Merge branch 'master' into NBC-issue-13873

.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 *2017.09.02*. 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 Issues with outdated version will be rejected.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 *2017.09.11*. 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 Issues with outdated version will be rejected.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 **2017.09.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.09.11**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2017.09.02
+[debug] youtube-dl version 2017.09.11
 [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: {}

CONTRIBUTING.md

@@ -82,6 +82,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file
     python test/test_download.py
     nosetests
 
+See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases.
+
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
@@ -149,7 +151,7 @@ After you have ensured this site is distributing its content legally, you can fo
             }
     ```
 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.
+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. Note that tests with `only_matching` key in test's dict are not counted in.
 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. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
 9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:

ChangeLog

@@ -1,3 +1,38 @@
+version 2017.09.11
+
+Extractors
+* [rutube:playlist] Fix suitable (#14166)
+
+
+version 2017.09.10
+
+Core
++ [utils] Introduce bool_or_none
+* [YoutubeDL] Ensure dir existence for each requested format (#14116)
+
+Extractors
+* [fox] Fix extraction (#14147)
+* [rutube] Use bool_or_none
+* [rutube] Rework and generalize playlist extractors (#13565)
++ [rutube:playlist] Add support for playlists (#13534, #13565)
++ [radiocanada] Add fallback for title extraction (#14145)
+* [vk] Use dedicated YouTube embeds extraction routine
+* [vice] Use dedicated YouTube embeds extraction routine
+* [cracked] Use dedicated YouTube embeds extraction routine
+* [chilloutzone] Use dedicated YouTube embeds extraction routine
+* [abcnews] Use dedicated YouTube embeds extraction routine
+* [youtube] Separate methods for embeds extraction
+* [redtube] Fix formats extraction (#14122)
+* [arte] Relax unavailability check (#14112)
++ [manyvids] Add support for preview videos from manyvids.com (#14053, #14059)
+* [vidme:user] Relax URL regular expression (#14054)
+* [bpb] Fix extraction (#14043, #14086)
+* [soundcloud] Fix download URL with private tracks (#14093)
+* [aliexpress:live] Add support for live.aliexpress.com (#13698, #13707)
+* [viidea] Capture and output lecture error message (#14099)
+* [radiocanada] Skip unsupported platforms (#14100)
+
+
 version 2017.09.02
 
 Extractors

docs/supportedsites.md

@@ -38,6 +38,7 @@
  - **afreecatv**: afreecatv.com
  - **afreecatv:global**: afreecatv.com
  - **AirMozilla**
+ - **AliExpressLive**
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
@@ -437,6 +438,7 @@
  - **MakerTV**
  - **mangomolo:live**
  - **mangomolo:video**
+ - **ManyVids**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -701,6 +703,7 @@
  - **rutube:embed**: Rutube embedded videos
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
+ - **rutube:playlist**: Rutube playlists
  - **RUTV**: RUTV.RU
  - **Ruutu**
  - **Ruv**

youtube_dl/extractor/animeondemand.py

@@ -3,16 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
+from ..compat import compat_str
-    compat_urlparse,
-    compat_str,
-)
 from ..utils import (
     determine_ext,
     extract_attributes,
     ExtractorError,
-    sanitized_Request,
     urlencode_postdata,
+    urljoin,
 )
 
 
@@ -21,6 +18,8 @@ class AnimeOnDemandIE(InfoExtractor):
     _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
     _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
     _NETRC_MACHINE = 'animeondemand'
+    # German-speaking countries of Europe
+    _GEO_COUNTRIES = ['AT', 'CH', 'DE', 'LI', 'LU']
     _TESTS = [{
         # jap, OmU
         'url': 'https://www.anime-on-demand.de/anime/161',
@@ -46,6 +45,10 @@ class AnimeOnDemandIE(InfoExtractor):
         # Full length film, non-series, ger/jap, Dub/OmU, account required
         'url': 'https://www.anime-on-demand.de/anime/185',
         'only_matching': True,
+    }, {
+        # Flash videos
+        'url': 'https://www.anime-on-demand.de/anime/12',
+        'only_matching': True,
     }]
 
     def _login(self):
@@ -72,14 +75,13 @@ class AnimeOnDemandIE(InfoExtractor):
             'post url', default=self._LOGIN_URL, group='url')
 
         if not post_url.startswith('http'):
-            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+            post_url = urljoin(self._LOGIN_URL, post_url)
-
-        request = sanitized_Request(
-            post_url, urlencode_postdata(login_form))
-        request.add_header('Referer', self._LOGIN_URL)
 
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            post_url, None, 'Logging in as %s' % username,
+            data=urlencode_postdata(login_form), headers={
+                'Referer': self._LOGIN_URL,
+            })
 
         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
             error = self._search_regex(
@@ -120,10 +122,11 @@ class AnimeOnDemandIE(InfoExtractor):
             formats = []
 
             for input_ in re.findall(
-                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html):
+                    r'<input[^>]+class=["\'].*?streamstarter[^>]+>', html):
                 attributes = extract_attributes(input_)
+                title = attributes.get('data-dialog-header')
                 playlist_urls = []
-                for playlist_key in ('data-playlist', 'data-otherplaylist'):
+                for playlist_key in ('data-playlist', 'data-otherplaylist', 'data-stream'):
                     playlist_url = attributes.get(playlist_key)
                     if isinstance(playlist_url, compat_str) and re.match(
                             r'/?[\da-zA-Z]+', playlist_url):
@@ -147,19 +150,38 @@ class AnimeOnDemandIE(InfoExtractor):
                         format_id_list.append(compat_str(num))
                     format_id = '-'.join(format_id_list)
                     format_note = ', '.join(filter(None, (kind, lang_note)))
-                    request = sanitized_Request(
+                    item_id_list = []
-                        compat_urlparse.urljoin(url, playlist_url),
+                    if format_id:
+                        item_id_list.append(format_id)
+                    item_id_list.append('videomaterial')
+                    playlist = self._download_json(
+                        urljoin(url, playlist_url), video_id,
+                        'Downloading %s JSON' % ' '.join(item_id_list),
                         headers={
                             'X-Requested-With': 'XMLHttpRequest',
                             'X-CSRF-Token': csrf_token,
                             'Referer': url,
                             'Accept': 'application/json, text/javascript, */*; q=0.01',
-                        })
+                        }, fatal=False)
-                    playlist = self._download_json(
-                        request, video_id, 'Downloading %s playlist JSON' % format_id,
-                        fatal=False)
                     if not playlist:
                         continue
+                    stream_url = playlist.get('streamurl')
+                    if stream_url:
+                        rtmp = re.search(
+                            r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',
+                            stream_url)
+                        if rtmp:
+                            formats.append({
+                                'url': rtmp.group('url'),
+                                'app': rtmp.group('app'),
+                                'play_path': rtmp.group('playpath'),
+                                'page_url': url,
+                                'player_url': 'https://www.anime-on-demand.de/assets/jwplayer.flash-55abfb34080700304d49125ce9ffb4a6.swf',
+                                'rtmp_real_time': True,
+                                'format_id': 'rtmp',
+                                'ext': 'flv',
+                            })
+                            continue
                     start_video = playlist.get('startvideo', 0)
                     playlist = playlist.get('playlist')
                     if not playlist or not isinstance(playlist, list):
@@ -222,7 +244,7 @@ class AnimeOnDemandIE(InfoExtractor):
                     f.update({
                         'id': '%s-%s' % (f['id'], m.group('kind').lower()),
                         'title': m.group('title'),
-                        'url': compat_urlparse.urljoin(url, m.group('href')),
+                        'url': urljoin(url, m.group('href')),
                     })
                     entries.append(f)
 

youtube_dl/extractor/extractors.py

@@ -899,6 +899,7 @@ from .rutube import (
     RutubeEmbedIE,
     RutubeMovieIE,
     RutubePersonIE,
+    RutubePlaylistIE,
 )
 from .rutv import RUTVIE
 from .ruutu import RuutuIE

youtube_dl/extractor/fox.py

@@ -3,56 +3,99 @@ from __future__ import unicode_literals
 
 from .adobepass import AdobePassIE
 from ..utils import (
-    smuggle_url,
+    int_or_none,
-    update_url_query,
+    parse_age_limit,
+    parse_duration,
+    try_get,
+    unified_timestamp,
 )
 
 
 class FOXIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
-    _TEST = {
+    _TESTS = [{
-        'url': 'http://www.fox.com/watch/255180355939/7684182528',
+        # clip
+        'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
         'info_dict': {
-            'id': '255180355939',
+            'id': '4b765a60490325103ea69888fb2bd4e8',
             'ext': 'mp4',
-            'title': 'Official Trailer: Gotham',
+            'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
-            'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
+            'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
-            'duration': 129,
+            'duration': 102,
-            'timestamp': 1400020798,
+            'timestamp': 1504291893,
-            'upload_date': '20140513',
+            'upload_date': '20170901',
-            'uploader': 'NEWA-FNG-FOXCOM',
+            'creator': 'FOX',
+            'series': 'Gotham',
         },
-        'add_ie': ['ThePlatform'],
+        'params': {
-    }
+            'skip_download': True,
+        },
+    }, {
+        # episode, geo-restricted
+        'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
+        'only_matching': True,
+    }, {
+        # episode, geo-restricted, tv provided required
+        'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
 
-        settings = self._parse_json(self._search_regex(
+        video = self._download_json(
-            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+            'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
-            webpage, 'drupal settings'), video_id)
+            video_id, headers={
-        fox_pdk_player = settings['fox_pdk_player']
+                'apikey': 'abdcbed02c124d393b39e818a4312055',
-        release_url = fox_pdk_player['release_url']
+                'Content-Type': 'application/json',
-        query = {
+                'Referer': url,
-            'mbr': 'true',
+            })
-            'switch': 'http'
-        }
-        if fox_pdk_player.get('access') == 'locked':
-            ap_p = settings['foxAdobePassProvider']
-            rating = ap_p.get('videoRating')
-            if rating == 'n/a':
-                rating = None
-            resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
 
-        info = self._search_json_ld(webpage, video_id, fatal=False)
+        title = video['name']
-        info.update({
+
-            '_type': 'url_transparent',
+        m3u8_url = self._download_json(
-            'ie_key': 'ThePlatform',
+            video['videoRelease']['url'], video_id)['playURL']
-            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        description = video.get('description')
+        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+            video.get('duration')) or parse_duration(video.get('duration'))
+        timestamp = unified_timestamp(video.get('datePublished'))
+        age_limit = parse_age_limit(video.get('contentRating'))
+
+        data = try_get(
+            video, lambda x: x['trackingData']['properties'], dict) or {}
+
+        creator = data.get('brand') or data.get('network') or video.get('network')
+
+        series = video.get('seriesName') or data.get(
+            'seriesName') or data.get('show')
+        season_number = int_or_none(video.get('seasonNumber'))
+        episode = video.get('name')
+        episode_number = int_or_none(video.get('episodeNumber'))
+        release_year = int_or_none(video.get('releaseYear'))
+
+        if data.get('authRequired'):
+            # TODO: AP
+            pass
+
+        return {
             'id': video_id,
-        })
+            'title': title,
-
+            'description': description,
-        return info
+            'duration': duration,
+            'timestamp': timestamp,
+            'age_limit': age_limit,
+            'creator': creator,
+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'release_year': release_year,
+            'formats': formats,
+        }

youtube_dl/extractor/rutube.py

@@ -7,43 +7,84 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     determine_ext,
-    unified_strdate,
+    bool_or_none,
+    int_or_none,
+    try_get,
+    unified_timestamp,
 )
 
 
-class RutubeIE(InfoExtractor):
+class RutubeBaseIE(InfoExtractor):
+    def _extract_video(self, video, video_id=None, require_title=True):
+        title = video['title'] if require_title else video.get('title')
+
+        age_limit = video.get('is_adult')
+        if age_limit is not None:
+            age_limit = 18 if age_limit is True else 0
+
+        uploader_id = try_get(video, lambda x: x['author']['id'])
+        category = try_get(video, lambda x: x['category']['name'])
+
+        return {
+            'id': video.get('id') or video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': video.get('thumbnail_url'),
+            'duration': int_or_none(video.get('duration')),
+            'uploader': try_get(video, lambda x: x['author']['name']),
+            'uploader_id': compat_str(uploader_id) if uploader_id else None,
+            'timestamp': unified_timestamp(video.get('created_ts')),
+            'category': [category] if category else None,
+            'age_limit': age_limit,
+            'view_count': int_or_none(video.get('hits')),
+            'comment_count': int_or_none(video.get('comments_count')),
+            'is_live': bool_or_none(video.get('is_livestream')),
+        }
+
+
+class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'
     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'md5': '79938ade01294ef7e27574890d0d3769',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
+            'timestamp': 1381943602,
             'upload_date': '20131016',
             'age_limit': 0,
         },
-        'params': {
-            # It requires ffmpeg (m3u8 download)
-            'skip_download': True,
-        },
     }, {
         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
+    }, {
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
+        'only_matching': True,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
+
     @staticmethod
     def _extract_urls(webpage):
         return [mobj.group('url') for mobj in re.finditer(
@@ -52,12 +93,12 @@ class RutubeIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
 
-        # Some videos don't have the author field
+        info = self._extract_video(video, video_id)
-        author = video.get('author') or {}
 
         options = self._download_json(
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
@@ -79,19 +120,8 @@ class RutubeIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
-        return {
+        info['formats'] = formats
-            'id': video['id'],
+        return info
-            'title': video['title'],
-            'description': video['description'],
-            'duration': video['duration'],
-            'view_count': video['hits'],
-            'formats': formats,
-            'thumbnail': video['thumbnail_url'],
-            'uploader': author.get('name'),
-            'uploader_id': compat_str(author['id']) if author else None,
-            'upload_date': unified_strdate(video['created_ts']),
-            'age_limit': 18 if video['is_adult'] else 0,
-        }
 
 
 class RutubeEmbedIE(InfoExtractor):
@@ -103,7 +133,8 @@ class RutubeEmbedIE(InfoExtractor):
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
-            'ext': 'mp4',
+            'ext': 'flv',
+            'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
@@ -111,7 +142,7 @@ class RutubeEmbedIE(InfoExtractor):
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
         },
         'params': {
-            'skip_download': 'Requires ffmpeg',
+            'skip_download': True,
         },
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',
@@ -125,10 +156,51 @@ class RutubeEmbedIE(InfoExtractor):
         canonical_url = self._html_search_regex(
             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
             'Canonical URL')
-        return self.url_result(canonical_url, 'Rutube')
+        return self.url_result(canonical_url, RutubeIE.ie_key())
 
 
-class RutubeChannelIE(InfoExtractor):
+class RutubePlaylistBaseIE(RutubeBaseIE):
+    def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
+        return self._PAGE_TEMPLATE % (playlist_id, page_num)
+
+    def _entries(self, playlist_id, *args, **kwargs):
+        next_page_url = None
+        for pagenum in itertools.count(1):
+            page = self._download_json(
+                next_page_url or self._next_page_url(
+                    pagenum, playlist_id, *args, **kwargs),
+                playlist_id, 'Downloading page %s' % pagenum)
+
+            results = page.get('results')
+            if not results or not isinstance(results, list):
+                break
+
+            for result in results:
+                video_url = result.get('video_url')
+                if not video_url or not isinstance(video_url, compat_str):
+                    continue
+                entry = self._extract_video(result, require_title=False)
+                entry.update({
+                    '_type': 'url',
+                    'url': video_url,
+                    'ie_key': RutubeIE.ie_key(),
+                })
+                yield entry
+
+            next_page_url = page.get('next')
+            if not next_page_url or not page.get('has_next'):
+                break
+
+    def _extract_playlist(self, playlist_id, *args, **kwargs):
+        return self.playlist_result(
+            self._entries(playlist_id, *args, **kwargs),
+            playlist_id, kwargs.get('playlist_name'))
+
+    def _real_extract(self, url):
+        return self._extract_playlist(self._match_id(url))
+
+
+class RutubeChannelIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
@@ -142,27 +214,8 @@ class RutubeChannelIE(InfoExtractor):
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
-    def _extract_videos(self, channel_id, channel_title=None):
-        entries = []
-        for pagenum in itertools.count(1):
-            page = self._download_json(
-                self._PAGE_TEMPLATE % (channel_id, pagenum),
-                channel_id, 'Downloading page %s' % pagenum)
-            results = page['results']
-            if not results:
-                break
-            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
-            if not page['has_next']:
-                break
-        return self.playlist_result(entries, channel_id, channel_title)
 
-    def _real_extract(self, url):
+class RutubeMovieIE(RutubePlaylistBaseIE):
-        mobj = re.match(self._VALID_URL, url)
-        channel_id = mobj.group('id')
-        return self._extract_videos(channel_id)
-
-
-class RutubeMovieIE(RutubeChannelIE):
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
@@ -176,11 +229,11 @@ class RutubeMovieIE(RutubeChannelIE):
         movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')
-        movie_name = movie['name']
+        return self._extract_playlist(
-        return self._extract_videos(movie_id, movie_name)
+            movie_id, playlist_name=movie.get('name'))
 
 
-class RutubePersonIE(RutubeChannelIE):
+class RutubePersonIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
@@ -193,3 +246,37 @@ class RutubePersonIE(RutubeChannelIE):
     }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+
+
+class RutubePlaylistIE(RutubePlaylistBaseIE):
+    IE_NAME = 'rutube:playlist'
+    IE_DESC = 'Rutube playlists'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
+        'info_dict': {
+            'id': '3097',
+        },
+        'playlist_count': 27,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
+        'only_matching': True,
+    }]
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
+
+    @classmethod
+    def suitable(cls, url):
+        if not super(RutubePlaylistIE, cls).suitable(url):
+            return False
+        params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
+
+    def _next_page_url(self, page_num, playlist_id, item_kind):
+        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
+
+    def _real_extract(self, url):
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        playlist_kind = qs['pl_type'][0]
+        playlist_id = qs['pl_id'][0]
+        return self._extract_playlist(playlist_id, item_kind=playlist_kind)

youtube_dl/utils.py

@@ -1815,6 +1815,10 @@ def float_or_none(v, scale=1, invscale=1, default=None):
         return default
 
 
+def bool_or_none(v, default=None):
+    return v if isinstance(v, bool) else default
+
+
 def strip_or_none(v):
     return None if v is None else v.strip()
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.09.02'
+__version__ = '2017.09.11'