpacked, 'duration', fatal=False, group='duration'))
 
         extract_format(webpage, 'default')
 

youtube_dl/extractor/channel9.py

@@ -20,54 +20,64 @@ class Channel9IE(InfoExtractor):
     '''
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
-    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
 
-    _TESTS = [
+    _TESTS = [{
-        {
+        'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+        'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
-            'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
+        'info_dict': {
-            'info_dict': {
+            'id': 'Events/TechEd/Australia/2013/KOS002',
-                'id': 'Events/TechEd/Australia/2013/KOS002',
+            'ext': 'mp4',
-                'ext': 'mp4',
+            'title': 'Developer Kick-Off Session: Stuff We Love',
-                'title': 'Developer Kick-Off Session: Stuff We Love',
+            'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
-                'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
+            'duration': 4576,
-                'duration': 4576,
+            'thumbnail': 're:http://.*\.jpg',
-                'thumbnail': 're:http://.*\.jpg',
+            'session_code': 'KOS002',
-                'session_code': 'KOS002',
+            'session_day': 'Day 1',
-                'session_day': 'Day 1',
+            'session_room': 'Arena 1A',
-                'session_room': 'Arena 1A',
+            'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug',
-                'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'],
+                                 'Mads Kristensen'],
-            },
         },
-        {
+    }, {
-            'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+        'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
+        'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
-            'info_dict': {
+        'info_dict': {
-                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+            'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
-                'ext': 'mp4',
+            'ext': 'mp4',
-                'title': 'Self-service BI with Power BI - nuclear testing',
+            'title': 'Self-service BI with Power BI - nuclear testing',
-                'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+            'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
-                'duration': 1540,
+            'duration': 1540,
-                'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': 're:http://.*\.jpg',
-                'authors': ['Mike Wilmot'],
+            'authors': ['Mike Wilmot'],
-            },
         },
-        {
+    }, {
-            # low quality mp4 is best
+        # low quality mp4 is best
-            'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+        'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
-            'info_dict': {
+        'info_dict': {
-                'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+            'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
-                'ext': 'mp4',
+            'ext': 'mp4',
-                'title': 'Ranges for the Standard Library',
+            'title': 'Ranges for the Standard Library',
-                'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
+            'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
-                'duration': 5646,
+            'duration': 5646,
-                'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': 're:http://.*\.jpg',
-            },
+        },
-            'params': {
+        'params': {
-                'skip_download': True,
+            'skip_download': True,
-            },
+        },
-        }
+    }, {
-    ]
+        'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
+        'info_dict': {
+            'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
+            'title': 'Channel 9',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
+        'only_matching': True,
+    }, {
+        'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman',
+        'only_matching': True,
+    }]
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
@@ -254,22 +264,30 @@ class Channel9IE(InfoExtractor):
 
         return self.playlist_result(contents)
 
-    def _extract_list(self, content_path):
+    def _extract_list(self, video_id, rss_url=None):
-        rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
+        if not rss_url:
+            rss_url = self._RSS_URL % video_id
+        rss = self._download_xml(rss_url, video_id, 'Downloading RSS')
         entries = [self.url_result(session_url.text, 'Channel9')
                    for session_url in rss.findall('./channel/item/link')]
         title_text = rss.find('./channel/title').text
-        return self.playlist_result(entries, content_path, title_text)
+        return self.playlist_result(entries, video_id, title_text)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         content_path = mobj.group('contentpath')
+        rss = mobj.group('rss')
 
-        webpage = self._download_webpage(url, content_path, 'Downloading web page')
+        if rss:
+            return self._extract_list(content_path, url)
 
-        page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage)
+        webpage = self._download_webpage(
-        if page_type_m is not None:
+            url, content_path, 'Downloading web page')
-            page_type = page_type_m.group('pagetype')
+
+        page_type = self._search_regex(
+            r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2',
+            webpage, 'page type', default=None, group='pagetype')
+        if page_type:
             if page_type == 'Entry':      # Any 'item'-like page, may contain downloadable content
                 return self._extract_entry_item(webpage, content_path)
             elif page_type == 'Session':  # Event session page, may contain downloadable content
@@ -278,6 +296,5 @@ class Channel9IE(InfoExtractor):
                 return self._extract_list(content_path)
             else:
                 raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
-
         else:  # Assuming list
             return self._extract_list(content_path)

youtube_dl/extractor/closertotruth.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class CloserToTruthIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
+        'info_dict': {
+            'id': '0_zof1ktre',
+            'display_id': 'solutions-the-mind-body-problem',
+            'ext': 'mov',
+            'title': 'Solutions to the Mind-Body Problem?',
+            'upload_date': '20140221',
+            'timestamp': 1392956007,
+            'uploader_id': 'CTTXML'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://closertotruth.com/episodes/how-do-brains-work',
+        'info_dict': {
+            'id': '0_iuxai6g6',
+            'display_id': 'how-do-brains-work',
+            'ext': 'mov',
+            'title': 'How do Brains Work?',
+            'upload_date': '20140221',
+            'timestamp': 1392956024,
+            'uploader_id': 'CTTXML'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://closertotruth.com/interviews/1725',
+        'info_dict': {
+            'id': '1725',
+            'title': 'AyaFr-002',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        partner_id = self._search_regex(
+            r'<script[^>]+src=["\'].*?\b(?:partner_id|p)/(\d+)',
+            webpage, 'kaltura partner_id')
+
+        title = self._search_regex(
+            r'<title>(.+?)\s*\|\s*.+?</title>', webpage, 'video title')
+
+        select = self._search_regex(
+            r'(?s)<select[^>]+id="select-version"[^>]*>(.+?)</select>',
+            webpage, 'select version', default=None)
+        if select:
+            entry_ids = set()
+            entries = []
+            for mobj in re.finditer(
+                    r'<option[^>]+value=(["\'])(?P<id>[0-9a-z_]+)(?:#.+?)?\1[^>]*>(?P<title>[^<]+)',
+                    webpage):
+                entry_id = mobj.group('id')
+                if entry_id in entry_ids:
+                    continue
+                entry_ids.add(entry_id)
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': 'kaltura:%s:%s' % (partner_id, entry_id),
+                    'ie_key': 'Kaltura',
+                    'title': mobj.group('title'),
+                })
+            if entries:
+                return self.playlist_result(entries, display_id, title)
+
+        entry_id = self._search_regex(
+            r'<a[^>]+id=(["\'])embed-kaltura\1[^>]+data-kaltura=(["\'])(?P<id>[0-9a-z_]+)\2',
+            webpage, 'kaltura entry_id', group='id')
+
+        return {
+            '_type': 'url_transparent',
+            'display_id': display_id,
+            'url': 'kaltura:%s:%s' % (partner_id, entry_id),
+            'ie_key': 'Kaltura',
+            'title': title
+        }

youtube_dl/extractor/common.py

@@ -45,6 +45,7 @@ from ..utils import (
     unescapeHTML,
     unified_strdate,
     url_basename,
+    xpath_element,
     xpath_text,
     xpath_with_ns,
     determine_protocol,
@@ -52,6 +53,7 @@ from ..utils import (
     mimetype2ext,
     update_Request,
     update_url_query,
+    parse_m3u8_attributes,
 )
 
 
@@ -1030,7 +1032,7 @@ class InfoExtractor(object):
         if base_url:
             base_url = base_url.strip()
 
-        bootstrap_info = xpath_text(
+        bootstrap_info = xpath_element(
             manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
             'bootstrap info', default=None)
 
@@ -1085,7 +1087,7 @@ class InfoExtractor(object):
             formats.append({
                 'format_id': format_id,
                 'url': manifest_url,
-                'ext': 'flv' if bootstrap_info else None,
+                'ext': 'flv' if bootstrap_info is not None else None,
                 'tbr': tbr,
                 'width': width,
                 'height': height,
@@ -1149,23 +1151,11 @@ class InfoExtractor(object):
             }]
         last_info = None
         last_media = None
-        kv_rex = re.compile(
-            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
-                last_info = {}
+                last_info = parse_m3u8_attributes(line)
-                for m in kv_rex.finditer(line):
-                    v = m.group('val')
-                    if v.startswith('"'):
-                        v = v[1:-1]
-                    last_info[m.group('key')] = v
             elif line.startswith('#EXT-X-MEDIA:'):
-                last_media = {}
+                last_media = parse_m3u8_attributes(line)
-                for m in kv_rex.finditer(line):
-                    v = m.group('val')
-                    if v.startswith('"'):
-                        v = v[1:-1]
-                    last_media[m.group('key')] = v
             elif line.startswith('#') or not line.strip():
                 continue
             else:

youtube_dl/extractor/dw.py

@@ -35,6 +35,7 @@ class DWIE(InfoExtractor):
             'upload_date': '20160311',
         }
     }, {
+        # DW documentaries, only last for one or two weeks
         'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
         'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
         'info_dict': {
@@ -44,6 +45,7 @@ class DWIE(InfoExtractor):
             'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
             'upload_date': '20160521',
         },
+        'skip': 'Video removed',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -21,6 +21,7 @@ from .adobetv import (
 )
 from .adultswim import AdultSwimIE
 from .aenetworks import AENetworksIE
+from .afreecatv import AfreecaTVIE
 from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
@@ -43,7 +44,6 @@ from .archiveorg import ArchiveOrgIE
 from .ard import (
     ARDIE,
     ARDMediathekIE,
-    SportschauIE,
 )
 from .arte import (
     ArteTvIE,
@@ -70,6 +70,8 @@ from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbc import (
     BBCCoUkIE,
     BBCCoUkArticleIE,
+    BBCCoUkIPlayerPlaylistIE,
+    BBCCoUkPlaylistIE,
     BBCIE,
 )
 from .beeg import BeegIE
@@ -107,6 +109,10 @@ from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .canvas import CanvasIE
+from .carambatv import (
+    CarambaTVIE,
+    CarambaTVPageIE,
+)
 from .cbc import (
     CBCIE,
     CBCPlayerIE,
@@ -134,6 +140,7 @@ from .cliprs import ClipRsIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .closertotruth import CloserToTruthIE
 from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .clyp import ClypIE
@@ -291,6 +298,7 @@ from .globo import (
     GloboArticleIE,
 )
 from .godtube import GodTubeIE
+from .godtv import GodTVIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googledrive import GoogleDriveIE
@@ -510,7 +518,10 @@ from .nhl import (
     NHLVideocenterCategoryIE,
     NHLIE,
 )
-from .nick import NickIE
+from .nick import (
+    NickIE,
+    NickDeIE,
+)
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
@@ -620,7 +631,10 @@ from .qqmusic import (
     QQMusicToplistIE,
     QQMusicPlaylistIE,
 )
-from .r7 import R7IE
+from .r7 import (
+    R7IE,
+    R7ArticleIE,
+)
 from .radiocanada import (
     RadioCanadaIE,
     RadioCanadaAudioVideoIE,
@@ -647,6 +661,7 @@ from .revision3 import (
 from .rice import RICEIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
+from .rockstargames import RockstarGamesIE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
@@ -735,6 +750,7 @@ from .sportbox import (
     SportBoxEmbedIE,
 )
 from .sportdeutschland import SportDeutschlandIE
+from .sportschau import SportschauIE
 from .srgssr import (
     SRGSSRIE,
     SRGSSRPlayIE,
@@ -775,6 +791,7 @@ from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
+from .telewebion import TelewebionIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .theintercept import TheInterceptIE
@@ -859,6 +876,7 @@ from .twitch import (
     TwitchProfileIE,
     TwitchPastBroadcastsIE,
     TwitchStreamIE,
+    TwitchClipsIE,
 )
 from .twitter import (
     TwitterCardIE,
@@ -910,6 +928,7 @@ from .videomore import (
 )
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
+from .vidio import VidioIE
 from .vidme import (
     VidmeIE,
     VidmeUserIE,
@@ -955,7 +974,6 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
-from .vulture import VultureIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,
@@ -966,18 +984,19 @@ from .watchindianporn import WatchIndianPornIE
 from .wdr import (
     WDRIE,
     WDRMobileIE,
-    WDRMausIE,
 )
 from .webofstories import (
     WebOfStoriesIE,
     WebOfStoriesPlaylistIE,
 )
-from .weibo import WeiboIE
 from .weiqitv import WeiqiTVIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
-from .wrzuta import WrzutaIE
+from .wrzuta import (
+    WrzutaIE,
+    WrzutaPlaylistIE,
+)
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
@@ -1013,7 +1032,10 @@ from .yesjapan import YesJapanIE
 from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
-from .youku import YoukuIE
+from .youku import (
+    YoukuIE,
+    YoukuShowIE,
+)
 from .youporn import YouPornIE
 from .yourupload import YourUploadIE
 from .youtube import (

youtube_dl/extractor/foxsports.py

@@ -1,7 +1,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import smuggle_url
+from ..utils import (
+    smuggle_url,
+    update_url_query,
+)
 
 
 class FoxSportsIE(InfoExtractor):
@@ -9,11 +12,15 @@ class FoxSportsIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.foxsports.com/video?vid=432609859715',
+        'md5': 'b49050e955bebe32c301972e4012ac17',
         'info_dict': {
-            'id': 'gA0bHB3Ladz3',
+            'id': 'i0qKWsk3qJaM',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
             'description': 'Courtney Lee talks about Memphis being focused.',
+            'upload_date': '20150423',
+            'timestamp': 1429761109,
+            'uploader': 'NEWA-FNG-FOXSPORTS',
         },
         'add_ie': ['ThePlatform'],
     }
@@ -28,5 +35,8 @@ class FoxSportsIE(InfoExtractor):
                 r"data-player-config='([^']+)'", webpage, 'data player config'),
             video_id)
 
-        return self.url_result(smuggle_url(
+        return self.url_result(smuggle_url(update_url_query(
-            config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True}))
+            config['releaseURL'], {
+                'mbr': 'true',
+                'switch': 'http',
+            }), {'force_smil_url': True}))

youtube_dl/extractor/generic.py

@@ -63,6 +63,7 @@ from .instagram import InstagramIE
 from .liveleak import LiveLeakIE
 from .threeqsdn import ThreeQSDNIE
 from .theplatform import ThePlatformIE
+from .vessel import VesselIE
 
 
 class GenericIE(InfoExtractor):
@@ -626,13 +627,13 @@ class GenericIE(InfoExtractor):
         },
         # MTVSercices embed
         {
-            'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
+            'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
-            'md5': '35727f82f58c76d996fc188f9755b0d5',
+            'md5': 'ca1aef97695ef2c1d6973256a57e5252',
             'info_dict': {
-                'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
+                'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
                 'ext': 'mp4',
-                'title': 'Review',
+                'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
-                'description': 'Mario\'s life in the fast lane has never looked so good.',
+                'description': 'Two valets share their love for movie star Liam Neesons.',
             },
         },
         # YouTube embed via <data-embed-url="">
@@ -1031,6 +1032,17 @@ class GenericIE(InfoExtractor):
                 'timestamp': 1389118457,
             },
         },
+        # NBC News embed
+        {
+            'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
+            'md5': '1aa589c675898ae6d37a17913cf68d66',
+            'info_dict': {
+                'id': '701714499682',
+                'ext': 'mp4',
+                'title': 'PREVIEW: On Assignment: David Letterman',
+                'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
+            },
+        },
         # UDN embed
         {
             'url': 'https://video.udn.com/news/300346',
@@ -1061,20 +1073,6 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
-        # Contains a SMIL manifest
-        {
-            'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
-            'info_dict': {
-                'id': 'file',
-                'ext': 'flv',
-                'title': '+ Football: Lottery Champions League Europe',
-                'uploader': 'www.telewebion.com',
-            },
-            'params': {
-                # rtmpe downloads
-                'skip_download': True,
-            }
-        },
         # Brightcove URL in single quotes
         {
             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
@@ -1533,6 +1531,11 @@ class GenericIE(InfoExtractor):
         if tp_urls:
             return _playlist_from_matches(tp_urls, ie='ThePlatform')
 
+        # Look for Vessel embeds
+        vessel_urls = VesselIE._extract_urls(webpage)
+        if vessel_urls:
+            return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
@@ -1840,14 +1843,6 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url)
 
-        # Look for embedded vulture.com player
-        mobj = re.search(
-            r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
-            webpage)
-        if mobj is not None:
-            url = unescapeHTML(mobj.group('url'))
-            return self.url_result(url, ie='Vulture')
-
         # Look for embedded mtvservices player
         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
         if mtvservices_url:
@@ -1960,6 +1955,12 @@ class GenericIE(InfoExtractor):
         if nbc_sports_url:
             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
 
+        # Look for NBC News embeds
+        nbc_news_embed_url = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
+        if nbc_news_embed_url:
+            return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
+
         # Look for Google Drive embeds
         google_drive_url = GoogleDriveIE._extract_url(webpage)
         if google_drive_url:

youtube_dl/extractor/godtv.py

@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+from ..utils import js_to_json
+
+
+class GodTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?god\.tv(?:/[^/]+)*/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://god.tv/jesus-image/video/jesus-conference-2016/randy-needham',
+        'info_dict': {
+            'id': 'lpd3g2MzE6D1g8zFAKz8AGpxWcpu6o_3',
+            'ext': 'mp4',
+            'title': 'Randy Needham',
+            'duration': 3615.08,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://god.tv/playlist/bible-study',
+        'info_dict': {
+            'id': 'bible-study',
+        },
+        'playlist_mincount': 37,
+    }, {
+        'url': 'http://god.tv/node/15097',
+        'only_matching': True,
+    }, {
+        'url': 'http://god.tv/live/africa',
+        'only_matching': True,
+    }, {
+        'url': 'http://god.tv/liveevents',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        settings = self._parse_json(
+            self._search_regex(
+                r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+                webpage, 'settings', default='{}'),
+            display_id, transform_source=js_to_json, fatal=False)
+
+        ooyala_id = None
+
+        if settings:
+            playlist = settings.get('playlist')
+            if playlist and isinstance(playlist, list):
+                entries = [
+                    OoyalaIE._build_url_result(video['content_id'])
+                    for video in playlist if video.get('content_id')]
+                if entries:
+                    return self.playlist_result(entries, display_id)
+            ooyala_id = settings.get('ooyala', {}).get('content_id')
+
+        if not ooyala_id:
+            ooyala_id = self._search_regex(
+                r'["\']content_id["\']\s*:\s*(["\'])(?P<id>[\w-]+)\1',
+                webpage, 'ooyala id', group='id')
+
+        return OoyalaIE._build_url_result(ooyala_id)

youtube_dl/extractor/imdb.py

@@ -12,7 +12,7 @@ from ..utils import (
 class ImdbIE(InfoExtractor):
     IE_NAME = 'imdb'
     IE_DESC = 'Internet Movie Database trailers'
-    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/[^/]+/vi(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-)vi(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
@@ -25,6 +25,12 @@ class ImdbIE(InfoExtractor):
     }, {
         'url': 'http://www.imdb.com/video/_/vi2524815897',
         'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/indavideo.py

@@ -60,7 +60,8 @@ class IndavideoEmbedIE(InfoExtractor):
 
         formats = [{
             'url': video_url,
-            'height': self._search_regex(r'\.(\d{3,4})\.mp4$', video_url, 'height', default=None),
+            'height': int_or_none(self._search_regex(
+                r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None)),
         } for video_url in video_urls]
         self._sort_formats(formats)
 

youtube_dl/extractor/instagram.py

@@ -8,6 +8,7 @@ from ..utils import (
     int_or_none,
     limit_length,
     lowercase_escape,
+    try_get,
 )
 
 
@@ -19,10 +20,16 @@ class InstagramIE(InfoExtractor):
         'info_dict': {
             'id': 'aye83DjauH',
             'ext': 'mp4',
-            'uploader_id': 'naomipq',
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
-        }
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1371748545,
+            'upload_date': '20130620',
+            'uploader_id': 'naomipq',
+            'uploader': 'Naomi Leonor Phan-Quang',
+            'like_count': int,
+            'comment_count': int,
+        },
     }, {
         # missing description
         'url': 'https://www.instagram.com/p/BA-pQFBG8HZ/?taken-by=britneyspears',
@@ -31,6 +38,13 @@ class InstagramIE(InfoExtractor):
             'ext': 'mp4',
             'uploader_id': 'britneyspears',
             'title': 'Video by britneyspears',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1453760977,
+            'upload_date': '20160125',
+            'uploader_id': 'britneyspears',
+            'uploader': 'Britney Spears',
+            'like_count': int,
+            'comment_count': int,
         },
         'params': {
             'skip_download': True,
@@ -67,21 +81,57 @@ class InstagramIE(InfoExtractor):
         url = mobj.group('url')
 
         webpage = self._download_webpage(url, video_id)
-        uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
+
-                                         webpage, 'uploader id', fatal=False)
+        (video_url, description, thumbnail, timestamp, uploader,
-        desc = self._search_regex(
+         uploader_id, like_count, comment_count) = [None] * 8
-            r'"caption":"(.+?)"', webpage, 'description', default=None)
+
-        if desc is not None:
+        shared_data = self._parse_json(
-            desc = lowercase_escape(desc)
+            self._search_regex(
+                r'window\._sharedData\s*=\s*({.+?});',
+                webpage, 'shared data', default='{}'),
+            video_id, fatal=False)
+        if shared_data:
+            media = try_get(
+                shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict)
+            if media:
+                video_url = media.get('video_url')
+                description = media.get('caption')
+                thumbnail = media.get('display_src')
+                timestamp = int_or_none(media.get('date'))
+                uploader = media.get('owner', {}).get('full_name')
+                uploader_id = media.get('owner', {}).get('username')
+                like_count = int_or_none(media.get('likes', {}).get('count'))
+                comment_count = int_or_none(media.get('comments', {}).get('count'))
+
+        if not video_url:
+            video_url = self._og_search_video_url(webpage, secure=False)
+
+        if not uploader_id:
+            uploader_id = self._search_regex(
+                r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"',
+                webpage, 'uploader id', fatal=False)
+
+        if not description:
+            description = self._search_regex(
+                r'"caption"\s*:\s*"(.+?)"', webpage, 'description', default=None)
+            if description is not None:
+                description = lowercase_escape(description)
+
+        if not thumbnail:
+            thumbnail = self._og_search_thumbnail(webpage)
 
         return {
             'id': video_id,
-            'url': self._og_search_video_url(webpage, secure=False),
+            'url': video_url,
             'ext': 'mp4',
             'title': 'Video by %s' % uploader_id,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
             'uploader_id': uploader_id,
-            'description': desc,
+            'uploader': uploader,
+            'like_count': like_count,
+            'comment_count': comment_count,
         }
 
 

youtube_dl/extractor/jwplatform.py

@@ -12,9 +12,35 @@ from ..utils import (
 
 
 class JWPlatformBaseIE(InfoExtractor):
+    @staticmethod
+    def _find_jwplayer_data(webpage):
+        # TODO: Merge this with JWPlayer-related codes in generic.py
+
+        mobj = re.search(
+            'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\((?P<options>[^)]+)\)',
+            webpage)
+        if mobj:
+            return mobj.group('options')
+
+    def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
+        jwplayer_data = self._parse_json(
+            self._find_jwplayer_data(webpage), video_id)
+        return self._parse_jwplayer_data(
+            jwplayer_data, video_id, *args, **kwargs)
+
     def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None):
+        # JWPlayer backward compatibility: flattened playlists
+        # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
+        if 'playlist' not in jwplayer_data:
+            jwplayer_data = {'playlist': [jwplayer_data]}
+
         video_data = jwplayer_data['playlist'][0]
 
+        # JWPlayer backward compatibility: flattened sources
+        # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
+        if 'sources' not in video_data:
+            video_data['sources'] = [video_data]
+
         formats = []
         for source in video_data['sources']:
             source_url = self._proto_relative_url(source['file'])

youtube_dl/extractor/kuwo.py

@@ -148,8 +148,8 @@ class KuwoAlbumIE(InfoExtractor):
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
             'id': '502294',
-            'title': 'M',
+            'title': 'Made\xa0Series\xa0《M》',
-            'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
+            'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
         },
         'playlist_count': 2,
     }
@@ -209,7 +209,7 @@ class KuwoSingerIE(InfoExtractor):
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
             'id': 'bruno+mars',
-            'title': 'Bruno Mars',
+            'title': 'Bruno\xa0Mars',
         },
         'playlist_mincount': 329,
     }, {
@@ -306,7 +306,7 @@ class KuwoMvIE(KuwoBaseIE):
             'id': '6480076',
             'ext': 'mp4',
             'title': 'My HouseMV',
-            'creator': '2PM',
+            'creator': 'PM02:00',
         },
         # In this video, music URLs (anti.s) are blocked outside China and
         # USA, while the MV URL (mvurl) is available globally, so force the MV

youtube_dl/extractor/leeco.py

@@ -28,7 +28,7 @@ from ..utils import (
 
 class LeIE(InfoExtractor):
     IE_DESC = '乐视网'
-    _VALID_URL = r'https?://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|sports\.le\.com/video)/(?P<id>\d+)\.html'
 
     _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
 
@@ -69,6 +69,9 @@ class LeIE(InfoExtractor):
             'hls_prefer_native': True,
         },
         'skip': 'Only available in China',
+    }, {
+        'url': 'http://sports.le.com/video/25737697.html',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -196,7 +199,7 @@ class LeIE(InfoExtractor):
 
 
 class LePlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
+    _VALID_URL = r'https?://[a-z]+\.le\.com/(?!video)[a-z]+/(?P<id>[a-z0-9_]+)'
 
     _TESTS = [{
         'url': 'http://www.le.com/tv/46177.html',

youtube_dl/extractor/libraryofcongress.py

@@ -1,20 +1,24 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    parse_filesize,
 )
 
 
 class LibraryOfCongressIE(InfoExtractor):
     IE_NAME = 'loc'
     IE_DESC = 'Library of Congress'
-    _VALID_URL = r'https?://(?:www\.)?loc\.gov/item/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
+        # embedded via <div class="media-player"
         'url': 'http://loc.gov/item/90716351/',
         'md5': '353917ff7f0255aa6d4b80a034833de8',
         'info_dict': {
@@ -25,7 +29,35 @@ class LibraryOfCongressIE(InfoExtractor):
             'duration': 0,
             'view_count': int,
         },
-    }
+    }, {
+        # webcast embedded via mediaObjectId
+        'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
+        'info_dict': {
+            'id': '5578',
+            'ext': 'mp4',
+            'title': 'Help! Preservation Training Needs Here, There & Everywhere',
+            'duration': 3765,
+            'view_count': int,
+            'subtitles': 'mincount:1',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # with direct download links
+        'url': 'https://www.loc.gov/item/78710669/',
+        'info_dict': {
+            'id': '78710669',
+            'ext': 'mp4',
+            'title': 'La vie et la passion de Jesus-Christ',
+            'duration': 0,
+            'view_count': int,
+            'formats': 'mincount:4',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -34,18 +66,20 @@ class LibraryOfCongressIE(InfoExtractor):
         media_id = self._search_regex(
             (r'id=(["\'])media-player-(?P<id>.+?)\1',
              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
-             r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1'),
+             r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
+             r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'),
             webpage, 'media id', group='id')
 
-        data = self._parse_json(
+        data = self._download_json(
-            self._download_webpage(
+            'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
-                'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
-                video_id),
             video_id)['mediaObject']
 
         derivative = data['derivatives'][0]
         media_url = derivative['derivativeUrl']
 
+        title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
+            webpage)
+
         # Following algorithm was extracted from setAVSource js function
         # found in webpage
         media_url = media_url.replace('rtmp', 'https')
@@ -61,6 +95,7 @@ class LibraryOfCongressIE(InfoExtractor):
                 'format_id': 'hls',
                 'ext': 'mp4',
                 'protocol': 'm3u8_native',
+                'quality': 1,
             }]
         elif 'vod/mp3:' in media_url:
             formats = [{
@@ -68,17 +103,41 @@ class LibraryOfCongressIE(InfoExtractor):
                 'vcodec': 'none',
             }]
 
+        download_urls = set()
+        for m in re.finditer(
+                r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
+            format_id = m.group('id').lower()
+            if format_id == 'gif':
+                continue
+            download_url = m.group('url')
+            if download_url in download_urls:
+                continue
+            download_urls.add(download_url)
+            formats.append({
+                'url': download_url,
+                'format_id': format_id,
+                'filesize_approx': parse_filesize(m.group('size')),
+            })
+
         self._sort_formats(formats)
 
-        title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(webpage)
         duration = float_or_none(data.get('duration'))
         view_count = int_or_none(data.get('viewCount'))
 
+        subtitles = {}
+        cc_url = data.get('ccUrl')
+        if cc_url:
+            subtitles.setdefault('en', []).append({
+                'url': cc_url,
+                'ext': 'ttml',
+            })
+
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/limelight.py

@@ -98,13 +98,19 @@ class LimelightBaseIE(InfoExtractor):
         } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
 
         subtitles = {}
-        for caption in properties.get('captions', {}):
+        for caption in properties.get('captions', []):
             lang = caption.get('language_code')
             subtitles_url = caption.get('url')
             if lang and subtitles_url:
-                subtitles[lang] = [{
+                subtitles.setdefault(lang, []).append({
                     'url': subtitles_url,
-                }]
+                })
+        closed_captions_url = properties.get('closed_captions_url')
+        if closed_captions_url:
+            subtitles.setdefault('en', []).append({
+                'url': closed_captions_url,
+                'ext': 'ttml',
+            })
 
         return {
             'id': video_id,
@@ -123,7 +129,18 @@ class LimelightBaseIE(InfoExtractor):
 
 class LimelightMediaIE(LimelightBaseIE):
     IE_NAME = 'limelight'
-    _VALID_URL = r'(?:limelight:media:|https?://link\.videoplatform\.limelight\.com/media/\??\bmediaId=)(?P<id>[a-z0-9]{32})'
+    _VALID_URL = r'''(?x)
+                        (?:
+                            limelight:media:|
+                            https?://
+                                (?:
+                                    link\.videoplatform\.limelight\.com/media/|
+                                    assets\.delvenetworks\.com/player/loader\.swf
+                                )
+                                \?.*?\bmediaId=
+                        )
+                        (?P<id>[a-z0-9]{32})
+                    '''
     _TESTS = [{
         'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
         'info_dict': {
@@ -158,6 +175,9 @@ class LimelightMediaIE(LimelightBaseIE):
             # rtmp download
             'skip_download': True,
         },
+    }, {
+        'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
+        'only_matching': True,
     }]
     _PLAYLIST_SERVICE_PATH = 'media'
     _API_PATH = 'media'
@@ -176,15 +196,29 @@ class LimelightMediaIE(LimelightBaseIE):
 
 class LimelightChannelIE(LimelightBaseIE):
     IE_NAME = 'limelight:channel'
-    _VALID_URL = r'(?:limelight:channel:|https?://link\.videoplatform\.limelight\.com/media/\??\bchannelId=)(?P<id>[a-z0-9]{32})'
+    _VALID_URL = r'''(?x)
-    _TEST = {
+                        (?:
+                            limelight:channel:|
+                            https?://
+                                (?:
+                                    link\.videoplatform\.limelight\.com/media/|
+                                    assets\.delvenetworks\.com/player/loader\.swf
+                                )
+                                \?.*?\bchannelId=
+                        )
+                        (?P<id>[a-z0-9]{32})
+                    '''
+    _TESTS = [{
         'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082',
         'info_dict': {
             'id': 'ab6a524c379342f9b23642917020c082',
             'title': 'Javascript Sample Code',
         },
         'playlist_mincount': 3,
-    }
+    }, {
+        'url': 'http://assets.delvenetworks.com/player/loader.swf?channelId=ab6a524c379342f9b23642917020c082',
+        'only_matching': True,
+    }]
     _PLAYLIST_SERVICE_PATH = 'channel'
     _API_PATH = 'channels'
 
@@ -207,15 +241,29 @@ class LimelightChannelIE(LimelightBaseIE):
 
 class LimelightChannelListIE(LimelightBaseIE):
     IE_NAME = 'limelight:channel_list'
-    _VALID_URL = r'(?:limelight:channel_list:|https?://link\.videoplatform\.limelight\.com/media/\?.*?\bchannelListId=)(?P<id>[a-z0-9]{32})'
+    _VALID_URL = r'''(?x)
-    _TEST = {
+                        (?:
+                            limelight:channel_list:|
+                            https?://
+                                (?:
+                                    link\.videoplatform\.limelight\.com/media/|
+                                    assets\.delvenetworks\.com/player/loader\.swf
+                                )
+                                \?.*?\bchannelListId=
+                        )
+                        (?P<id>[a-z0-9]{32})
+                    '''
+    _TESTS = [{
         'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b',
         'info_dict': {
             'id': '301b117890c4465c8179ede21fd92e2b',
             'title': 'Website - Hero Player',
         },
         'playlist_mincount': 2,
-    }
+    }, {
+        'url': 'https://assets.delvenetworks.com/player/loader.swf?channelListId=301b117890c4465c8179ede21fd92e2b',
+        'only_matching': True,
+    }]
     _PLAYLIST_SERVICE_PATH = 'channel_list'
 
     def _real_extract(self, url):

youtube_dl/extractor/livestream.py

@@ -203,9 +203,10 @@ class LivestreamIE(InfoExtractor):
             if not videos_info:
                 break
             for v in videos_info:
+                v_id = compat_str(v['id'])
                 entries.append(self.url_result(
-                    'http://livestream.com/accounts/%s/events/%s/videos/%s' % (account_id, event_id, v['id']),
+                    'http://livestream.com/accounts/%s/events/%s/videos/%s' % (account_id, event_id, v_id),
-                    'Livestream', v['id'], v['caption']))
+                    'Livestream', v_id, v.get('caption')))
             last_video = videos_info[-1]['id']
         return self.playlist_result(entries, event_id, event_data['full_name'])
 

youtube_dl/extractor/lynda.py

@@ -1,100 +1,100 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
-    clean_html,
     int_or_none,
-    sanitized_Request,
     urlencode_postdata,
 )
 
 
 class LyndaBaseIE(InfoExtractor):
-    _LOGIN_URL = 'https://www.lynda.com/login/login.aspx'
+    _SIGNIN_URL = 'https://www.lynda.com/signin'
+    _PASSWORD_URL = 'https://www.lynda.com/signin/password'
+    _USER_URL = 'https://www.lynda.com/signin/user'
     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
     _NETRC_MACHINE = 'lynda'
 
     def _real_initialize(self):
         self._login()
 
+    @staticmethod
+    def _check_error(json_string, key_or_keys):
+        keys = [key_or_keys] if isinstance(key_or_keys, compat_str) else key_or_keys
+        for key in keys:
+            error = json_string.get(key)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+
+    def _login_step(self, form_html, fallback_action_url, extra_form_data, note, referrer_url):
+        action_url = self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_html,
+            'post url', default=fallback_action_url, group='url')
+
+        if not action_url.startswith('http'):
+            action_url = compat_urlparse.urljoin(self._SIGNIN_URL, action_url)
+
+        form_data = self._hidden_inputs(form_html)
+        form_data.update(extra_form_data)
+
+        try:
+            response = self._download_json(
+                action_url, None, note,
+                data=urlencode_postdata(form_data),
+                headers={
+                    'Referer': referrer_url,
+                    'X-Requested-With': 'XMLHttpRequest',
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
+                response = self._parse_json(e.cause.read().decode('utf-8'), None)
+                self._check_error(response, ('email', 'password'))
+            raise
+
+        self._check_error(response, 'ErrorMessage')
+
+        return response, action_url
+
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
             return
 
-        login_form = {
+        # Step 1: download signin page
-            'username': username,
+        signin_page = self._download_webpage(
-            'password': password,
+            self._SIGNIN_URL, None, 'Downloading signin page')
-            'remember': 'false',
-            'stayPut': 'false'
-        }
-        request = sanitized_Request(
-            self._LOGIN_URL, urlencode_postdata(login_form))
-        login_page = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
 
-        # Not (yet) logged in
+        # Already logged in
-        m = re.search(r'loginResultJson\s*=\s*\'(?P<json>[^\']+)\';', login_page)
+        if any(re.search(p, signin_page) for p in (
-        if m is not None:
+                'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
-            response = m.group('json')
-            response_json = json.loads(response)
-            state = response_json['state']
-
-            if state == 'notlogged':
-                raise ExtractorError(
-                    'Unable to login, incorrect username and/or password',
-                    expected=True)
-
-            # This is when we get popup:
-            # > You're already logged in to lynda.com on two devices.
-            # > If you log in here, we'll log you out of another device.
-            # So, we need to confirm this.
-            if state == 'conflicted':
-                confirm_form = {
-                    'username': '',
-                    'password': '',
-                    'resolve': 'true',
-                    'remember': 'false',
-                    'stayPut': 'false',
-                }
-                request = sanitized_Request(
-                    self._LOGIN_URL, urlencode_postdata(confirm_form))
-                login_page = self._download_webpage(
-                    request, None,
-                    'Confirming log in and log out from another device')
-
-        if all(not re.search(p, login_page) for p in ('isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
-            if 'login error' in login_page:
-                mobj = re.search(
-                    r'(?s)<h1[^>]+class="topmost">(?P<title>[^<]+)</h1>\s*<div>(?P<description>.+?)</div>',
-                    login_page)
-                if mobj:
-                    raise ExtractorError(
-                        'lynda returned error: %s - %s'
-                        % (mobj.group('title'), clean_html(mobj.group('description'))),
-                        expected=True)
-            raise ExtractorError('Unable to log in')
-
-    def _logout(self):
-        username, _ = self._get_login_info()
-        if username is None:
             return
 
-        self._download_webpage(
+        # Step 2: submit email
-            'http://www.lynda.com/ajax/logout.aspx', None,
+        signin_form = self._search_regex(
-            'Logging out', 'Unable to log out', fatal=False)
+            r'(?s)(<form[^>]+data-form-name=["\']signin["\'][^>]*>.+?</form>)',
+            signin_page, 'signin form')
+        signin_page, signin_url = self._login_step(
+            signin_form, self._PASSWORD_URL, {'email': username},
+            'Submitting email', self._SIGNIN_URL)
+
+        # Step 3: submit password
+        password_form = signin_page['body']
+        self._login_step(
+            password_form, self._USER_URL, {'email': username, 'password': password},
+            'Submitting password', signin_url)
 
 
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
     _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
-    _NETRC_MACHINE = 'lynda'
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
@@ -212,8 +212,6 @@ class LyndaCourseIE(LyndaBaseIE):
             'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
             course_id, 'Downloading course JSON')
 
-        self._logout()
-
         if course.get('Status') == 'NotFound':
             raise ExtractorError(
                 'Course %s does not exist' % course_id, expected=True)
@@ -246,5 +244,6 @@ class LyndaCourseIE(LyndaBaseIE):
                 % unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT)
 
         course_title = course.get('Title')
+        course_description = course.get('Description')
 
-        return self.playlist_result(entries, course_id, course_title)
+        return self.playlist_result(entries, course_id, course_title, course_description)

youtube_dl/extractor/matchtv.py

@@ -4,16 +4,12 @@ from __future__ import unicode_literals
 import random
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
+from ..utils import xpath_text
-from ..utils import (
-    sanitized_Request,
-    xpath_text,
-)
 
 
 class MatchTVIE(InfoExtractor):
-    _VALID_URL = r'https?://matchtv\.ru/?#live-player'
+    _VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://matchtv.ru/#live-player',
         'info_dict': {
             'id': 'matchtv-live',
@@ -24,12 +20,16 @@ class MatchTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://matchtv.ru/on-air/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = 'matchtv-live'
-        request = sanitized_Request(
+        video_url = self._download_json(
-            'http://player.matchtv.ntvplus.tv/player/smil?%s' % compat_urllib_parse_urlencode({
+            'http://player.matchtv.ntvplus.tv/player/smil', video_id,
+            query={
                 'ts': '',
                 'quality': 'SD',
                 'contentId': '561d2c0df7159b37178b4567',
@@ -40,11 +40,10 @@ class MatchTVIE(InfoExtractor):
                 'contentType': 'channel',
                 'timeShift': '0',
                 'platform': 'portal',
-            }),
+            },
             headers={
                 'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
-            })
+            })['data']['videoUrl']
-        video_url = self._download_json(request, video_id)['data']['videoUrl']
         f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
         formats = self._extract_f4m_formats(f4m_url, video_id)
         self._sort_formats(formats)

youtube_dl/extractor/mitele.py

@@ -1,5 +1,8 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse_urlencode,
@@ -8,6 +11,7 @@ from ..compat import (
 from ..utils import (
     get_element_by_attribute,
     int_or_none,
+    remove_start,
 )
 
 
@@ -15,7 +19,7 @@ class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
     _VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
         # MD5 is unstable
         'info_dict': {
@@ -24,10 +28,31 @@ class MiTeleIE(InfoExtractor):
             'ext': 'flv',
             'title': 'Tor, la web invisible',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+            'series': 'Diario de',
+            'season': 'La redacción',
+            'episode': 'Programa 144',
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
         },
-    }
+    }, {
+        # no explicit title
+        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
+        'info_dict': {
+            'id': 'eLZSwoEd1S3pVyUm8lc6F',
+            'display_id': 'programa-226',
+            'ext': 'flv',
+            'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
+            'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
+            'series': 'Cuarto Milenio',
+            'season': 'Temporada 6',
+            'episode': 'Programa 226',
+            'thumbnail': 're:(?i)^https?://.*\.jpg$',
+            'duration': 7312,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -70,7 +95,22 @@ class MiTeleIE(InfoExtractor):
         self._sort_formats(formats)
 
         title = self._search_regex(
-            r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
+            r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
+            webpage, 'title', default=None)
+
+        mobj = re.search(r'''(?sx)
+                            class="Destacado-text"[^>]*>.*?<h1>\s*
+                            <span>(?P<series>[^<]+)</span>\s*
+                            <span>(?P<season>[^<]+)</span>\s*
+                            <span>(?P<episode>[^<]+)</span>''', webpage)
+        series, season, episode = mobj.groups() if mobj else [None] * 3
+
+        if not title:
+            if mobj:
+                title = '%s - %s - %s' % (series, season, episode)
+            else:
+                title = remove_start(self._search_regex(
+                    r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
 
         video_id = self._search_regex(
             r'data-media-id\s*=\s*"([^"]+)"', webpage,
@@ -83,6 +123,9 @@ class MiTeleIE(InfoExtractor):
             'display_id': display_id,
             'title': title,
             'description': get_element_by_attribute('class', 'text', webpage),
+            'series': series,
+            'season': season,
+            'episode': episode,
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,

youtube_dl/extractor/mtv.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse_urlencode,
     compat_str,
+    compat_xpath,
 )
 from ..utils import (
     ExtractorError,
@@ -84,9 +85,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 rtmp_video_url = rendition.find('./src').text
                 if rtmp_video_url.endswith('siteunavail.png'):
                     continue
+                new_url = self._transform_rtmp_url(rtmp_video_url)
                 formats.append({
-                    'ext': ext,
+                    'ext': 'flv' if new_url.startswith('rtmp') else ext,
-                    'url': self._transform_rtmp_url(rtmp_video_url),
+                    'url': new_url,
                     'format_id': rendition.get('bitrate'),
                     'width': int(rendition.get('width')),
                     'height': int(rendition.get('height')),
@@ -139,9 +141,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 itemdoc, './/{http://search.yahoo.com/mrss/}category',
                 'scheme', 'urn:mtvn:video_title')
         if title_el is None:
-            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
+            title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title'))
         if title_el is None:
-            title_el = itemdoc.find('.//title') or itemdoc.find('./title')
+            title_el = itemdoc.find(compat_xpath('.//title'))
             if title_el.text is None:
                 title_el = None
 

youtube_dl/extractor/nbc.py

@@ -67,6 +67,23 @@ class NBCIE(InfoExtractor):
             # This video has expired but with an escaped embedURL
             'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
             'only_matching': True,
+        },
+        {
+            # HLS streams requires the 'hdnea3' cookie
+            'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
+            'info_dict': {
+                'id': 'n1806',
+                'ext': 'mp4',
+                'title': 'Goliath',
+                'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
+                'timestamp': 1237100400,
+                'upload_date': '20090315',
+                'uploader': 'NBCU-COM',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'skip': 'Only works from US',
         }
     ]
 
@@ -249,6 +266,11 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
             'only_matching': True,
         },
+        {
+            # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
+            'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -272,18 +294,17 @@ class NBCNewsIE(ThePlatformIE):
             webpage = self._download_webpage(url, display_id)
             info = None
             bootstrap_json = self._search_regex(
-                r'(?m)var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$',
+                [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
+                 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"'],
                 webpage, 'bootstrap json', default=None)
-            if bootstrap_json:
+            bootstrap = self._parse_json(
-                bootstrap = self._parse_json(bootstrap_json, display_id)
+                bootstrap_json, display_id, transform_source=unescapeHTML)
+            if 'results' in bootstrap:
                 info = bootstrap['results'][0]['video']
+            elif 'video' in bootstrap:
+                info = bootstrap['video']
             else:
-                player_instance_json = self._search_regex(
+                info = bootstrap
-                    r'videoObj\s*:\s*({.+})', webpage, 'player instance', default=None)
-                if not player_instance_json:
-                    player_instance_json = self._html_search_regex(
-                        r'data-video="([^"]+)"', webpage, 'video json')
-                info = self._parse_json(player_instance_json, display_id)
             video_id = info['mpxId']
             title = info['title']
 

youtube_dl/extractor/nick.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
 from ..compat import compat_urllib_parse_urlencode
+from ..utils import update_url_query
 
 
 class NickIE(MTVServicesInfoExtractor):
@@ -61,3 +62,26 @@ class NickIE(MTVServicesInfoExtractor):
 
     def _extract_mgid(self, webpage):
         return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid')
+
+
+class NickDeIE(MTVServicesInfoExtractor):
+    IE_NAME = 'nick.de'
+    _VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.nick.de/shows/342-icarly',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        mrss_url = update_url_query(self._search_regex(
+            r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
+            {'siteKey': 'nick.de'})
+
+        return self._get_videos_info_from_url(mrss_url, video_id)

youtube_dl/extractor/nrk.py

@@ -163,7 +163,7 @@ class NRKTVIE(NRKBaseIE):
             'ext': 'mp4',
             'title': '20 spørsmål 23.05.2014',
             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
-            'duration': 1741.52,
+            'duration': 1741,
         },
     }, {
         'url': 'https://tv.nrk.no/program/mdfp15000514',
@@ -173,7 +173,7 @@ class NRKTVIE(NRKBaseIE):
             'ext': 'mp4',
             'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
-            'duration': 4605.08,
+            'duration': 4605,
         },
     }, {
         # single playlist video
@@ -260,30 +260,34 @@ class NRKPlaylistIE(InfoExtractor):
 
 class NRKSkoleIE(InfoExtractor):
     IE_DESC = 'NRK Skole'
-    _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
+        'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
-        'md5': '04cd85877cc1913bce73c5d28a47e00f',
+        'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
         'info_dict': {
             'id': '6021',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Genetikk og eneggede tvillinger',
             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
             'duration': 399,
         },
     }, {
-        'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed',
+        'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.nrk.no/skole/klippdetalj?topic=urn:x-mediadb:21379',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = compat_urllib_parse_unquote(self._match_id(url))
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
+            video_id)
+
+        nrk_id = self._parse_json(
+            self._search_regex(
+                r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
+                webpage, 'application json'),
+            video_id)['activeMedia']['psId']
 
-        nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id')
         return self.url_result('nrk:%s' % nrk_id)

youtube_dl/extractor/openload.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
+    _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -31,6 +31,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://openload.io/f/ZAn6oz-VZGE/',
         'only_matching': True,
+    }, {
+        'url': 'https://openload.co/f/_-ztPaZtMhM/',
+        'only_matching': True,
     }, {
         # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
         # for title and ext
@@ -100,7 +103,7 @@ class OpenloadIE(InfoExtractor):
             raise ExtractorError('File not found', expected=True)
 
         code = self._search_regex(
-            r'</video>\s*</div>\s*<script[^>]+>([^<]+)</script>',
+            r'</video>\s*</div>\s*<script[^>]+>[^>]+</script>\s*<script[^>]+>([^<]+)</script>',
             webpage, 'JS code')
 
         decoded = self.openload_decode(code)

youtube_dl/extractor/pornhd.py

@@ -1,19 +1,32 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
     js_to_json,
-    qualities,
 )
 
 
 class PornHdIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
-    _TEST = {
+    _TESTS = [{
+        'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
+        'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+        'info_dict': {
+            'id': '9864',
+            'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
+            'ext': 'mp4',
+            'title': 'Restroom selfie masturbation',
+            'description': 'md5:3748420395e03e31ac96857a8f125b2b',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'view_count': int,
+            'age_limit': 18,
+        }
+    }, {
+        # removed video
         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
         'md5': '956b8ca569f7f4d8ec563e2c41598441',
         'info_dict': {
@@ -25,8 +38,9 @@ class PornHdIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg',
             'view_count': int,
             'age_limit': 18,
-        }
+        },
-    }
+        'skip': 'Not available anymore',
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -38,28 +52,38 @@ class PornHdIE(InfoExtractor):
         title = self._html_search_regex(
             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
-        description = self._html_search_regex(
-            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
-        view_count = int_or_none(self._html_search_regex(
-            r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
-        thumbnail = self._search_regex(
-            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
 
-        quality = qualities(['sd', 'hd'])
+        sources = self._parse_json(js_to_json(self._search_regex(
-        sources = json.loads(js_to_json(self._search_regex(
             r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
-            webpage, 'sources')))
+            webpage, 'sources', default='{}')), video_id)
+
+        if not sources:
+            message = self._html_search_regex(
+                r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
+                webpage, 'error message', group='value')
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
+
         formats = []
-        for qname, video_url in sources.items():
+        for format_id, video_url in sources.items():
             if not video_url:
                 continue
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]', format_id, 'height', default=None))
             formats.append({
                 'url': video_url,
-                'format_id': qname,
+                'format_id': format_id,
-                'quality': quality(qname),
+                'height': height,
             })
         self._sort_formats(formats)
 
+        description = self._html_search_regex(
+            r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
+            webpage, 'description', fatal=False, group='value')
+        view_count = int_or_none(self._html_search_regex(
+            r'(\d+) views\s*<', webpage, 'view count', fatal=False))
+        thumbnail = self._search_regex(
+            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
+
         return {
             'id': video_id,
             'display_id': display_id,

youtube_dl/extractor/pornhub.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools
@@ -39,7 +40,25 @@ class PornHubIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
-        }
+        },
+    }, {
+        # non-ASCII title
+        'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
+        'info_dict': {
+            'id': '1331683002',
+            'ext': 'mp4',
+            'title': '重庆婷婷女王足交',
+            'uploader': 'cj397186295',
+            'duration': 1753,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
         'only_matching': True,
@@ -76,19 +95,25 @@ class PornHubIE(InfoExtractor):
                 'PornHub said: %s' % error_msg,
                 expected=True, video_id=video_id)
 
+        # video_title from flashvars contains whitespace instead of non-ASCII (see
+        # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
+        # on that anymore.
+        title = self._html_search_meta(
+            'twitter:title', webpage, default=None) or self._search_regex(
+            (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
+             r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
+             r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
+            webpage, 'title', group='title')
+
         flashvars = self._parse_json(
             self._search_regex(
                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
             video_id)
         if flashvars:
-            video_title = flashvars.get('video_title')
             thumbnail = flashvars.get('image_url')
             duration = int_or_none(flashvars.get('video_duration'))
         else:
-            video_title, thumbnail, duration = [None] * 3
+            title, thumbnail, duration = [None] * 3
-
-        if not video_title:
-            video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
 
         video_uploader = self._html_search_regex(
             r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
@@ -137,7 +162,7 @@ class PornHubIE(InfoExtractor):
         return {
             'id': video_id,
             'uploader': video_uploader,
-            'title': video_title,
+            'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,

youtube_dl/extractor/r7.py

@@ -2,22 +2,19 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import int_or_none
-    js_to_json,
-    unescapeHTML,
-    int_or_none,
-)
 
 
 class R7IE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://
+    _VALID_URL = r'''(?x)
+                        https?://
                         (?:
                             (?:[a-zA-Z]+)\.r7\.com(?:/[^/]+)+/idmedia/|
                             noticias\.r7\.com(?:/[^/]+)+/[^/]+-|
                             player\.r7\.com/video/i/
                         )
                         (?P<id>[\da-f]{24})
-                        '''
+                    '''
     _TESTS = [{
         'url': 'http://videos.r7.com/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-/idmedia/54e7050b0cf2ff57e0279389.html',
         'md5': '403c4e393617e8e8ddc748978ee8efde',
@@ -25,6 +22,7 @@ class R7IE(InfoExtractor):
             'id': '54e7050b0cf2ff57e0279389',
             'ext': 'mp4',
             'title': 'Policiais humilham suspeito à beira da morte: "Morre com dignidade"',
+            'description': 'md5:01812008664be76a6479aa58ec865b72',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 98,
             'like_count': int,
@@ -44,45 +42,72 @@ class R7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
+        video = self._download_json(
-            'http://player.r7.com/video/i/%s' % video_id, video_id)
+            'http://player-api.r7.com/video/i/%s' % video_id, video_id)
 
-        item = self._parse_json(js_to_json(self._search_regex(
+        title = video['title']
-            r'(?s)var\s+item\s*=\s*({.+?});', webpage, 'player')), video_id)
-
-        title = unescapeHTML(item['title'])
-        thumbnail = item.get('init', {}).get('thumbUri')
-        duration = None
-
-        statistics = item.get('statistics', {})
-        like_count = int_or_none(statistics.get('likes'))
-        view_count = int_or_none(statistics.get('views'))
 
         formats = []
-        for format_key, format_dict in item['playlist'][0].items():
+        media_url_hls = video.get('media_url_hls')
-            src = format_dict.get('src')
+        if media_url_hls:
-            if not src:
+            formats.extend(self._extract_m3u8_formats(
-                continue
+                media_url_hls, video_id, 'mp4', entry_protocol='m3u8_native',
-            format_id = format_dict.get('format') or format_key
+                m3u8_id='hls', fatal=False))
-            if duration is None:
+        media_url = video.get('media_url')
-                duration = format_dict.get('duration')
+        if media_url:
-            if '.f4m' in src:
+            f = {
-                formats.extend(self._extract_f4m_formats(src, video_id, preference=-1))
+                'url': media_url,
-            elif src.endswith('.m3u8'):
+                'format_id': 'http',
-                formats.extend(self._extract_m3u8_formats(src, video_id, 'mp4', preference=-2))
+            }
-            else:
+            # m3u8 format always matches the http format, let's copy metadata from
-                formats.append({
+            # one to another
-                    'url': src,
+            m3u8_formats = list(filter(
-                    'format_id': format_id,
+                lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                })
+                formats))
+            if len(m3u8_formats) == 1:
+                f_copy = m3u8_formats[0].copy()
+                f_copy.update(f)
+                f_copy['protocol'] = 'http'
+                f = f_copy
+            formats.append(f)
         self._sort_formats(formats)
 
+        description = video.get('description')
+        thumbnail = video.get('thumb')
+        duration = int_or_none(video.get('media_duration'))
+        like_count = int_or_none(video.get('likes'))
+        view_count = int_or_none(video.get('views'))
+
         return {
             'id': video_id,
             'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'duration': duration,
             'like_count': like_count,
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class R7ArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[a-zA-Z]+)\.r7\.com/(?:[^/]+/)+[^/?#&]+-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://tv.r7.com/record-play/balanco-geral/videos/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-16102015',
+        'only_matching': True,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if R7IE.suitable(url) else super(R7ArticleIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'<div[^>]+(?:id=["\']player-|class=["\']embed["\'][^>]+id=["\'])([\da-f]{24})',
+            webpage, 'video id')
+
+        return self.url_result('http://player.r7.com/video/i/%s' % video_id, R7IE.ie_key())

youtube_dl/extractor/radiojavan.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import(
+from ..utils import (
     unified_strdate,
     str_to_int,
 )

youtube_dl/extractor/rockstargames.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class RockstarGamesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rockstargames\.com/videos(?:/video/|#?/?\?.*\bvideo=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.rockstargames.com/videos/video/11544/',
+        'md5': '03b5caa6e357a4bd50e3143fc03e5733',
+        'info_dict': {
+            'id': '11544',
+            'ext': 'mp4',
+            'title': 'Further Adventures in Finance and Felony Trailer',
+            'description': 'md5:6d31f55f30cb101b5476c4a379e324a3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1464876000,
+            'upload_date': '20160602',
+        }
+    }, {
+        'url': 'http://www.rockstargames.com/videos#/?video=48',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'https://www.rockstargames.com/videoplayer/videos/get-video.json',
+            video_id, query={
+                'id': video_id,
+                'locale': 'en_us',
+            })['video']
+
+        title = video['title']
+
+        formats = []
+        for video in video['files_processed']['video/mp4']:
+            if not video.get('src'):
+                continue
+            resolution = video.get('resolution')
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]$', resolution or '', 'height', default=None))
+            formats.append({
+                'url': self._proto_relative_url(video['src']),
+                'format_id': resolution,
+                'height': height,
+            })
+
+        if not formats:
+            youtube_id = video.get('youtube_id')
+            if youtube_id:
+                return self.url_result(youtube_id, 'Youtube')
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': self._proto_relative_url(video.get('screencap')),
+            'timestamp': parse_iso8601(video.get('created')),
+            'formats': formats,
+        }

youtube_dl/extractor/sportschau.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .wdr import WDRBaseIE
+from ..utils import get_element_by_attribute
+
+
+class SportschauIE(WDRBaseIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video-?(?P<id>[^/#?]+)\.html'
+    _TEST = {
+        'url': 'http://www.sportschau.de/uefaeuro2016/videos/video-dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100.html',
+        'info_dict': {
+            'id': 'mdb-1140188',
+            'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100',
+            'ext': 'mp4',
+            'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen',
+            'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.',
+            'upload_date': '20160615',
+        },
+        'skip': 'Geo-restricted to Germany',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_wdr_video(webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info

youtube_dl/extractor/streamcloud.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     sanitized_Request,
     urlencode_postdata,
 )
@@ -14,7 +15,7 @@ class StreamcloudIE(InfoExtractor):
     IE_NAME = 'streamcloud.eu'
     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
         'md5': '6bea4c7fa5daaacc2a946b7146286686',
         'info_dict': {
@@ -23,7 +24,10 @@ class StreamcloudIE(InfoExtractor):
             'title': 'youtube-dl test video  \'/\\ ä ↭',
         },
         'skip': 'Only available from the EU'
-    }
+    }, {
+        'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -31,6 +35,10 @@ class StreamcloudIE(InfoExtractor):
 
         orig_webpage = self._download_webpage(url, video_id)
 
+        if '>File Not Found<' in orig_webpage:
+            raise ExtractorError(
+                'Video %s does not exist' % video_id, expected=True)
+
         fields = re.findall(r'''(?x)<input\s+
             type="(?:hidden|submit)"\s+
             name="([^"]+)"\s+

youtube_dl/extractor/telewebion.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class TelewebionIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.telewebion\.com/#!/episode/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.telewebion.com/#!/episode/1263668/',
+        'info_dict': {
+            'id': '1263668',
+            'ext': 'mp4',
+            'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'view_count': int,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        secure_token = self._download_webpage(
+            'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id)
+        episode_details = self._download_json(
+            'http://m.s2.telewebion.com/op/op', video_id,
+            query={'action': 'getEpisodeDetails', 'episode_id': video_id})
+
+        m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % (
+            video_id, episode_details['file_path'], secure_token)
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4', m3u8_id='hls')
+
+        picture_paths = [
+            episode_details.get('picture_path'),
+            episode_details.get('large_picture_path'),
+        ]
+
+        thumbnails = [{
+            'url': picture_path,
+            'preference': idx,
+        } for idx, picture_path in enumerate(picture_paths) if picture_path is not None]
+
+        return {
+            'id': video_id,
+            'title': episode_details['title'],
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'view_count': episode_details.get('view_count'),
+        }

youtube_dl/extractor/theplatform.py

@@ -14,11 +14,13 @@ from ..compat import (
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     int_or_none,
     sanitized_Request,
     unsmuggle_url,
+    update_url_query,
     xpath_with_ns,
     mimetype2ext,
     find_xpath_attr,
@@ -48,6 +50,12 @@ class ThePlatformBaseIE(OnceIE):
             if OnceIE.suitable(_format['url']):
                 formats.extend(self._extract_once_formats(_format['url']))
             else:
+                media_url = _format['url']
+                if determine_ext(media_url) == 'm3u8':
+                    hdnea2 = self._get_cookies(media_url).get('hdnea2')
+                    if hdnea2:
+                        _format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
+
                 formats.append(_format)
 
         subtitles = self._parse_smil_subtitles(meta, default_ns)
@@ -269,9 +277,9 @@ class ThePlatformIE(ThePlatformBaseIE):
 
 
 class ThePlatformFeedIE(ThePlatformBaseIE):
-    _URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&byGuid=%s'
+    _URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&%s'
-    _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*byGuid=(?P<id>[a-zA-Z0-9_]+)'
+    _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*(?P<filter>by(?:Gui|I)d=(?P<id>[\w-]+))'
-    _TEST = {
+    _TESTS = [{
         # From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207
         'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207',
         'md5': '6e32495b5073ab414471b615c5ded394',
@@ -287,32 +295,38 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
             'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'],
             'uploader': 'NBCU-NEWS',
         },
-    }
+    }]
 
-    def _real_extract(self, url):
+    def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
-        mobj = re.match(self._VALID_URL, url)
+        real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
-
+        entry = self._download_json(real_url, video_id)['entries'][0]
-        video_id = mobj.group('id')
-        provider_id = mobj.group('provider_id')
-        feed_id = mobj.group('feed_id')
-
-        real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, video_id)
-        feed = self._download_json(real_url, video_id)
-        entry = feed['entries'][0]
 
         formats = []
         subtitles = {}
         first_video_id = None
         duration = None
+        asset_types = []
         for item in entry['media$content']:
-            smil_url = item['plfile$url'] + '&mbr=true'
+            smil_url = item['plfile$url']
             cur_video_id = ThePlatformIE._match_id(smil_url)
             if first_video_id is None:
                 first_video_id = cur_video_id
                 duration = float_or_none(item.get('plfile$duration'))
-            cur_formats, cur_subtitles = self._extract_theplatform_smil(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id)
+            for asset_type in item['plfile$assetTypes']:
-            formats.extend(cur_formats)
+                if asset_type in asset_types:
-            subtitles = self._merge_subtitles(subtitles, cur_subtitles)
+                    continue
+                asset_types.append(asset_type)
+                query = {
+                    'mbr': 'true',
+                    'formats': item['plfile$format'],
+                    'assetTypes': asset_type,
+                }
+                if asset_type in asset_types_query:
+                    query.update(asset_types_query[asset_type])
+                cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
+                    smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
+                formats.extend(cur_formats)
+                subtitles = self._merge_subtitles(subtitles, cur_subtitles)
 
         self._sort_formats(formats)
 
@@ -336,5 +350,17 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
             'timestamp': timestamp,
             'categories': categories,
         })
+        if custom_fields:
+            ret.update(custom_fields(entry))
 
         return ret
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        provider_id = mobj.group('provider_id')
+        feed_id = mobj.group('feed_id')
+        filter_query = mobj.group('filter')
+
+        return self._extract_feed_info(provider_id, feed_id, filter_query, video_id)

youtube_dl/extractor/thesixtyone.py

@@ -12,7 +12,7 @@ class TheSixtyOneIE(InfoExtractor):
             s|
             song/comments/list|
             song
-        )/(?P<id>[A-Za-z0-9]+)/?$'''
+        )/(?:[^/]+/)?(?P<id>[A-Za-z0-9]+)/?$'''
     _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
     _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
     _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
@@ -45,6 +45,10 @@ class TheSixtyOneIE(InfoExtractor):
             'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/',
             'only_matching': True,
         },
+        {
+            'url': 'http://www.thesixtyone.com/maryatmidnight/song/StrawberriesandCream/yvWtLp0c4GQ/',
+            'only_matching': True,
+        },
     ]
 
     _DECODE_MAP = {

youtube_dl/extractor/twitch.py

@@ -16,6 +16,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
+    js_to_json,
     orderedSet,
     parse_duration,
     parse_iso8601,
@@ -260,7 +261,7 @@ class TwitchVodIE(TwitchItemBaseIE):
                     'nauth': access_token['token'],
                     'nauthsig': access_token['sig'],
                 })),
-            item_id, 'mp4')
+            item_id, 'mp4', entry_protocol='m3u8_native')
 
         self._prefer_source(formats)
         info['formats'] = formats
@@ -454,3 +455,45 @@ class TwitchStreamIE(TwitchBaseIE):
             'formats': formats,
             'is_live': True,
         }
+
+
+class TwitchClipsIE(InfoExtractor):
+    IE_NAME = 'twitch:clips'
+    _VALID_URL = r'https?://clips\.twitch\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+
+    _TEST = {
+        'url': 'https://clips.twitch.tv/ea/AggressiveCobraPoooound',
+        'md5': '761769e1eafce0ffebfb4089cb3847cd',
+        'info_dict': {
+            'id': 'AggressiveCobraPoooound',
+            'ext': 'mp4',
+            'title': 'EA Play 2016 Live from the Novo Theatre',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'creator': 'EA',
+            'uploader': 'stereotype_',
+            'uploader_id': 'stereotype_',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        clip = self._parse_json(
+            self._search_regex(
+                r'(?s)clipInfo\s*=\s*({.+?});', webpage, 'clip info'),
+            video_id, transform_source=js_to_json)
+
+        video_url = clip['clip_video_url']
+        title = clip['channel_title']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'creator': clip.get('broadcaster_display_name') or clip.get('broadcaster_login'),
+            'uploader': clip.get('curator_login'),
+            'uploader_id': clip.get('curator_display_name'),
+        }

youtube_dl/extractor/twitter.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     float_or_none,
     xpath_text,
     remove_end,
@@ -52,7 +53,7 @@ class TwitterCardIE(TwitterBaseIE):
                 'id': 'dq4Oj5quskI',
                 'ext': 'mp4',
                 'title': 'Ubuntu 11.10 Overview',
-                'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
+                'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10...',
                 'upload_date': '20111013',
                 'uploader': 'OMG! Ubuntu!',
                 'uploader_id': 'omgubuntu',
@@ -116,13 +117,16 @@ class TwitterCardIE(TwitterBaseIE):
         video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source')
 
         if video_url:
-            f = {
+            if determine_ext(video_url) == 'm3u8':
-                'url': video_url,
+                formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
-            }
+            else:
+                f = {
+                    'url': video_url,
+                }
 
-            _search_dimensions_in_video_url(f, video_url)
+                _search_dimensions_in_video_url(f, video_url)
 
-            formats.append(f)
+                formats.append(f)
 
         vmap_url = config.get('vmapUrl') or config.get('vmap_url')
         if vmap_url:
@@ -207,6 +211,7 @@ class TwitterIE(InfoExtractor):
             'uploader_id': 'giphz',
         },
         'expected_warnings': ['height', 'width'],
+        'skip': 'Account suspended',
     }, {
         'url': 'https://twitter.com/starwars/status/665052190608723968',
         'md5': '39b7199856dee6cd4432e72c74bc69d4',
@@ -239,10 +244,10 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': '700207533655363584',
             'ext': 'mp4',
-            'title': 'jay - BEAT PROD: @suhmeduh #Damndaniel',
+            'title': 'Donte The Dumbass - BEAT PROD: @suhmeduh #Damndaniel',
-            'description': 'jay on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
+            'description': 'Donte The Dumbass on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
             'thumbnail': 're:^https?://.*\.jpg',
-            'uploader': 'jay',
+            'uploader': 'Donte The Dumbass',
             'uploader_id': 'jaydingeer',
         },
         'params': {
@@ -262,7 +267,6 @@ class TwitterIE(InfoExtractor):
         'add_ie': ['Vine'],
     }, {
         'url': 'https://twitter.com/captainamerica/status/719944021058060289',
-        # md5 constantly changes
         'info_dict': {
             'id': '719944021058060289',
             'ext': 'mp4',
@@ -271,6 +275,9 @@ class TwitterIE(InfoExtractor):
             'uploader_id': 'captainamerica',
             'uploader': 'Captain America',
         },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
     }]
 
     def _real_extract(self, url):
@@ -278,7 +285,11 @@ class TwitterIE(InfoExtractor):
         user_id = mobj.group('user_id')
         twid = mobj.group('id')
 
-        webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
+        webpage, urlh = self._download_webpage_handle(
+            self._TEMPLATE_URL % (user_id, twid), twid)
+
+        if 'twitter.com/account/suspended' in urlh.geturl():
+            raise ExtractorError('Account suspended by Twitter.', expected=True)
 
         username = remove_end(self._og_search_title(webpage), ' on Twitter')
 

youtube_dl/extractor/vessel.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import json
+import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -12,11 +13,11 @@ from ..utils import (
 
 
 class VesselIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vessel\.com/videos/(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
     _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
     _LOGIN_URL = 'https://www.vessel.com/api/account/login'
     _NETRC_MACHINE = 'vessel'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.vessel.com/videos/HDN7G5UMs',
         'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
         'info_dict': {
@@ -28,7 +29,16 @@ class VesselIE(InfoExtractor):
             'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
             'timestamp': int,
         },
-    }
+    }, {
+        'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z]+.*?)\1',
+            webpage)]
 
     @staticmethod
     def make_json_request(url, data):
@@ -98,16 +108,24 @@ class VesselIE(InfoExtractor):
 
         formats = []
         for f in video_asset.get('sources', []):
-            if f['name'] == 'hls-index':
+            location = f.get('location')
+            if not location:
+                continue
+            name = f.get('name')
+            if name == 'hls-index':
                 formats.extend(self._extract_m3u8_formats(
-                    f['location'], video_id, ext='mp4', m3u8_id='m3u8'))
+                    location, video_id, ext='mp4',
+                    entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False))
+            elif name == 'dash-index':
+                formats.extend(self._extract_mpd_formats(
+                    location, video_id, mpd_id='dash', fatal=False))
             else:
                 formats.append({
-                    'format_id': f['name'],
+                    'format_id': name,
                     'tbr': f.get('bitrate'),
                     'height': f.get('height'),
                     'width': f.get('width'),
-                    'url': f['location'],
+                    'url': location,
                 })
         self._sort_formats(formats)
 

youtube_dl/extractor/vidio.py

@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class VidioIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
+        'md5': 'cd2801394afc164e9775db6a140b91fe',
+        'info_dict': {
+            'id': '165683',
+            'display_id': 'dj_ambred-booyah-live-2015',
+            'ext': 'mp4',
+            'title': 'DJ_AMBRED - Booyah (Live 2015)',
+            'description': 'md5:27dc15f819b6a78a626490881adbadf8',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 149,
+            'like_count': int,
+        },
+    }, {
+        'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id, display_id = mobj.group('id', 'display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._og_search_title(webpage)
+
+        m3u8_url, duration, thumbnail = [None] * 3
+
+        clips = self._parse_json(
+            self._html_search_regex(
+                r'data-json-clips\s*=\s*(["\'])(?P<data>\[.+?\])\1',
+                webpage, 'video data', default='[]', group='data'),
+            display_id, fatal=False)
+        if clips:
+            clip = clips[0]
+            m3u8_url = clip.get('sources', [{}])[0].get('file')
+            duration = clip.get('clip_duration')
+            thumbnail = clip.get('image')
+
+        m3u8_url = m3u8_url or self._search_regex(
+            r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>.+?)\1', webpage, 'hls url')
+        formats = self._extract_m3u8_formats(m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
+
+        duration = int_or_none(duration or self._search_regex(
+            r'data-video-duration=(["\'])(?P<duartion>\d+)\1', webpage, 'duration'))
+        thumbnail = thumbnail or self._og_search_thumbnail(webpage)
+
+        like_count = int_or_none(self._search_regex(
+            (r'<span[^>]+data-comment-vote-count=["\'](\d+)',
+             r'<span[^>]+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'like_count': like_count,
+            'formats': formats,
+        }

youtube_dl/extractor/viki.py

@@ -101,10 +101,13 @@ class VikiBaseIE(InfoExtractor):
             self.report_warning('Unable to get session token, login has probably failed')
 
     @staticmethod
-    def dict_selection(dict_obj, preferred_key):
+    def dict_selection(dict_obj, preferred_key, allow_fallback=True):
         if preferred_key in dict_obj:
             return dict_obj.get(preferred_key)
 
+        if not allow_fallback:
+            return
+
         filtered_dict = list(filter(None, [dict_obj.get(k) for k in dict_obj.keys()]))
         return filtered_dict[0] if filtered_dict else None
 
@@ -127,7 +130,7 @@ class VikiIE(VikiBaseIE):
     }, {
         # clip
         'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
-        'md5': '86c0b5dbd4d83a6611a79987cc7a1989',
+        'md5': 'feea2b1d7b3957f70886e6dfd8b8be84',
         'info_dict': {
             'id': '1067139v',
             'ext': 'mp4',
@@ -156,17 +159,18 @@ class VikiIE(VikiBaseIE):
         'params': {
             # m3u8 download
             'skip_download': True,
-        }
+        },
+        'skip': 'Blocked in the US',
     }, {
         # episode
         'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
-        'md5': '190f3ef426005ba3a080a63325955bc3',
+        'md5': '1f54697dabc8f13f31bf06bb2e4de6db',
         'info_dict': {
             'id': '44699v',
             'ext': 'mp4',
             'title': 'Boys Over Flowers - Episode 1',
-            'description': 'md5:52617e4f729c7d03bfd4bcbbb6e946f2',
+            'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
-            'duration': 4155,
+            'duration': 4204,
             'timestamp': 1270496524,
             'upload_date': '20100405',
             'uploader': 'group8',
@@ -196,7 +200,7 @@ class VikiIE(VikiBaseIE):
     }, {
         # non-English description
         'url': 'http://www.viki.com/videos/158036v-love-in-magic',
-        'md5': '1713ae35df5a521b31f6dc40730e7c9c',
+        'md5': '013dc282714e22acf9447cad14ff1208',
         'info_dict': {
             'id': '158036v',
             'ext': 'mp4',
@@ -217,7 +221,7 @@ class VikiIE(VikiBaseIE):
 
         self._check_errors(video)
 
-        title = self.dict_selection(video.get('titles', {}), 'en')
+        title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
         if not title:
             title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
             container_titles = video.get('container', {}).get('titles', {})
@@ -302,7 +306,7 @@ class VikiChannelIE(VikiBaseIE):
             'title': 'Boys Over Flowers',
             'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
         },
-        'playlist_count': 70,
+        'playlist_mincount': 71,
     }, {
         'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
         'info_dict': {

youtube_dl/extractor/vimeo.py

@@ -8,6 +8,7 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
+    compat_str,
     compat_urlparse,
 )
 from ..utils import (
@@ -24,6 +25,7 @@ from ..utils import (
     urlencode_postdata,
     unescapeHTML,
     parse_filesize,
+    try_get,
 )
 
 
@@ -66,6 +68,69 @@ class VimeoBaseInfoExtractor(InfoExtractor):
     def _set_vimeo_cookie(self, name, value):
         self._set_cookie('vimeo.com', name, value)
 
+    def _vimeo_sort_formats(self, formats):
+        # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
+        # at the same time without actual units specified. This lead to wrong sorting.
+        self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
+
+    def _parse_config(self, config, video_id):
+        # Extract title
+        video_title = config['video']['title']
+
+        # Extract uploader, uploader_url and uploader_id
+        video_uploader = config['video'].get('owner', {}).get('name')
+        video_uploader_url = config['video'].get('owner', {}).get('url')
+        video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
+
+        # Extract video thumbnail
+        video_thumbnail = config['video'].get('thumbnail')
+        if video_thumbnail is None:
+            video_thumbs = config['video'].get('thumbs')
+            if video_thumbs and isinstance(video_thumbs, dict):
+                _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
+
+        # Extract video duration
+        video_duration = int_or_none(config['video'].get('duration'))
+
+        formats = []
+        config_files = config['video'].get('files') or config['request'].get('files', {})
+        for f in config_files.get('progressive', []):
+            video_url = f.get('url')
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'format_id': 'http-%s' % f.get('quality'),
+                'width': int_or_none(f.get('width')),
+                'height': int_or_none(f.get('height')),
+                'fps': int_or_none(f.get('fps')),
+                'tbr': int_or_none(f.get('bitrate')),
+            })
+        m3u8_url = config_files.get('hls', {}).get('url')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
+        subtitles = {}
+        text_tracks = config['request'].get('text_tracks')
+        if text_tracks:
+            for tt in text_tracks:
+                subtitles[tt['lang']] = [{
+                    'ext': 'vtt',
+                    'url': 'https://vimeo.com' + tt['url'],
+                }]
+
+        return {
+            'title': video_title,
+            'uploader': video_uploader,
+            'uploader_id': video_uploader_id,
+            'uploader_url': video_uploader_url,
+            'thumbnail': video_thumbnail,
+            'duration': video_duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
 
 class VimeoIE(VimeoBaseInfoExtractor):
     """Information extractor for vimeo.com."""
@@ -153,7 +218,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader_id': 'user18948128',
                 'uploader': 'Jaime Marquínez Ferrándiz',
                 'duration': 10,
-                'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
+                'description': 'This is "youtube-dl password protected test video" by  on Vimeo, the home for high quality videos and the people who love them.',
             },
             'params': {
                 'videopassword': 'youtube-dl',
@@ -382,28 +447,24 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if config.get('view') == 4:
                 config = self._verify_player_video_password(url, video_id)
 
-        if '>You rented this title.<' in webpage:
+        def is_rented():
+            if '>You rented this title.<' in webpage:
+                return True
+            if config.get('user', {}).get('purchased'):
+                return True
+            label = try_get(
+                config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
+            if label and label.startswith('You rented this'):
+                return True
+            return False
+
+        if is_rented():
             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
             if feature_id and not data.get('force_feature_id', False):
                 return self.url_result(smuggle_url(
                     'https://player.vimeo.com/player/%s' % feature_id,
                     {'force_feature_id': True}), 'Vimeo')
 
-        # Extract title
-        video_title = config['video']['title']
-
-        # Extract uploader, uploader_url and uploader_id
-        video_uploader = config['video'].get('owner', {}).get('name')
-        video_uploader_url = config['video'].get('owner', {}).get('url')
-        video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
-
-        # Extract video thumbnail
-        video_thumbnail = config['video'].get('thumbnail')
-        if video_thumbnail is None:
-            video_thumbs = config['video'].get('thumbs')
-            if video_thumbs and isinstance(video_thumbs, dict):
-                _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
-
         # Extract video description
 
         video_description = self._html_search_regex(
@@ -423,9 +484,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
         if not video_description and not mobj.group('player'):
             self._downloader.report_warning('Cannot find video description')
 
-        # Extract video duration
-        video_duration = int_or_none(config['video'].get('duration'))
-
         # Extract upload date
         video_upload_date = None
         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
@@ -463,53 +521,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
                             'format_id': source_name,
                             'preference': 1,
                         })
-        config_files = config['video'].get('files') or config['request'].get('files', {})
-        for f in config_files.get('progressive', []):
-            video_url = f.get('url')
-            if not video_url:
-                continue
-            formats.append({
-                'url': video_url,
-                'format_id': 'http-%s' % f.get('quality'),
-                'width': int_or_none(f.get('width')),
-                'height': int_or_none(f.get('height')),
-                'fps': int_or_none(f.get('fps')),
-                'tbr': int_or_none(f.get('bitrate')),
-            })
-        m3u8_url = config_files.get('hls', {}).get('url')
-        if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-        # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
-        # at the same time without actual units specified. This lead to wrong sorting.
-        self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
 
-        subtitles = {}
+        info_dict = self._parse_config(config, video_id)
-        text_tracks = config['request'].get('text_tracks')
+        formats.extend(info_dict['formats'])
-        if text_tracks:
+        self._vimeo_sort_formats(formats)
-            for tt in text_tracks:
+        info_dict.update({
-                subtitles[tt['lang']] = [{
-                    'ext': 'vtt',
-                    'url': 'https://vimeo.com' + tt['url'],
-                }]
-
-        return {
             'id': video_id,
-            'uploader': video_uploader,
-            'uploader_url': video_uploader_url,
-            'uploader_id': video_uploader_id,
-            'upload_date': video_upload_date,
-            'title': video_title,
-            'thumbnail': video_thumbnail,
-            'description': video_description,
-            'duration': video_duration,
             'formats': formats,
+            'upload_date': video_upload_date,
+            'description': video_description,
             'webpage_url': url,
             'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,
-            'subtitles': subtitles,
+        })
-        }
+
+        return info_dict
 
 
 class VimeoOndemandIE(VimeoBaseInfoExtractor):
@@ -692,7 +719,7 @@ class VimeoGroupsIE(VimeoAlbumIE):
         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 
 
-class VimeoReviewIE(InfoExtractor):
+class VimeoReviewIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'
     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
@@ -704,6 +731,7 @@ class VimeoReviewIE(InfoExtractor):
             'ext': 'mp4',
             'title': "DICK HARDWICK 'Comedian'",
             'uploader': 'Richard Hardwick',
+            'uploader_id': 'user21297594',
         }
     }, {
         'note': 'video player needs Referer',
@@ -716,14 +744,18 @@ class VimeoReviewIE(InfoExtractor):
             'uploader': 'DevWeek Events',
             'duration': 2773,
             'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader_id': 'user22258446',
         }
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
+        config = self._download_json(
-        player_url = 'https://player.vimeo.com/player/' + video_id
+            'https://player.vimeo.com/video/%s/config' % video_id, video_id)
-        return self.url_result(player_url, 'Vimeo', video_id)
+        info_dict = self._parse_config(config, video_id)
+        self._vimeo_sort_formats(info_dict['formats'])
+        info_dict['id'] = video_id
+        return info_dict
 
 
 class VimeoWatchLaterIE(VimeoChannelIE):

youtube_dl/extractor/vlive.py

@@ -9,6 +9,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    remove_start,
 )
 from ..compat import compat_urllib_parse_urlencode
 
@@ -39,6 +40,7 @@ class VLiveIE(InfoExtractor):
             webpage, 'video params')
         status, _, _, live_params, long_video_id, key = re.split(
             r'"\s*,\s*"', video_params)[2:8]
+        status = remove_start(status, 'PRODUCT_')
 
         if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
             live_params = self._parse_json('"%s"' % live_params, video_id)

youtube_dl/extractor/voicerepublic.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
     determine_ext,
@@ -16,13 +19,13 @@ class VoiceRepublicIE(InfoExtractor):
     _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
     _TESTS = [{
         'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
-        'md5': '0554a24d1657915aa8e8f84e15dc9353',
+        'md5': 'b9174d651323f17783000876347116e3',
         'info_dict': {
             'id': '2296',
             'display_id': 'watching-the-watchers-building-a-sousveillance-state',
             'ext': 'm4a',
             'title': 'Watching the Watchers: Building a Sousveillance State',
-            'description': 'md5:715ba964958afa2398df615809cfecb1',
+            'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
             'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
             'duration': 1800,
             'view_count': int,
@@ -52,7 +55,7 @@ class VoiceRepublicIE(InfoExtractor):
         if data:
             title = data['title']
             description = data.get('teaser')
-            talk_id = data.get('talk_id') or display_id
+            talk_id = compat_str(data.get('talk_id') or display_id)
             talk = data['talk']
             duration = int_or_none(talk.get('duration'))
             formats = [{

youtube_dl/extractor/vporn.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     parse_duration,
     str_to_int,
 )
@@ -27,7 +28,8 @@ class VpornIE(InfoExtractor):
                 'duration': 393,
                 'age_limit': 18,
                 'view_count': int,
-            }
+            },
+            'skip': 'video removed',
         },
         {
             'url': 'http://www.vporn.com/female/hana-shower/523564/',
@@ -40,7 +42,7 @@ class VpornIE(InfoExtractor):
                 'description': 'Hana showers at the bathroom.',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'uploader': 'Hmmmmm',
-                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'],
+                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
                 'duration': 588,
                 'age_limit': 18,
                 'view_count': int,
@@ -55,6 +57,10 @@ class VpornIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
+        errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!'
+        if errmsg in webpage:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
+
         title = self._html_search_regex(
             r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
         description = self._html_search_regex(

youtube_dl/extractor/vulture.py

@@ -1,69 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-import os.path
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-)
-
-
-class VultureIE(InfoExtractor):
-    IE_NAME = 'vulture.com'
-    _VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/'
-    _TEST = {
-        'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1',
-        'md5': '8d997845642a2b5152820f7257871bc8',
-        'info_dict': {
-            'id': '6GHRQL3RV7MSD1H4',
-            'ext': 'mp4',
-            'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED',
-            'uploader_id': 'Sarah',
-            'thumbnail': 're:^http://.*\.jpg$',
-            'timestamp': 1401288564,
-            'upload_date': '20140528',
-            'description': 'Uplifting and witty, as predicted.',
-            'duration': 1015,
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-
-        webpage = self._download_webpage(url, display_id)
-        query_string = self._search_regex(
-            r"queryString\s*=\s*'([^']+)'", webpage, 'query string')
-        video_id = self._search_regex(
-            r'content=([^&]+)', query_string, 'video ID')
-        query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string
-
-        query_webpage = self._download_webpage(
-            query_url, display_id, note='Downloading query page')
-        params_json = self._search_regex(
-            r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n?,\n',
-            query_webpage,
-            'player params')
-        params = json.loads(params_json)
-
-        upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T'))
-        uploader_id = params.get('user', {}).get('handle')
-
-        media_item = params['media_item']
-        title = os.path.splitext(media_item['title'])[0]
-        duration = int_or_none(media_item.get('duration_seconds'))
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'url': media_item['pipeline_xid'],
-            'title': title,
-            'timestamp': upload_timestamp,
-            'thumbnail': params.get('thumbnail_url'),
-            'uploader_id': uploader_id,
-            'description': params.get('description'),
-            'duration': duration,
-        }

youtube_dl/extractor/wdr.py

@@ -1,215 +1,236 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import itertools
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urlparse,
-)
 from ..utils import (
+    determine_ext,
+    ExtractorError,
+    js_to_json,
+    strip_jsonp,
     unified_strdate,
-    qualities,
+    update_url_query,
+    urlhandle_detect_ext,
 )
 
 
-class WDRIE(InfoExtractor):
+class WDRBaseIE(InfoExtractor):
-    _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
+    def _extract_wdr_video(self, webpage, display_id):
-    _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
+        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
+        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
+        json_metadata = self._html_search_regex(
+            r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
+            webpage, 'media link', default=None, flags=re.MULTILINE)
+
+        if not json_metadata:
+            return
+
+        media_link_obj = self._parse_json(json_metadata, display_id,
+                                          transform_source=js_to_json)
+        jsonp_url = media_link_obj['mediaObj']['url']
+
+        metadata = self._download_json(
+            jsonp_url, 'metadata', transform_source=strip_jsonp)
+
+        metadata_tracker_data = metadata['trackerData']
+        metadata_media_resource = metadata['mediaResource']
+
+        formats = []
+
+        # check if the metadata contains a direct URL to a file
+        for kind, media_resource in metadata_media_resource.items():
+            if kind not in ('dflt', 'alt'):
+                continue
+
+            for tag_name, medium_url in media_resource.items():
+                if tag_name not in ('videoURL', 'audioURL'):
+                    continue
+
+                ext = determine_ext(medium_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        medium_url, display_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls'))
+                elif ext == 'f4m':
+                    manifest_url = update_url_query(
+                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
+                    formats.extend(self._extract_f4m_formats(
+                        manifest_url, display_id, f4m_id='hds', fatal=False))
+                elif ext == 'smil':
+                    formats.extend(self._extract_smil_formats(
+                        medium_url, 'stream', fatal=False))
+                else:
+                    a_format = {
+                        'url': medium_url
+                    }
+                    if ext == 'unknown_video':
+                        urlh = self._request_webpage(
+                            medium_url, display_id, note='Determining extension')
+                        ext = urlhandle_detect_ext(urlh)
+                        a_format['ext'] = ext
+                    formats.append(a_format)
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        caption_url = metadata_media_resource.get('captionURL')
+        if caption_url:
+            subtitles['de'] = [{
+                'url': caption_url,
+                'ext': 'ttml',
+            }]
+
+        title = metadata_tracker_data['trackerClipTitle']
+
+        return {
+            'id': metadata_tracker_data.get('trackerClipId', display_id),
+            'display_id': display_id,
+            'title': title,
+            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
+            'formats': formats,
+            'subtitles': subtitles,
+            'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
+        }
+
+
+class WDRIE(WDRBaseIE):
+    _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
+    _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
+    _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
 
     _TESTS = [
         {
-            'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
+            # HDS download, MD5 is unstable
             'info_dict': {
-                'id': 'mdb-362427',
+                'id': 'mdb-1058683',
                 'ext': 'flv',
-                'title': 'Servicezeit',
+                'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
-                'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
+                'title': 'Geheimnis Aachener Dom',
-                'upload_date': '20140310',
+                'alt_title': 'Doku am Freitag',
-                'is_live': False
+                'upload_date': '20160304',
+                'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
+                'is_live': False,
+                'subtitles': {'de': [{
+                    'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
+                    'ext': 'ttml',
+                }]},
             },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Page Not Found',
         },
         {
-            'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
+            'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
+            'md5': 'f4c1f96d01cf285240f53ea4309663d8',
             'info_dict': {
-                'id': 'mdb-363194',
+                'id': 'mdb-1072000',
-                'ext': 'flv',
-                'title': 'Marga Spiegel ist tot',
-                'description': 'md5:2309992a6716c347891c045be50992e4',
-                'upload_date': '20140311',
-                'is_live': False
-            },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Page Not Found',
-        },
-        {
-            'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
-            'md5': '83e9e8fefad36f357278759870805898',
-            'info_dict': {
-                'id': 'mdb-194332',
                 'ext': 'mp3',
-                'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
+                'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
-                'description': 'md5:2309992a6716c347891c045be50992e4',
+                'title': 'Schriftstellerin Juli Zeh',
-                'upload_date': '20091129',
+                'alt_title': 'WDR 3 Gespräch am Samstag',
-                'is_live': False
+                'upload_date': '20160312',
+                'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
+                'is_live': False,
+                'subtitles': {}
             },
         },
         {
-            'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+            'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
-            'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
-            'info_dict': {
-                'id': 'mdb-478135',
-                'ext': 'mp3',
-                'title': 'Flavia Coelho: Amar é Amar',
-                'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
-                'upload_date': '20140717',
-                'is_live': False
-            },
-            'skip': 'Page Not Found',
-        },
-        {
-            'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
-            'playlist_mincount': 146,
-            'info_dict': {
-                'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
-            }
-        },
-        {
-            'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
             'info_dict': {
                 'id': 'mdb-103364',
-                'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'ext': 'mp4',
+                'display_id': 'index',
+                'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'alt_title': 'WDR Fernsehen Live',
+                'upload_date': None,
                 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
-                'ext': 'flv',
+                'is_live': True,
-                'upload_date': '20150101',
+                'subtitles': {}
-                'is_live': True
             },
             'params': {
-                'skip_download': True,
+                'skip_download': True,  # m3u8 download
+            },
+        },
+        {
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
+            'playlist_mincount': 8,
+            'info_dict': {
+                'id': 'aktuelle-stunde/aktuelle-stunde-120',
+            },
+        },
+        {
+            'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
+            'info_dict': {
+                'id': 'mdb-1096487',
+                'ext': 'flv',
+                'upload_date': 're:^[0-9]{8}$',
+                'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
+                'description': '- Die Sendung mit der Maus -',
+            },
+            'skip': 'The id changes from week to week because of the new episode'
+        },
+        {
+            'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
+            'md5': '803138901f6368ee497b4d195bb164f2',
+            'info_dict': {
+                'id': 'mdb-186083',
+                'ext': 'mp4',
+                'upload_date': '20130919',
+                'title': 'Sachgeschichte - Achterbahn ',
+                'description': '- Die Sendung mit der Maus -',
+            },
+        },
+        {
+            'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
+            # Live stream, MD5 unstable
+            'info_dict': {
+                'id': 'mdb-869971',
+                'ext': 'flv',
+                'title': 'Funkhaus Europa Livestream',
+                'description': 'md5:2309992a6716c347891c045be50992e4',
+                'upload_date': '20160101',
             },
         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        page_url = mobj.group('url')
+        url_type = mobj.group('type')
-        page_id = mobj.group('id')
+        page_url = mobj.group('page_url')
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id)
 
-        webpage = self._download_webpage(url, page_id)
+        info_dict = self._extract_wdr_video(webpage, display_id)
 
-        if mobj.group('player') is None:
+        if not info_dict:
             entries = [
-                self.url_result(page_url + href, 'WDR')
+                self.url_result(page_url + href[0], 'WDR')
                 for href in re.findall(
-                    r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX,
+                    r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
                     webpage)
             ]
 
             if entries:  # Playlist page
-                return self.playlist_result(entries, page_id)
+                return self.playlist_result(entries, playlist_id=display_id)
 
-            # Overview page
+            raise ExtractorError('No downloadable streams found', expected=True)
-            entries = []
-            for page_num in itertools.count(2):
-                hrefs = re.findall(
-                    r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
-                    webpage)
-                entries.extend(
-                    self.url_result(page_url + href, 'WDR')
-                    for href in hrefs)
-                next_url_m = re.search(
-                    r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
-                if not next_url_m:
-                    break
-                next_url = page_url + next_url_m.group(1)
-                webpage = self._download_webpage(
-                    next_url, page_id,
-                    note='Downloading playlist page %d' % page_num)
-            return self.playlist_result(entries, page_id)
 
-        flashvars = compat_parse_qs(self._html_search_regex(
+        is_live = url_type == 'live'
-            r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
-
-        page_id = flashvars['trackerClipId'][0]
-        video_url = flashvars['dslSrc'][0]
-        title = flashvars['trackerClipTitle'][0]
-        thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
-        is_live = flashvars.get('isLive', ['0'])[0] == '1'
 
         if is_live:
-            title = self._live_title(title)
+            info_dict.update({
-
+                'title': self._live_title(info_dict['title']),
-        if 'trackerClipAirTime' in flashvars:
+                'upload_date': None,
-            upload_date = flashvars['trackerClipAirTime'][0]
-        else:
-            upload_date = self._html_search_meta(
-                'DC.Date', webpage, 'upload date')
-
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
-
-        formats = []
-        preference = qualities(['S', 'M', 'L', 'XL'])
-
-        if video_url.endswith('.f4m'):
-            formats.extend(self._extract_f4m_formats(
-                video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id,
-                f4m_id='hds', fatal=False))
-        elif video_url.endswith('.smil'):
-            formats.extend(self._extract_smil_formats(
-                video_url, page_id, False, {
-                    'hdcore': '3.3.0',
-                    'plugin': 'aasp-3.3.0.99.43',
-                }))
-        else:
-            formats.append({
-                'url': video_url,
-                'http_headers': {
-                    'User-Agent': 'mobile',
-                },
             })
+        elif 'upload_date' not in info_dict:
+            info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
 
-        m3u8_url = self._search_regex(
+        info_dict.update({
-            r'rel="adaptiv"[^>]+href="([^"]+)"',
+            'description': self._html_search_meta('Description', webpage),
-            webpage, 'm3u8 url', default=None)
+            'is_live': is_live,
-        if m3u8_url:
+        })
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, page_id, 'mp4', 'm3u8_native',
-                m3u8_id='hls', fatal=False))
 
-        direct_urls = re.findall(
+        return info_dict
-            r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
-        if direct_urls:
-            for quality, video_url in direct_urls:
-                formats.append({
-                    'url': video_url,
-                    'preference': preference(quality),
-                    'http_headers': {
-                        'User-Agent': 'mobile',
-                    },
-                })
-
-        self._sort_formats(formats)
-
-        description = self._html_search_meta('Description', webpage, 'description')
-
-        return {
-            'id': page_id,
-            'formats': formats,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-            'is_live': is_live
-        }
 
 
 class WDRMobileIE(InfoExtractor):
@@ -241,81 +262,3 @@ class WDRMobileIE(InfoExtractor):
                 'User-Agent': 'mobile',
             },
         }
-
-
-class WDRMausIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
-    IE_DESC = 'Sendung mit der Maus'
-    _TESTS = [{
-        'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
-        'info_dict': {
-            'id': 'aktuelle-sendung',
-            'ext': 'mp4',
-            'thumbnail': 're:^http://.+\.jpg',
-            'upload_date': 're:^[0-9]{8}$',
-            'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
-        }
-    }, {
-        'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
-        'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
-        'info_dict': {
-            'id': '40_jahre_maus',
-            'ext': 'mp4',
-            'thumbnail': 're:^http://.+\.jpg',
-            'upload_date': '20131007',
-            'title': '12.03.2011 - 40 Jahre Maus',
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        param_code = self._html_search_regex(
-            r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
-
-        title_date = self._search_regex(
-            r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
-            webpage, 'air date')
-        title_str = self._html_search_regex(
-            r'<h1>(.*?)</h1>', webpage, 'title')
-        title = '%s - %s' % (title_date, title_str)
-        upload_date = unified_strdate(
-            self._html_search_meta('dc.date', webpage))
-
-        fields = compat_parse_qs(param_code)
-        video_url = fields['firstVideo'][0]
-        thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
-
-        formats = [{
-            'format_id': 'rtmp',
-            'url': video_url,
-        }]
-
-        jscode = self._download_webpage(
-            'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
-            video_id, fatal=False,
-            note='Downloading URL translation table',
-            errnote='Could not download URL translation table')
-        if jscode:
-            for m in re.finditer(
-                    r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
-                    jscode):
-                if video_url.startswith(m.group('stream')):
-                    http_url = video_url.replace(
-                        m.group('stream'), m.group('dl'))
-                    formats.append({
-                        'format_id': 'http',
-                        'url': http_url,
-                    })
-                    break
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-        }

youtube_dl/extractor/weibo.py

@@ -1,49 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class WeiboIE(InfoExtractor):
-    """
-    The videos in Weibo come from different sites, this IE just finds the link
-    to the external video and returns it.
-    """
-    _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
-
-    _TEST = {
-        'url': 'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
-        'info_dict': {
-            'id': '98322879',
-            'ext': 'flv',
-            'title': '魔声耳机最新广告“All Eyes On Us”',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'add_ie': ['Sina'],
-    }
-
-    # Additional example videos from different sites
-    # Youku: http://video.weibo.com/v/weishipin/t_zQGDWQ8.htm
-    # 56.com: http://video.weibo.com/v/weishipin/t_zQ44HxN.htm
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
-        video_id = mobj.group('id')
-        info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id
-        info = self._download_json(info_url, video_id)
-
-        videos_urls = map(lambda v: v['play_page_url'], info['result']['data'])
-        # Prefer sina video since they have thumbnails
-        videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u)
-        player_url = videos_urls[-1]
-        m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html',
-                          player_url)
-        if m_sina is not None:
-            self.to_screen('Sina video detected')
-            sina_id = m_sina.group(1)
-            player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id
-        return self.url_result(player_url)

youtube_dl/extractor/wimp.py

@@ -1,29 +1,33 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
 from .youtube import YoutubeIE
+from .jwplatform import JWPlatformBaseIE
 
 
-class WimpIE(InfoExtractor):
+class WimpIE(JWPlatformBaseIE):
     _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
     _TESTS = [{
-        'url': 'http://www.wimp.com/maruexhausted/',
+        'url': 'http://www.wimp.com/maru-is-exhausted/',
         'md5': 'ee21217ffd66d058e8b16be340b74883',
         'info_dict': {
-            'id': 'maruexhausted',
+            'id': 'maru-is-exhausted',
             'ext': 'mp4',
             'title': 'Maru is exhausted.',
             'description': 'md5:57e099e857c0a4ea312542b684a869b8',
         }
     }, {
         'url': 'http://www.wimp.com/clowncar/',
-        'md5': '4e2986c793694b55b37cf92521d12bb4',
+        'md5': '5c31ad862a90dc5b1f023956faec13fe',
         'info_dict': {
-            'id': 'clowncar',
+            'id': 'cG4CEr2aiSg',
             'ext': 'webm',
-            'title': 'It\'s like a clown car.',
+            'title': 'Basset hound clown car...incredible!',
-            'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2',
+            'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom',
+            'upload_date': '20140303',
+            'uploader': 'Gretchen Hoey',
+            'uploader_id': 'gretchenandjeff1',
         },
+        'add_ie': ['Youtube'],
     }]
 
     def _real_extract(self, url):
@@ -41,14 +45,13 @@ class WimpIE(InfoExtractor):
                 'ie_key': YoutubeIE.ie_key(),
             }
 
-        video_url = self._search_regex(
+        info_dict = self._extract_jwplayer_data(
-            r'<video[^>]+>\s*<source[^>]+src=(["\'])(?P<url>.+?)\1',
+            webpage, video_id, require_title=False)
-            webpage, 'video URL', group='url')
 
-        return {
+        info_dict.update({
             'id': video_id,
-            'url': video_url,
             'title': self._og_search_title(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
-        }
+        })
+
+        return info_dict

youtube_dl/extractor/wrzuta.py

@@ -5,8 +5,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
     qualities,
+    remove_start,
 )
 
 
@@ -26,16 +28,17 @@ class WrzutaIE(InfoExtractor):
             'uploader_id': 'laboratoriumdextera',
             'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
         },
+        'skip': 'Redirected to wrzuta.pl',
     }, {
-        'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty',
+        'url': 'http://vexling.wrzuta.pl/audio/01xBFabGXu6/james_horner_-_into_the_na_39_vi_world_bonus',
-        'md5': 'bc78077859bea7bcfe4295d7d7fc9025',
+        'md5': 'f80564fb5a2ec6ec59705ae2bf2ba56d',
         'info_dict': {
-            'id': '063jOPX5ue2',
+            'id': '01xBFabGXu6',
-            'ext': 'ogg',
+            'ext': 'mp3',
-            'title': 'Liber & Natalia Szroeder - Teraz Ty',
+            'title': 'James Horner - Into The Na\'vi World [Bonus]',
-            'duration': 203,
+            'description': 'md5:30a70718b2cd9df3120fce4445b0263b',
-            'uploader_id': 'jolka85',
+            'duration': 95,
-            'description': 'md5:2d2b6340f9188c8c4cd891580e481096',
+            'uploader_id': 'vexling',
         },
     }]
 
@@ -45,7 +48,10 @@ class WrzutaIE(InfoExtractor):
         typ = mobj.group('typ')
         uploader = mobj.group('uploader')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        if urlh.geturl() == 'http://www.wrzuta.pl/':
+            raise ExtractorError('Video removed', expected=True)
 
         quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
 
@@ -80,3 +86,73 @@ class WrzutaIE(InfoExtractor):
             'description': self._og_search_description(webpage),
             'age_limit': embedpage.get('minimalAge', 0),
         }
+
+
+class WrzutaPlaylistIE(InfoExtractor):
+    """
+        this class covers extraction of wrzuta playlist entries
+        the extraction process bases on following steps:
+        * collect information of playlist size
+        * download all entries provided on
+          the playlist webpage (the playlist is split
+          on two pages: first directly reached from webpage
+          second: downloaded on demand by ajax call and rendered
+          using the ajax call response)
+        * in case size of extracted entries not reached total number of entries
+          use the ajax call to collect the remaining entries
+    """
+
+    IE_NAME = 'wrzuta.pl:playlist'
+    _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
+        'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR/moja_muza',
+        'playlist_mincount': 14,
+        'info_dict': {
+            'id': '7XfO4vE84iR',
+            'title': 'Moja muza',
+        },
+    }, {
+        'url': 'http://heroesf70.wrzuta.pl/playlista/6Nj3wQHx756/lipiec_-_lato_2015_muzyka_swiata',
+        'playlist_mincount': 144,
+        'info_dict': {
+            'id': '6Nj3wQHx756',
+            'title': 'Lipiec - Lato 2015 Muzyka Świata',
+        },
+    }, {
+        'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        uploader = mobj.group('uploader')
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_size = int_or_none(self._html_search_regex(
+            (r'<div[^>]+class=["\']playlist-counter["\'][^>]*>\d+/(\d+)',
+             r'<div[^>]+class=["\']all-counter["\'][^>]*>(.+?)</div>'),
+            webpage, 'playlist size', default=None))
+
+        playlist_title = remove_start(
+            self._og_search_title(webpage), 'Playlista: ')
+
+        entries = []
+        if playlist_size:
+            entries = [
+                self.url_result(entry_url)
+                for _, entry_url in re.findall(
+                    r'<a[^>]+href=(["\'])(http.+?)\1[^>]+class=["\']playlist-file-page',
+                    webpage)]
+            if playlist_size > len(entries):
+                playlist_content = self._download_json(
+                    'http://%s.wrzuta.pl/xhr/get_playlist_offset/%s' % (uploader, playlist_id),
+                    playlist_id,
+                    'Downloading playlist JSON',
+                    'Unable to download playlist JSON')
+                entries.extend([
+                    self.url_result(entry['filelink'])
+                    for entry in playlist_content.get('files', []) if entry.get('filelink')])
+
+        return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/xfileshare.py

@@ -5,8 +5,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    decode_packed_codes,
     ExtractorError,
     int_or_none,
+    NO_DEFAULT,
     sanitized_Request,
     urlencode_postdata,
 )
@@ -23,20 +25,24 @@ class XFileShareIE(InfoExtractor):
         ('thevideobee.to', 'TheVideoBee'),
         ('vidto.me', 'Vidto'),
         ('streamin.to', 'Streamin.To'),
+        ('xvidstage.com', 'XVIDSTAGE'),
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                   % '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
 
-    _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
+    _FILE_NOT_FOUND_REGEXES = (
+        r'>(?:404 - )?File Not Found<',
+        r'>The file was removed by administrator<',
+    )
 
     _TESTS = [{
         'url': 'http://gorillavid.in/06y9juieqpmi',
         'md5': '5ae4a3580620380619678ee4875893ba',
         'info_dict': {
             'id': '06y9juieqpmi',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
             'thumbnail': 're:http://.*\.jpg',
         },
@@ -62,7 +68,8 @@ class XFileShareIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
             'thumbnail': 're:http://.*\.jpg',
-        }
+        },
+        'skip': 'Video removed',
     }, {
         'url': 'http://vidto.me/ku5glz52nqe1.html',
         'info_dict': {
@@ -77,6 +84,17 @@ class XFileShareIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Big Buck Bunny trailer',
         },
+    }, {
+        'url': 'http://xvidstage.com/e0qcnl03co6z',
+        'info_dict': {
+            'id': 'e0qcnl03co6z',
+            'ext': 'mp4',
+            'title': 'Chucky Prank 2015.mp4',
+        },
+    }, {
+        # removed by administrator
+        'url': 'http://xvidstage.com/amfy7atlkx25',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -86,7 +104,7 @@ class XFileShareIE(InfoExtractor):
         url = 'http://%s/%s' % (mobj.group('host'), video_id)
         webpage = self._download_webpage(url, video_id)
 
-        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+        if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         fields = self._hidden_inputs(webpage)
@@ -112,10 +130,23 @@ class XFileShareIE(InfoExtractor):
              r'>Watch (.+) ',
              r'<h2 class="video-page-head">([^<]+)</h2>'],
             webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
-        video_url = self._search_regex(
+
-            [r'file\s*:\s*["\'](http[^"\']+)["\'],',
+        def extract_video_url(default=NO_DEFAULT):
-             r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
+            return self._search_regex(
-            webpage, 'file url')
+                (r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
+                 r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
+                 r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
+                 r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
+                webpage, 'file url', default=default, group='url')
+
+        video_url = extract_video_url(default=None)
+
+        if not video_url:
+            webpage = decode_packed_codes(self._search_regex(
+                r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
+                webpage, 'packed code'))
+            video_url = extract_video_url()
+
         thumbnail = self._search_regex(
             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 

youtube_dl/extractor/xuite.py

@@ -66,6 +66,7 @@ class XuiteIE(InfoExtractor):
             'uploader_id': '242127761',
             'categories': ['電玩動漫'],
         },
+        'skip': 'Video removed',
     }, {
         'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
         'only_matching': True,

youtube_dl/extractor/yahoo.py

@@ -343,7 +343,7 @@ class YahooIE(InfoExtractor):
             webpage, 'region', fatal=False, default='US')
         data = compat_urllib_parse_urlencode({
             'protocol': 'http',
-            'region': region,
+            'region': region.upper(),
         })
         query_url = (
             'https://video.media.yql.yahoo.com/v1/video/sapi/streams/'

youtube_dl/extractor/youku.py

@@ -2,7 +2,9 @@
 from __future__ import unicode_literals
 
 import base64
+import itertools
 import random
+import re
 import string
 import time
 
@@ -13,6 +15,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    get_element_by_attribute,
     sanitized_Request,
 )
 
@@ -285,3 +288,52 @@ class YoukuIE(InfoExtractor):
             'title': title,
             'entries': entries,
         }
+
+
+class YoukuShowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
+    IE_NAME = 'youku:show'
+
+    _TEST = {
+        'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
+        'info_dict': {
+            'id': 'zc7c670be07ff11e48b3f',
+            'title': '花千骨 未删减版',
+            'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
+        },
+        'playlist_count': 50,
+    }
+
+    _PAGE_SIZE = 40
+
+    def _find_videos_in_page(self, webpage):
+        videos = re.findall(
+            r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
+        return [
+            self.url_result(video_url, YoukuIE.ie_key(), title)
+            for video_url, title in videos]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        entries = self._find_videos_in_page(webpage)
+
+        playlist_title = self._html_search_regex(
+            r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
+        detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
+        playlist_description = self._html_search_regex(
+            r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
+            detail_div, 'playlist description', fatal=False)
+
+        for idx in itertools.count(1):
+            episodes_page = self._download_webpage(
+                'http://www.youku.com/show_episode/id_%s.html' % show_id,
+                show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
+                note='Downloading episodes page %d' % idx)
+            new_entries = self._find_videos_in_page(episodes_page)
+            entries.extend(new_entries)
+            if len(new_entries) < self._PAGE_SIZE:
+                break
+
+        return self.playlist_result(entries, show_id, playlist_title, playlist_description)

youtube_dl/extractor/youporn.py

@@ -17,7 +17,7 @@ class YouPornIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
-        'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
+        'md5': '3744d24c50438cf5b6f6d59feb5055c2',
         'info_dict': {
             'id': '505835',
             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
@@ -121,21 +121,21 @@ class YouPornIE(InfoExtractor):
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         uploader = self._html_search_regex(
-            r'(?s)<div[^>]+class=["\']videoInfoBy(?:\s+[^"\']+)?["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
+            r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
-            r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
+            r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
             webpage, 'upload date', fatal=False))
 
         age_limit = self._rta_search(webpage)
 
         average_rating = int_or_none(self._search_regex(
-            r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
+            r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
             webpage, 'average rating', fatal=False))
 
         view_count = str_to_int(self._search_regex(
-            r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
+            r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
-            webpage, 'view count', fatal=False))
+            webpage, 'view count', fatal=False, group='count'))
         comment_count = str_to_int(self._search_regex(
             r'>All [Cc]omments? \(([\d,.]+)\)',
             webpage, 'comment count', fatal=False))

youtube_dl/extractor/youtube.py

@@ -344,6 +344,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
         '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
+        '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
+        '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
 
         # Dash webm
         '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
@@ -1986,7 +1988,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
 
 class YoutubeUserIE(YoutubeChannelIE):
     IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
-    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
+    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/|c/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
     _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
     IE_NAME = 'youtube:user'
 
@@ -1999,6 +2001,9 @@ class YoutubeUserIE(YoutubeChannelIE):
     }, {
         'url': 'ytuser:phihag',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtube.com/c/gametrailers',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/options.py

@@ -668,7 +668,7 @@ def parseOpts(overrideArguments=None):
         action='store_true', dest='writeannotations', default=False,
         help='Write video annotations to a .annotations.xml file')
     filesystem.add_option(
-        '--load-info',
+        '--load-info-json', '--load-info',
         dest='load_info_filename', metavar='FILE',
         help='JSON file containing the video information (created with the "--write-info-json" option)')
     filesystem.add_option(

youtube_dl/utils.py

@@ -39,6 +39,7 @@ from .compat import (
     compat_chr,
     compat_etree_fromstring,
     compat_html_entities,
+    compat_html_entities_html5,
     compat_http_client,
     compat_kwargs,
     compat_parse_qs,
@@ -75,7 +76,7 @@ def register_socks_protocols():
 compiled_regex_type = type(re.compile(''))
 
 std_headers = {
-    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)',
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/47.0 (Chrome)',
     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Encoding': 'gzip, deflate',
@@ -456,12 +457,19 @@ def orderedSet(iterable):
     return res
 
 
-def _htmlentity_transform(entity):
+def _htmlentity_transform(entity_with_semicolon):
     """Transforms an HTML entity to a character."""
+    entity = entity_with_semicolon[:-1]
+
     # Known non-numeric HTML entity
     if entity in compat_html_entities.name2codepoint:
         return compat_chr(compat_html_entities.name2codepoint[entity])
 
+    # TODO: HTML5 allows entities without a semicolon. For example,
+    # '&Eacuteric' should be decoded as 'Éric'.
+    if entity_with_semicolon in compat_html_entities_html5:
+        return compat_html_entities_html5[entity_with_semicolon]
+
     mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
     if mobj is not None:
         numstr = mobj.group(1)
@@ -486,7 +494,7 @@ def unescapeHTML(s):
     assert type(s) == compat_str
 
     return re.sub(
-        r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
+        r'&([^;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
 def get_subprocess_encoding():
@@ -1893,6 +1901,16 @@ def dict_get(d, key_or_keys, default=None, skip_false_values=True):
     return d.get(key_or_keys, default)
 
 
+def try_get(src, getter, expected_type=None):
+    try:
+        v = getter(src)
+    except (AttributeError, KeyError, TypeError, IndexError):
+        pass
+    else:
+        if expected_type is None or isinstance(v, expected_type):
+            return v
+
+
 def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
     return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
 
@@ -1952,7 +1970,7 @@ def js_to_json(code):
         '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
         /\*.*?\*/|,(?=\s*[\]}])|
         [a-zA-Z_][.a-zA-Z_0-9]*|
-        (?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:\s*:)?|
+        \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:\s*:)?|
         [0-9]+(?=\s*:)
         ''', fix_kv, code)
 
@@ -2020,6 +2038,9 @@ def mimetype2ext(mt):
 
     ext = {
         'audio/mp4': 'm4a',
+        # Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
+        # it's the most popular one
+        'audio/mpeg': 'mp3',
     }.get(mt)
     if ext is not None:
         return ext
@@ -2831,3 +2852,12 @@ def decode_packed_codes(code):
     return re.sub(
         r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
         obfucasted_code)
+
+
+def parse_m3u8_attributes(attrib):
+    info = {}
+    for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib):
+        if val.startswith('"'):
+            val = val[1:-1]
+        info[key] = val
+    return info

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.06.03'
+__version__ = '2016.06.20'