Merge branch 'master' of github.com:rg3/youtube-dl into mixcloud-play-info

AUTHORS

@@ -146,3 +146,4 @@ Lukáš Lalinský
 Qijiang Fan
 Rémy Léone
 Marco Ferragina
+reiv

Makefile

@@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
+	COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
-	python devscripts/make_contributing.py README.md CONTRIBUTING.md
+	$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
 
 supportedsites:
-	python devscripts/make_supportedsites.py docs/supportedsites.md
+	$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
 
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
 	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
 	rm -f youtube-dl.1.temp.md
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
-	python devscripts/bash-completion.py
+	$(PYTHON) devscripts/bash-completion.py
 
 bash-completion: youtube-dl.bash-completion
 
 youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
-	python devscripts/zsh-completion.py
+	$(PYTHON) devscripts/zsh-completion.py
 
 zsh-completion: youtube-dl.zsh
 
 youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
-	python devscripts/fish-completion.py
+	$(PYTHON) devscripts/fish-completion.py
 
 fish-completion: youtube-dl.fish
 

README.md

@@ -319,7 +319,8 @@ which means you can modify it, redistribute it or use it however you like.
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific
                                      one is requested
-    -F, --list-formats               List all available formats
+    -F, --list-formats               List all available formats of requested
+                                     videos
     --youtube-skip-dash-manifest     Do not download the DASH manifests and
                                      related data on YouTube videos
     --merge-output-format FORMAT     If a merge is required (e.g.

docs/supportedsites.md

@@ -15,8 +15,12 @@
  - **abc.net.au**
  - **Abc7News**
  - **AcademicEarth:Course**
+ - **acast**
+ - **acast:channel**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVChannel**
+ - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
@@ -43,6 +47,7 @@
  - **arte.tv:future**
  - **AtresPlayer**
  - **ATTTechChannel**
+ - **AudiMedia**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
@@ -92,6 +97,7 @@
  - **Clipfish**
  - **cliphunter**
  - **Clipsyndicate**
+ - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
  - **Clyp**
@@ -183,6 +189,7 @@
  - **freespeech.org**
  - **FreeVideo**
  - **FunnyOrDie**
+ - **GameInformer**
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
@@ -307,7 +314,6 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
- - **movshare**: MovShare
  - **MPORA**
  - **MSNBC**
  - **MTV**
@@ -480,6 +486,8 @@
  - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
  - **Sina**
+ - **skynewsarabia:video**
+ - **skynewsarabia:video**
  - **Slideshare**
  - **Slutload**
  - **smotri**: Smotri.com
@@ -665,6 +673,7 @@
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
  - **Weibo**
+ - **wholecloud**: WholeCloud
  - **Wimp**
  - **Wistia**
  - **WNL**

youtube_dl/downloader/hls.py

@@ -13,6 +13,7 @@ from ..utils import (
     encodeArgument,
     encodeFilename,
     sanitize_open,
+    handle_youtubedl_headers,
 )
 
 
@@ -33,9 +34,10 @@ class HlsFD(FileDownloader):
         if info_dict['http_headers'] and re.match(r'^https?://', url):
             # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
             # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+            headers = handle_youtubedl_headers(info_dict['http_headers'])
             args += [
                 '-headers',
-                ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
+                ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
 
         args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
 

youtube_dl/extractor/__init__.py

@@ -3,9 +3,15 @@ from __future__ import unicode_literals
 from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
+from .acast import (
+    ACastIE,
+    ACastChannelIE,
+)
 from .addanime import AddAnimeIE
 from .adobetv import (
     AdobeTVIE,
+    AdobeTVShowIE,
+    AdobeTVChannelIE,
     AdobeTVVideoIE,
 )
 from .adultswim import AdultSwimIE
@@ -38,6 +44,7 @@ from .arte import (
 )
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
+from .audimedia import AudiMediaIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
 from .baidu import BaiduVideoIE
@@ -200,6 +207,7 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .freevideo import FreeVideoIE
 from .funnyordie import FunnyOrDieIE
+from .gameinformer import GameInformerIE
 from .gamekings import GamekingsIE
 from .gameone import (
     GameOneIE,
@@ -349,7 +357,6 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
-from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
     MTVServicesEmbeddedIE,
@@ -415,7 +422,13 @@ from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .nova import NovaIE
-from .novamov import NovaMovIE
+from .novamov import (
+    NovaMovIE,
+    WholeCloudIE,
+    NowVideoIE,
+    VideoWeedIE,
+    CloudTimeIE,
+)
 from .nowness import (
     NownessIE,
     NownessPlaylistIE,
@@ -425,7 +438,6 @@ from .nowtv import (
     NowTVIE,
     NowTVListIE,
 )
-from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
     NPOLiveIE,
@@ -554,6 +566,10 @@ from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
+from .skynewsarabia import (
+    SkyNewsArabiaIE,
+    SkyNewsArabiaArticleIE,
+)
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
 from .smotri import (
@@ -732,7 +748,6 @@ from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
-from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE

youtube_dl/extractor/acast.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class ACastBaseIE(InfoExtractor):
+    _API_BASE_URL = 'https://www.acast.com/api/'
+
+
+class ACastIE(ACastBaseIE):
+    IE_NAME = 'acast'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
+        'md5': 'ada3de5a1e3a2a381327d749854788bb',
+        'info_dict': {
+            'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
+            'ext': 'mp3',
+            'title': '"Where Are You?": Taipei 101, Taiwan',
+            'timestamp': 1196172000000,
+            'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e',
+            'duration': 211,
+        }
+    }
+
+    def _real_extract(self, url):
+        channel, display_id = re.match(self._VALID_URL, url).groups()
+        cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id)
+
+        return {
+            'id': compat_str(cast_data['id']),
+            'display_id': display_id,
+            'url': cast_data['blings'][0]['audio'],
+            'title': cast_data['name'],
+            'description': cast_data.get('description'),
+            'thumbnail': cast_data.get('image'),
+            'timestamp': int_or_none(cast_data.get('publishingDate')),
+            'duration': int_or_none(cast_data.get('duration')),
+        }
+
+
+class ACastChannelIE(ACastBaseIE):
+    IE_NAME = 'acast:channel'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler',
+        'info_dict': {
+            'id': '50544219-29bb-499e-a083-6087f4cb7797',
+            'title': 'Condé Nast Traveler Podcast',
+            'description': 'md5:98646dee22a5b386626ae31866638fbd',
+        },
+        'playlist_mincount': 20,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
+        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
+        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+
+        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))

youtube_dl/extractor/adobetv.py

@@ -1,23 +1,32 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
+    int_or_none,
     float_or_none,
     ISO639Utils,
+    determine_ext,
 )
 
 
-class AdobeTVIE(InfoExtractor):
+class AdobeTVBaseIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
+    _API_BASE_URL = 'http://tv.adobe.com/api/v4/'
+
+
+class AdobeTVIE(AdobeTVBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
         'info_dict': {
-            'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
+            'id': '10981',
             'ext': 'mp4',
             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
@@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        language, show_urlname, urlname = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(url, video_id)
+        if not language:
+            language = 'en'
 
-        player = self._parse_json(
+        video_data = self._download_json(
-            self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
+            self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
-            video_id)
+            urlname)['data'][0]
-
-        title = player.get('title') or self._search_regex(
-            r'data-title="([^"]+)"', webpage, 'title')
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-
-        upload_date = unified_strdate(
-            self._html_search_meta('datepublished', webpage, 'upload date'))
-
-        duration = parse_duration(
-            self._html_search_meta('duration', webpage, 'duration') or
-            self._search_regex(
-                r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
-                webpage, 'duration', fatal=False))
-
-        view_count = str_to_int(self._search_regex(
-            r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
-            webpage, 'view count'))
 
         formats = [{
-            'url': source['src'],
+            'url': source['url'],
-            'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
+            'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
-            'tbr': source.get('bitrate'),
+            'width': int_or_none(source.get('width')),
-        } for source in player['sources']]
+            'height': int_or_none(source.get('height')),
+            'tbr': int_or_none(source.get('video_data_rate')),
+        } for source in video_data['videos']]
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
+            'id': compat_str(video_data['id']),
-            'title': title,
+            'title': video_data['title'],
-            'description': description,
+            'description': video_data.get('description'),
-            'thumbnail': thumbnail,
+            'thumbnail': video_data.get('thumbnail'),
-            'upload_date': upload_date,
+            'upload_date': unified_strdate(video_data.get('start_date')),
-            'duration': duration,
+            'duration': parse_duration(video_data.get('duration')),
-            'view_count': view_count,
+            'view_count': str_to_int(video_data.get('playcount')),
             'formats': formats,
         }
 
 
+class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
+    def _parse_page_data(self, page_data):
+        return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
+
+    def _extract_playlist_entries(self, url, display_id):
+        page = self._download_json(url, display_id)
+        entries = self._parse_page_data(page['data'])
+        for page_num in range(2, page['paging']['pages'] + 1):
+            entries.extend(self._parse_page_data(
+                self._download_json(url + '&page=%d' % page_num, display_id)['data']))
+        return entries
+
+
+class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
+        'info_dict': {
+            'id': '36',
+            'title': 'The Complete Picture with Julieanne Kost',
+            'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
+        },
+        'playlist_mincount': 136,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['urls'][0]
+
+    def _real_extract(self, url):
+        language, show_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&show_urlname=%s' % (language, show_urlname)
+
+        show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
+            compat_str(show_data['id']),
+            show_data['show_name'],
+            show_data['show_description'])
+
+
+class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/channel/development',
+        'info_dict': {
+            'id': 'development',
+        },
+        'playlist_mincount': 96,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['url']
+
+    def _real_extract(self, url):
+        language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
+        if category_urlname:
+            query += '&category_urlname=%s' % category_urlname
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
+            channel_urlname)
+
+
 class AdobeTVVideoIE(InfoExtractor):
     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
 
@@ -91,28 +156,25 @@ 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)
-
-        player_params = self._parse_json(self._search_regex(
-            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
-            video_id)
 
         formats = [{
+            'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
             'url': source['src'],
-            'width': source.get('width'),
+            'width': int_or_none(source.get('width')),
-            'height': source.get('height'),
+            'height': int_or_none(source.get('height')),
-            'tbr': source.get('bitrate'),
+            'tbr': int_or_none(source.get('bitrate')),
-        } for source in player_params['sources']]
+        } for source in video_data['sources']]
+        self._sort_formats(formats)
 
         # For both metadata and downloaded files the duration varies among
         # formats. I just pick the max one
         duration = max(filter(None, [
             float_or_none(source.get('duration'), scale=1000)
-            for source in player_params['sources']]))
+            for source in video_data['sources']]))
 
         subtitles = {}
-        for translation in player_params.get('translations', []):
+        for translation in video_data.get('translations', []):
             lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
             if lang_id not in subtitles:
                 subtitles[lang_id] = []
@@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'title': player_params['title'],
+            'title': video_data['title'],
-            'description': self._og_search_description(webpage),
+            'description': video_data.get('description'),
+            'thumbnail': video_data['video'].get('poster'),
             'duration': duration,
             'subtitles': subtitles,
         }

youtube_dl/extractor/audimedia.py

@@ -0,0 +1,80 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    sanitized_Request,
+)
+
+
+class AudiMediaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
+        'md5': '79a8b71c46d49042609795ab59779b66',
+        'info_dict': {
+            'id': '1564',
+            'ext': 'mp4',
+            'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
+            'description': 'md5:60e5d30a78ced725f7b8d34370762941',
+            'upload_date': '20151124',
+            'timestamp': 1448354940,
+            'duration': 74022,
+            'view_count': int,
+        }
+    }
+    # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
+    _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload')
+        _, stage_mode, video_id, lang = raw_payload.split('-')
+
+        # TODO: handle s and e stage_mode (live streams and ended live streams)
+        if stage_mode not in ('s', 'e'):
+            request = sanitized_Request(
+                'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
+                headers={'X-Auth-Token': self._AUTH_TOKEN})
+            json_data = self._download_json(request, video_id)['results']
+            formats = []
+
+            stream_url_hls = json_data.get('stream_url_hls')
+            if stream_url_hls:
+                m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+
+            stream_url_hds = json_data.get('stream_url_hds')
+            if stream_url_hds:
+                f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+
+            for video_version in json_data.get('video_versions'):
+                video_version_url = video_version.get('download_url') or video_version.get('stream_url')
+                if not video_version_url:
+                    continue
+                formats.append({
+                    'url': video_version_url,
+                    'width': int_or_none(video_version.get('width')),
+                    'height': int_or_none(video_version.get('height')),
+                    'abr': int_or_none(video_version.get('audio_bitrate')),
+                    'vbr': int_or_none(video_version.get('video_bitrate')),
+                })
+            self._sort_formats(formats)
+
+            return {
+                'id': video_id,
+                'title': json_data['title'],
+                'description': json_data.get('subtitle'),
+                'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
+                'timestamp': parse_iso8601(json_data.get('publication_date')),
+                'duration': int_or_none(json_data.get('duration')),
+                'view_count': int_or_none(json_data.get('view_count')),
+                'formats': formats,
+            }

youtube_dl/extractor/bbc.py

@@ -22,7 +22,8 @@ from ..compat import (
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
+    _ID_REGEX = r'[pb][\da-z]{7}'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
@@ -46,9 +47,8 @@ class BBCCoUkIE(InfoExtractor):
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope, Leonard Cohen',
+                'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
                 'description': 'The Canadian poet and songwriter reflects on his musical career.',
-                'duration': 1740,
             },
             'params': {
                 # rtmp download
@@ -111,7 +111,8 @@ class BBCCoUkIE(InfoExtractor):
             'params': {
                 # rtmp download
                 'skip_download': True,
-            }
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
         }, {
             'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
             'note': 'Audio',
@@ -453,6 +454,7 @@ class BBCCoUkIE(InfoExtractor):
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
         programme_id = None
+        duration = None
 
         tviplayer = self._search_regex(
             r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
@@ -465,14 +467,16 @@ class BBCCoUkIE(InfoExtractor):
 
         if not programme_id:
             programme_id = self._search_regex(
-                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+                r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
 
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
                 r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
-                webpage, 'description', fatal=False)
+                webpage, 'description', default=None)
+            if not description:
+                description = self._html_search_meta('description', webpage)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -586,6 +590,7 @@ class BBCIE(BBCCoUkIE):
             'ext': 'mp4',
             'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
             'duration': 56,
+            'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
         },
         'params': {
             'skip_download': True,
@@ -728,6 +733,7 @@ class BBCIE(BBCCoUkIE):
         # article with multiple videos embedded with playlist.sxml (e.g.
         # http://www.bbc.com/sport/0/football/34475836)
         playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
+        playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
         if playlists:
             entries = [
                 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
@@ -780,8 +786,9 @@ class BBCIE(BBCCoUkIE):
 
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
         programme_id = self._search_regex(
-            [r'data-video-player-vpid="([\da-z]{8})"',
+            [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
-             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+             r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
+             r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
             webpage, 'vpid', default=None)
 
         if programme_id:
@@ -816,7 +823,7 @@ class BBCIE(BBCCoUkIE):
 
         # Multiple video article (e.g.
         # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
-        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
         entries = []
         for match in extract_all(r'new\s+SMP\(({.+?})\)'):
             embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')

youtube_dl/extractor/beeg.py

@@ -1,6 +1,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_chr,
+    compat_ord,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
     int_or_none,
     parse_iso8601,
@@ -29,7 +34,24 @@ class BeegIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://beeg.com/api/v1/video/%s' % video_id, video_id)
+            'http://beeg.com/api/v4/video/%s' % video_id, video_id)
+
+        def decrypt_key(key):
+            # Reverse engineered from http://static.beeg.com/cpl/1067.js
+            a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo'
+            e = compat_urllib_parse_unquote(key)
+            return ''.join([
+                compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25)
+                for n in range(len(e))])
+
+        def decrypt_url(encrypted_url):
+            encrypted_url = self._proto_relative_url(
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
+            key = self._search_regex(
+                r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
+            if not key:
+                return encrypted_url
+            return encrypted_url.replace(key, decrypt_key(key))
 
         formats = []
         for format_id, video_url in video.items():
@@ -40,7 +62,7 @@ class BeegIE(InfoExtractor):
             if not height:
                 continue
             formats.append({
-                'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
+                'url': decrypt_url(video_url),
                 'format_id': format_id,
                 'height': int(height),
             })

youtube_dl/extractor/bilibili.py

@@ -2,143 +2,109 @@
 from __future__ import unicode_literals
 
 import re
-import itertools
-import json
 
 from .common import InfoExtractor
-from ..compat import (
+from ..compat import compat_str
-    compat_etree_fromstring,
-)
 from ..utils import (
     int_or_none,
-    unified_strdate,
+    unescapeHTML,
     ExtractorError,
+    xpath_text,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402_part1',
+            'id': '1554319',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
-            'duration': 308,
+            'duration': 308313,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
+            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
+            'timestamp': 1397983878,
+            'uploader': '菊子桑',
         },
     }, {
         'url': 'http://www.bilibili.com/video/av1041170/',
         'info_dict': {
             'id': '1041170',
             'title': '【BD1080P】刀语【诸神&异域】',
+            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
+            'uploader': '枫叶逝去',
+            'timestamp': 1396501299,
         },
         'playlist_count': 9,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
-        webpage = self._download_webpage(url, video_id)
+        video_id = mobj.group('id')
+        page_num = mobj.group('page_num') or '1'
 
-        if '(此视频不存在或被删除)' in webpage:
+        view_data = self._download_json(
-            raise ExtractorError(
+            'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
-                'The video does not exist or was deleted', expected=True)
+            video_id)
+        if 'error' in view_data:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
 
-        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
+        cid = view_data['cid']
-            raise ExtractorError(
+        title = unescapeHTML(view_data['title'])
-                'The video is not available in your region due to copyright reasons',
-                expected=True)
 
-        video_code = self._search_regex(
+        doc = self._download_xml(
-            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+            'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
+            cid,
+            'Downloading page %s/%s' % (page_num, view_data['pages'])
+        )
 
-        title = self._html_search_meta(
+        if xpath_text(doc, './result') == 'error':
-            'media:title', video_code, 'title', fatal=True)
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
-        duration_str = self._html_search_meta(
-            'duration', video_code, 'duration')
-        if duration_str is None:
-            duration = None
-        else:
-            duration_mobj = re.match(
-                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
-                duration_str)
-            duration = (
-                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
-                int(duration_mobj.group('minutes')) * 60 +
-                int(duration_mobj.group('seconds')))
-        upload_date = unified_strdate(self._html_search_meta(
-            'uploadDate', video_code, fatal=False))
-        thumbnail = self._html_search_meta(
-            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
-
-        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
         entries = []
 
-        lq_page = self._download_webpage(
+        for durl in doc.findall('./durl'):
-            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
+            size = xpath_text(durl, ['./filesize', './size'])
-            video_id,
-            note='Downloading LQ video info'
-        )
-        try:
-            err_info = json.loads(lq_page)
-            raise ExtractorError(
-                'BiliBili said: ' + err_info['error_text'], expected=True)
-        except ValueError:
-            pass
-
-        lq_doc = compat_etree_fromstring(lq_page)
-        lq_durls = lq_doc.findall('./durl')
-
-        hq_doc = self._download_xml(
-            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
-            video_id,
-            note='Downloading HQ video info',
-            fatal=False,
-        )
-        if hq_doc is not False:
-            hq_durls = hq_doc.findall('./durl')
-            assert len(lq_durls) == len(hq_durls)
-        else:
-            hq_durls = itertools.repeat(None)
-
-        i = 1
-        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
             formats = [{
-                'format_id': 'lq',
+                'url': durl.find('./url').text,
-                'quality': 1,
+                'filesize': int_or_none(size),
-                'url': lq_durl.find('./url').text,
+                'ext': 'flv',
-                'filesize': int_or_none(
-                    lq_durl.find('./size'), get_attr='text'),
             }]
-            if hq_durl is not None:
+            backup_urls = durl.find('./backup_url')
-                formats.append({
+            if backup_urls is not None:
-                    'format_id': 'hq',
+                for backup_url in backup_urls.findall('./url'):
-                    'quality': 2,
+                    formats.append({'url': backup_url.text})
-                    'ext': 'flv',
+            formats.reverse()
-                    'url': hq_durl.find('./url').text,
-                    'filesize': int_or_none(
-                        hq_durl.find('./size'), get_attr='text'),
-                })
-            self._sort_formats(formats)
 
             entries.append({
-                'id': '%s_part%d' % (video_id, i),
+                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
                 'title': title,
+                'duration': int_or_none(xpath_text(durl, './length'), 1000),
                 'formats': formats,
-                'duration': duration,
-                'upload_date': upload_date,
-                'thumbnail': thumbnail,
             })
 
-            i += 1
+        info = {
-
+            'id': compat_str(cid),
-        return {
+            'title': title,
-            '_type': 'multi_video',
+            'description': view_data.get('description'),
-            'entries': entries,
+            'thumbnail': view_data.get('pic'),
-            'id': video_id,
+            'uploader': view_data.get('author'),
-            'title': title
+            'timestamp': int_or_none(view_data.get('created')),
+            'view_count': int_or_none(view_data.get('play')),
+            'duration': int_or_none(xpath_text(doc, './timelength')),
         }
+
+        if len(entries) == 1:
+            entries[0].update(info)
+            return entries[0]
+        else:
+            info.update({
+                '_type': 'multi_video',
+                'id': video_id,
+                'entries': entries,
+            })
+            return info

youtube_dl/extractor/bloomberg.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
 
     _TESTS = [{
         'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
@@ -20,22 +20,36 @@ class BloombergIE(InfoExtractor):
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,
+    }, {
+        'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
+        video_id = self._search_regex(
+            r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'id', group='url')
         title = re.sub(': Video$', '', self._og_search_title(webpage))
 
         embed_info = self._download_json(
             'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
         formats = []
         for stream in embed_info['streams']:
-            if stream["muxing_format"] == "TS":
+            stream_url = stream.get('url')
-                formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
+            if not stream_url:
+                continue
+            if stream['muxing_format'] == 'TS':
+                m3u8_formats = self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
             else:
-                formats.extend(self._extract_f4m_formats(stream['url'], video_id))
+                f4m_formats = self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/byutv.py

@@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor):
         'info_dict': {
             'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:5438d33774b6bdc662f9485a340401cc',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
-            'thumbnail': 're:^https?://.*\.jpg$'
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1486.486,
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/clipfish.py

@@ -1,14 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     int_or_none,
-    js_to_json,
+    unified_strdate,
-    parse_iso8601,
-    remove_end,
 )
 
 
@@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor):
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
-            'timestamp': 1370938118,
+            'description': 'Video zu FIFA 14: E3 2013 Trailer',
             'upload_date': '20130611',
             'duration': 82,
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        video_info = self._download_json(
-
+            'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id,
-        video_info = self._parse_json(
+            video_id)['items'][0]
-            js_to_json(self._html_search_regex(
-                '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
-            video_id)
 
         formats = []
-        for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
-            ext = determine_ext(video_url)
-            if ext == 'm3u8':
-                formats.append({
-                    'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
-                    'ext': 'mp4',
-                    'format_id': 'hls',
-                })
-            else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': ext,
-                })
-        self._sort_formats(formats)
 
-        title = remove_end(self._og_search_title(webpage), ' - Video')
+        m3u8_url = video_info.get('media_videourl_hls')
-        thumbnail = self._og_search_thumbnail(webpage)
+        if m3u8_url:
-        duration = int_or_none(video_info.get('length'))
+            formats.append({
-        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
+                'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                'ext': 'mp4',
+                'format_id': 'hls',
+            })
+
+        mp4_url = video_info.get('media_videourl')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'mp4',
+                'width': int_or_none(video_info.get('width')),
+                'height': int_or_none(video_info.get('height')),
+                'tbr': int_or_none(video_info.get('bitrate')),
+            })
 
         return {
             'id': video_id,
-            'title': title,
+            'title': video_info['title'],
+            'description': video_info.get('descr'),
             'formats': formats,
-            'thumbnail': thumbnail,
+            'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
-            'duration': duration,
+            'duration': int_or_none(video_info.get('media_length')),
-            'timestamp': timestamp,
+            'upload_date': unified_strdate(video_info.get('pubDate')),
+            'view_count': int_or_none(video_info.get('media_views'))
         }

youtube_dl/extractor/common.py

@@ -167,7 +167,7 @@ class InfoExtractor(object):
                     "ext" will be calculated from URL if missing
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
-    duration:       Length of the video in seconds, as an integer.
+    duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video

youtube_dl/extractor/cspan.py

@@ -9,6 +9,7 @@ from ..utils import (
     find_xpath_attr,
     smuggle_url,
     determine_ext,
+    ExtractorError,
 )
 from .senateisvp import SenateISVPIE
 
@@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor):
     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
-        'md5': '8e44ce11f0f725527daccc453f553eb0',
+        'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
             'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
-        # For whatever reason, the served video alternates between
+        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
-        # two different ones
         'info_dict': {
-            'id': '340723',
+            'id': 'c4486943',
             'ext': 'mp4',
-            'title': 'International Health Care Models',
+            'title': 'CSPAN - International Health Care Models',
             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
-        'md5': '446562a736c6bf97118e389433ed88d4',
+        'md5': '2ae5051559169baadba13fc35345ae74',
         'info_dict': {
             'id': '342759',
             'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
             'duration': 14848,
-            'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
+            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
         },
     }, {
         # Video from senate.gov
@@ -57,67 +57,77 @@ class CSpanIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        page_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
-        webpage = self._download_webpage(url, page_id)
+        matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
-        video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
+        if matches:
+            video_type, video_id = matches.groups()
+            if video_type == 'prog':
+                video_type = 'program'
+        else:
+            senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+            if senate_isvp_url:
+                title = self._og_search_title(webpage)
+                surl = smuggle_url(senate_isvp_url, {'force_title': title})
+                return self.url_result(surl, 'SenateISVP', video_id, title)
 
-        description = self._html_search_regex(
+        def get_text_attr(d, attr):
-            [
+            return d.get(attr, {}).get('#text')
-                # The full description
-                r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
-                # If the description is small enough the other div is not
-                # present, otherwise this is a stripped version
-                r'<p class=\'initial\'>(.*?)</p>'
-            ],
-            webpage, 'description', flags=re.DOTALL, default=None)
 
-        info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
+        data = self._download_json(
-        data = self._download_json(info_url, video_id)
+            'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
+            video_id)['video']
+        if data['@status'] != 'Success':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
 
         doc = self._download_xml(
-            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+            'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
             video_id)
 
+        description = self._html_search_meta('description', webpage)
+
         title = find_xpath_attr(doc, './/string', 'name', 'title').text
         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
 
-        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+        files = data['files']
-        if senate_isvp_url:
+        capfile = get_text_attr(data, 'capfile')
-            surl = smuggle_url(senate_isvp_url, {'force_title': title})
-            return self.url_result(surl, 'SenateISVP', video_id, title)
 
-        files = data['video']['files']
+        entries = []
-        try:
+        for partnum, f in enumerate(files):
-            capfile = data['video']['capfile']['#text']
+            formats = []
-        except KeyError:
+            for quality in f['qualities']:
-            capfile = None
+                formats.append({
-
+                    'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
-        entries = [{
+                    'url': unescapeHTML(get_text_attr(quality, 'file')),
-            'id': '%s_%d' % (video_id, partnum + 1),
+                    'height': int_or_none(get_text_attr(quality, 'height')),
-            'title': (
+                    'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
-                title if len(files) == 1 else
+                })
-                '%s part %d' % (title, partnum + 1)),
+            self._sort_formats(formats)
-            'url': unescapeHTML(f['path']['#text']),
+            entries.append({
-            'description': description,
+                'id': '%s_%d' % (video_id, partnum + 1),
-            'thumbnail': thumbnail,
+                'title': (
-            'duration': int_or_none(f.get('length', {}).get('#text')),
+                    title if len(files) == 1 else
-            'subtitles': {
+                    '%s part %d' % (title, partnum + 1)),
-                'en': [{
+                'formats': formats,
-                    'url': capfile,
+                'description': description,
-                    'ext': determine_ext(capfile, 'dfxp')
+                'thumbnail': thumbnail,
-                }],
+                'duration': int_or_none(get_text_attr(f, 'length')),
-            } if capfile else None,
+                'subtitles': {
-        } for partnum, f in enumerate(files)]
+                    'en': [{
+                        'url': capfile,
+                        'ext': determine_ext(capfile, 'dfxp')
+                    }],
+                } if capfile else None,
+            })
 
         if len(entries) == 1:
             entry = dict(entries[0])
-            entry['id'] = video_id
+            entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
             return entry
         else:
             return {
                 '_type': 'playlist',
                 'entries': entries,
                 'title': title,
-                'id': video_id,
+                'id': 'c' + video_id if video_type == 'clip' else video_id,
             }

youtube_dl/extractor/dbtv.py

@@ -13,8 +13,8 @@ from ..utils import (
 
 
 class DBTVIE(InfoExtractor):
-    _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
         'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
         'info_dict': {
@@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor):
             'view_count': int,
             'categories': list,
         }
-    }
+    }, {
+        'url': 'http://dbtv.no/3649835190001',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
         data = self._download_json(
             'http://api.dbtv.no/discovery/%s' % video_id, display_id)

youtube_dl/extractor/facebook.py

@@ -164,7 +164,7 @@ class FacebookIE(InfoExtractor):
         if not video_title:
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
-                webpage, 'alternative title', fatal=False)
+                webpage, 'alternative title', default=None)
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id

youtube_dl/extractor/fc2.py

@@ -37,8 +37,8 @@ class FC2IE(InfoExtractor):
         'params': {
             'username': 'ytdl@yt-dl.org',
             'password': '(snip)',
-            'skip': 'requires actual password'
+        },
-        }
+        'skip': 'requires actual password',
     }, {
         'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
         'only_matching': True,

youtube_dl/extractor/gameinformer.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class GameInformerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx'
+    _TEST = {
+        'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
+        'info_dict': {
+            'id': '4515472681001',
+            'ext': 'm3u8',
+            'title': 'Replay - Animal Crossing',
+            'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
+            'timestamp': 1443457610706,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url')
+        json_data = self._download_json(
+            bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions',
+            display_id)
+
+        return {
+            'id': compat_str(json_data['id']),
+            'display_id': display_id,
+            'url': json_data['IOSRenditions'][0]['url'],
+            'title': json_data['name'],
+            'description': json_data.get('shortDescription'),
+            'timestamp': int_or_none(json_data.get('publishedDate')),
+            'duration': int_or_none(json_data.get('length')),
+        }

youtube_dl/extractor/gametrailers.py

@@ -1,19 +1,62 @@
 from __future__ import unicode_literals
 
-from .mtv import MTVServicesInfoExtractor
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_age_limit,
+    url_basename,
+)
 
 
-class GametrailersIE(MTVServicesInfoExtractor):
+class GametrailersIE(InfoExtractor):
-    _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+    _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
+
     _TEST = {
-        'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
+        'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
-        'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
+        'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a',
         'info_dict': {
-            'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
+            'id': '2983958',
             'ext': 'mp4',
-            'title': 'E3 2013: Debut Trailer',
+            'display_id': '116437-Just-Cause-3-Review',
-            'description': 'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
+            'title': 'Just Cause 3 - Review',
+            'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?',
         },
     }
 
-    _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.+?)\|', webpage, 'title').strip()
+        embed_url = self._proto_relative_url(
+            self._search_regex(
+                r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage,
+                'embed url'),
+            scheme='http:')
+        video_id = url_basename(embed_url)
+        embed_page = self._download_webpage(embed_url, video_id)
+        embed_vars_json = self._search_regex(
+            r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page,
+            'embed vars')
+        info = self._parse_json(embed_vars_json, video_id)
+
+        formats = []
+        for media in info['media']:
+            if media['mediaPurpose'] == 'play':
+                formats.append({
+                    'url': media['uri'],
+                    'height': media['height'],
+                    'width:': media['width'],
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': info.get('thumbUri'),
+            'description': self._og_search_description(webpage),
+            'duration': int_or_none(info.get('videoLengthInSeconds')),
+            'age_limit': parse_age_limit(info.get('audienceRating')),
+        }

youtube_dl/extractor/generic.py

@@ -339,6 +339,7 @@ class GenericIE(InfoExtractor):
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                 'ext': 'mp4',
                 'title': '2cc213299525360.mov',  # that's what we get
+                'duration': 238.231,
             },
             'add_ie': ['Ooyala'],
         },
@@ -350,6 +351,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': '"Steve Jobs: Man in the Machine" trailer',
                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
+                'duration': 135.427,
             },
             'params': {
                 'skip_download': True,
@@ -960,8 +962,9 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
                 'ext': 'mp4',
-                'description': 'VIDEO: Index/Match versus VLOOKUP.',
+                'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
                 'title': 'This is what separates the Excel masters from the wannabes',
+                'duration': 191.933,
             },
             'params': {
                 # m3u8 downloads
@@ -1501,7 +1504,7 @@ class GenericIE(InfoExtractor):
                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(mobj.group('ec'))
+            return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
 
         # Look for multiple Ooyala embeds on SBN network websites
         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
@@ -1509,7 +1512,7 @@ class GenericIE(InfoExtractor):
             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
             if embeds:
                 return _playlist_from_matches(
-                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
 
         # Look for Aparat videos
         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)

youtube_dl/extractor/groupon.py

@@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor):
                 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
                 'ext': 'mp4',
                 'title': 'Bikram Yoga Huntington Beach | Orange County',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'duration': 44.961,
             },
         }],
         'params': {

youtube_dl/extractor/howcast.py

@@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor):
             'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
             'timestamp': 1276081287,
             'upload_date': '20100609',
+            'duration': 56.823,
         },
         'params': {
             # m3u8 download

youtube_dl/extractor/hypem.py

@@ -28,15 +28,12 @@ class HypemIE(InfoExtractor):
         track_id = self._match_id(url)
 
         data = {'ax': 1, 'ts': time.time()}
-        data_encoded = compat_urllib_parse.urlencode(data)
+        request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data))
-        complete_url = url + "?" + data_encoded
-        request = sanitized_Request(complete_url)
         response, urlh = self._download_webpage_handle(
             request, track_id, 'Downloading webpage with the url')
-        cookie = urlh.headers.get('Set-Cookie', '')
 
         html_tracks = self._html_search_regex(
-            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
+            r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>',
             response, 'tracks')
         try:
             track_list = json.loads(html_tracks)
@@ -46,15 +43,14 @@ class HypemIE(InfoExtractor):
 
         key = track['key']
         track_id = track['id']
-        artist = track['artist']
         title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
         request = sanitized_Request(
-            serve_url, '', {'Content-Type': 'application/json'})
+            'http://hypem.com/serve/source/%s/%s' % (track_id, key),
-        request.add_header('cookie', cookie)
+            '', {'Content-Type': 'application/json'})
         song_data = self._download_json(request, track_id, 'Downloading metadata')
-        final_url = song_data["url"]
+        final_url = song_data['url']
+        artist = track.get('artist')
 
         return {
             'id': track_id,

youtube_dl/extractor/iqiyi.py

@@ -205,9 +205,8 @@ class IqiyiIE(InfoExtractor):
 
     def get_enc_key(self, swf_url, video_id):
         # TODO: automatic key extraction
-        # last update at 2015-10-22 for Zombie::bite
+        # last update at 2015-12-06 for Zombie::bite
-        # '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
+        enc_key = '3719f6a1da83ee0aee3488d8802d7696'[::-1]
-        enc_key = '2c76de15dcb44bd28ff0927d50d31620'
         return enc_key
 
     def _real_extract(self, url):

youtube_dl/extractor/keezmovies.py

@@ -1,23 +1,25 @@
 from __future__ import unicode_literals
 
-import os
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
-from ..utils import sanitized_Request
+    sanitized_Request,
+    url_basename,
+)
 
 
 class KeezMoviesIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
-        'md5': '6e297b7e789329923fcf83abb67c9289',
+        'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
         'info_dict': {
             'id': '1214711',
             'ext': 'mp4',
             'title': 'Petite Asian Lady Mai Playing In Bathtub',
             'age_limit': 18,
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
 
@@ -36,21 +38,29 @@ class KeezMoviesIE(InfoExtractor):
 
         video_title = self._html_search_regex(
             r'<h1 [^>]*>([^<]+)', webpage, 'title')
-        video_url = self._html_search_regex(
+        flashvars = self._parse_json(self._search_regex(
-            r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
+            r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
-        path = compat_urllib_parse_urlparse(video_url).path
+
-        extension = os.path.splitext(path)[1][1:]
+        formats = []
-        format = path.split('/')[4].split('_')[:2]
+        for height in (180, 240, 480):
-        format = "-".join(format)
+            if flashvars.get('quality_%dp' % height):
+                video_url = flashvars['quality_%dp' % height]
+                a_format = {
+                    'url': video_url,
+                    'height': height,
+                    'format_id': '%dp' % height,
+                }
+                filename_parts = url_basename(video_url).split('_')
+                if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
+                    a_format['tbr'] = int(filename_parts[1][:-1])
+                formats.append(a_format)
 
         age_limit = self._rta_search(webpage)
 
         return {
             'id': video_id,
             'title': video_title,
-            'url': video_url,
+            'formats': formats,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
             'age_limit': age_limit,
+            'thumbnail': flashvars.get('image_url')
         }

youtube_dl/extractor/metacafe.py

@@ -154,10 +154,10 @@ class MetacafeIE(InfoExtractor):
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None
-        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse_unquote(mobj.group(1))
-            video_ext = mediaURL[-3:]
+            video_ext = determine_ext(mediaURL)
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
@@ -229,7 +229,7 @@ class MetacafeIE(InfoExtractor):
 
         age_limit = (
             18
-            if re.search(r'"contentRating":"restricted"', webpage)
+            if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
             else 0)
 
         if isinstance(video_url, list):

youtube_dl/extractor/mixcloud.py

@@ -79,7 +79,8 @@ class MixcloudIE(InfoExtractor):
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url', default=None)
         if preview_url is not None:
-            song_url = preview_url.replace('/previews/', '/c/originals/')
+            song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
+            song_url = song_url.replace('/previews/', '/c/originals/')
             if not self._check_url(song_url, track_id, 'mp3'):
                 song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
                 if not self._check_url(song_url, track_id, 'm4a'):

youtube_dl/extractor/movshare.py

@@ -1,27 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class MovShareIE(NovaMovIE):
-    IE_NAME = 'movshare'
-    IE_DESC = 'MovShare'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'}
-
-    _HOST = 'www.movshare.net'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
-    _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
-
-    _TEST = {
-        'url': 'http://www.movshare.net/video/559e28be54d96',
-        'md5': 'abd31a2132947262c50429e1d16c1bfd',
-        'info_dict': {
-            'id': '559e28be54d96',
-            'ext': 'flv',
-            'title': 'dissapeared image',
-            'description': 'optical illusion  dissapeared image  magic illusion',
-        }
-    }

youtube_dl/extractor/nba.py

@@ -1,63 +1,102 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
-    remove_end,
     parse_duration,
+    int_or_none,
+    xpath_text,
+    xpath_attr,
 )
 
 
 class NBAIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
+    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
     _TESTS = [{
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
+        'md5': '9e7729d3010a9c71506fd1248f74e4f4',
         'info_dict': {
-            'id': '0021200253-okc-bkn-recap.nba',
+            'id': '0021200253-okc-bkn-recap',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Thunder vs. Nets',
             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'duration': 181,
+            'timestamp': 1354638466,
+            'upload_date': '20121204',
         },
     }, {
         'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
         'only_matching': True,
     }, {
-        'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+        'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+        'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
         'info_dict': {
-            'id': '0041400301-cle-atl-recap.nba',
+            'id': '0041400301-cle-atl-recap',
             'ext': 'mp4',
-            'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1',
+            'title': 'Hawks vs. Cavaliers Game 1',
             'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
             'duration': 228,
-        },
+            'timestamp': 1432134543,
-        'params': {
+            'upload_date': '20150520',
-            'skip_download': True,
         }
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        path, video_id = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(url, video_id)
+        if path.startswith('nba/'):
+            path = path[3:]
+        video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
+        video_id = xpath_text(video_info, 'slug')
+        title = xpath_text(video_info, 'headline')
+        description = xpath_text(video_info, 'description')
+        duration = parse_duration(xpath_text(video_info, 'length'))
+        timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
 
-        video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+        thumbnails = []
+        for image in video_info.find('images'):
+            thumbnails.append({
+                'id': image.attrib.get('cut'),
+                'url': image.text,
+                'width': int_or_none(image.attrib.get('width')),
+                'height': int_or_none(image.attrib.get('height')),
+            })
 
-        shortened_video_id = video_id.rpartition('/')[2]
+        formats = []
-        title = remove_end(
+        for video_file in video_info.findall('.//file'):
-            self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
+            video_url = video_file.text
-
+            if video_url.startswith('/'):
-        description = self._og_search_description(webpage)
+                continue
-        duration_str = self._html_search_meta(
+            if video_url.endswith('.m3u8'):
-            'duration', webpage, 'duration', default=None)
+                m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False)
-        if not duration_str:
+                if m3u8_formats:
-            duration_str = self._html_search_regex(
+                    formats.extend(m3u8_formats)
-                r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False)
+            elif video_url.endswith('.f4m'):
-        duration = parse_duration(duration_str)
+                f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+            else:
+                key = video_file.attrib.get('bitrate')
+                format_info = {
+                    'format_id': key,
+                    'url': video_url,
+                }
+                mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
+                if mobj:
+                    format_info.update({
+                        'width': int(mobj.group(1)),
+                        'height': int(mobj.group(2)),
+                        'tbr': int_or_none(mobj.group(3)),
+                    })
+                formats.append(format_info)
+        self._sort_formats(formats)
 
         return {
-            'id': shortened_video_id,
+            'id': video_id,
-            'url': video_url,
             'title': title,
             'description': description,
             'duration': duration,
+            'timestamp': timestamp,
+            'thumbnails': thumbnails,
+            'formats': formats,
         }

youtube_dl/extractor/novamov.py

@@ -92,3 +92,89 @@ class NovaMovIE(InfoExtractor):
             'title': title,
             'description': description
         }
+
+
+class WholeCloudIE(NovaMovIE):
+    IE_NAME = 'wholecloud'
+    IE_DESC = 'WholeCloud'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
+
+    _HOST = 'www.wholecloud.net'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
+    _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.wholecloud.net/video/559e28be54d96',
+        'md5': 'abd31a2132947262c50429e1d16c1bfd',
+        'info_dict': {
+            'id': '559e28be54d96',
+            'ext': 'flv',
+            'title': 'dissapeared image',
+            'description': 'optical illusion  dissapeared image  magic illusion',
+        }
+    }
+
+
+class NowVideoIE(NovaMovIE):
+    IE_NAME = 'nowvideo'
+    IE_DESC = 'NowVideo'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
+
+    _HOST = 'www.nowvideo.to'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
+    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
+    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
+        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'info_dict': {
+            'id': '0mw0yow7b6dxa',
+            'ext': 'flv',
+            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'description': 'Description',
+        }
+    }
+
+
+class VideoWeedIE(NovaMovIE):
+    IE_NAME = 'videoweed'
+    IE_DESC = 'VideoWeed'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
+
+    _HOST = 'www.videoweed.es'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
+
+    _TEST = {
+        'url': 'http://www.videoweed.es/file/b42178afbea14',
+        'md5': 'abd31a2132947262c50429e1d16c1bfd',
+        'info_dict': {
+            'id': 'b42178afbea14',
+            'ext': 'flv',
+            'title': 'optical illusion  dissapeared image magic illusion',
+            'description': ''
+        },
+    }
+
+
+class CloudTimeIE(NovaMovIE):
+    IE_NAME = 'cloudtime'
+    IE_DESC = 'CloudTime'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
+
+    _HOST = 'www.cloudtime.to'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
+
+    _TEST = None

youtube_dl/extractor/nowtv.py

@@ -71,7 +71,7 @@ class NowTVBaseIE(InfoExtractor):
 
 
 class NowTVIE(NowTVBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)'
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
 
     _TESTS = [{
         # rtl
@@ -190,6 +190,9 @@ class NowTVIE(NowTVBaseIE):
     }, {
         'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
         'only_matching': True,
+    }, {
+        'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/nowvideo.py

@@ -1,28 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class NowVideoIE(NovaMovIE):
-    IE_NAME = 'nowvideo'
-    IE_DESC = 'NowVideo'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
-
-    _HOST = 'www.nowvideo.to'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
-    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
-    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
-
-    _TEST = {
-        'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
-        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
-        'info_dict': {
-            'id': '0mw0yow7b6dxa',
-            'ext': 'flv',
-            'title': 'youtubedl test video _BaW_jenozKc.mp4',
-            'description': 'Description',
-        }
-    }

youtube_dl/extractor/nrk.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     parse_duration,
@@ -48,12 +49,22 @@ class NRKIE(InfoExtractor):
             'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
             video_id, 'Downloading media JSON')
 
-        if data['usageRights']['isGeoBlocked']:
+        media_url = data.get('mediaUrl')
-            raise ExtractorError(
-                'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
-                expected=True)
 
-        video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
+        if not media_url:
+            if data['usageRights']['isGeoBlocked']:
+                raise ExtractorError(
+                    'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
+                    expected=True)
+
+        if determine_ext(media_url) == 'f4m':
+            formats = self._extract_f4m_formats(
+                media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
+        else:
+            formats = [{
+                'url': media_url,
+                'ext': 'flv',
+            }]
 
         duration = parse_duration(data.get('duration'))
 
@@ -67,12 +78,11 @@ class NRKIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
             'title': data['title'],
             'description': data['description'],
             'duration': duration,
             'thumbnail': thumbnail,
+            'formats': formats,
         }
 
 

youtube_dl/extractor/ooyala.py

@@ -1,108 +1,69 @@
 from __future__ import unicode_literals
 import re
-import json
 import base64
 
 from .common import InfoExtractor
 from ..utils import (
-    unescapeHTML,
-    ExtractorError,
-    determine_ext,
     int_or_none,
+    float_or_none,
+    ExtractorError,
+    unsmuggle_url,
 )
+from ..compat import compat_urllib_parse
 
 
 class OoyalaBaseIE(InfoExtractor):
 
-    def _extract_result(self, info, more_info):
+    def _extract(self, content_tree_url, video_id, domain='example.org'):
-        embedCode = info['embedCode']
+        content_tree = self._download_json(content_tree_url, video_id)['content_tree']
-        video_url = info.get('ipad_url') or info['url']
+        metadata = content_tree[list(content_tree)[0]]
-
+        embed_code = metadata['embed_code']
-        if determine_ext(video_url) == 'm3u8':
+        pcode = metadata.get('asset_pcode') or embed_code
-            formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
+        video_info = {
-        else:
+            'id': embed_code,
-            formats = [{
+            'title': metadata['title'],
-                'url': video_url,
+            'description': metadata.get('description'),
-                'ext': 'mp4',
+            'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'),
-            }]
+            'duration': float_or_none(metadata.get('duration'), 1000),
-
-        return {
-            'id': embedCode,
-            'title': unescapeHTML(info['title']),
-            'formats': formats,
-            'description': unescapeHTML(more_info['description']),
-            'thumbnail': more_info['promo'],
         }
 
-    def _extract(self, player_url, video_id):
+        formats = []
-        player = self._download_webpage(player_url, video_id)
+        for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'):
-        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
-                                        player, 'mobile player url')
-        # Looks like some videos are only available for particular devices
-        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
-        # is only available for ipad)
-        # Working around with fetching URLs for all the devices found starting with 'unknown'
-        # until we succeed or eventually fail for each device.
-        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
-        devices.remove('unknown')
-        devices.insert(0, 'unknown')
-        for device in devices:
-            mobile_player = self._download_webpage(
-                '%s&device=%s' % (mobile_url, device), video_id,
-                'Downloading mobile player JS for %s device' % device)
-            videos_info = self._search_regex(
-                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
-                mobile_player, 'info', fatal=False, default=None)
-            if videos_info:
-                break
-
-        if not videos_info:
-            formats = []
             auth_data = self._download_json(
-                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
+                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}),
-                video_id)
+                video_id, 'Downloading %s JSON' % supported_format)
 
-            cur_auth_data = auth_data['authorization_data'][video_id]
+            cur_auth_data = auth_data['authorization_data'][embed_code]
 
-            for stream in cur_auth_data['streams']:
+            if cur_auth_data['authorized']:
-                formats.append({
+                for stream in cur_auth_data['streams']:
-                    'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
+                    url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8')
-                    'ext': stream.get('delivery_type'),
+                    delivery_type = stream['delivery_type']
-                    'format': stream.get('video_codec'),
+                    if delivery_type == 'remote_asset':
-                    'format_id': stream.get('profile'),
+                        video_info['url'] = url
-                    'width': int_or_none(stream.get('width')),
+                        return video_info
-                    'height': int_or_none(stream.get('height')),
+                    if delivery_type == 'hls':
-                    'abr': int_or_none(stream.get('audio_bitrate')),
+                        formats.extend(self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-                    'vbr': int_or_none(stream.get('video_bitrate')),
+                    elif delivery_type == 'hds':
-                })
+                        formats.extend(self._extract_f4m_formats(url, embed_code, -1, 'hds', fatal=False))
-            if formats:
+                    else:
-                return {
+                        formats.append({
-                    'id': video_id,
+                            'url': url,
-                    'formats': formats,
+                            'ext': stream.get('delivery_type'),
-                    'title': 'Ooyala video',
+                            'vcodec': stream.get('video_codec'),
-                }
+                            'format_id': '%s-%s-%sp' % (stream.get('profile'), delivery_type, stream.get('height')),
+                            'width': int_or_none(stream.get('width')),
+                            'height': int_or_none(stream.get('height')),
+                            'abr': int_or_none(stream.get('audio_bitrate')),
+                            'vbr': int_or_none(stream.get('video_bitrate')),
+                            'fps': float_or_none(stream.get('framerate')),
+                        })
+            else:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True)
+        self._sort_formats(formats)
 
-            if not cur_auth_data['authorized']:
+        video_info['formats'] = formats
-                raise ExtractorError(cur_auth_data['message'], expected=True)
+        return video_info
-
-        if not videos_info:
-            raise ExtractorError('Unable to extract info')
-        videos_info = videos_info.replace('\\"', '"')
-        videos_more_info = self._search_regex(
-            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
-        videos_info = json.loads(videos_info)
-        videos_more_info = json.loads(videos_more_info)
-
-        if videos_more_info.get('lineup'):
-            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
-            return {
-                '_type': 'playlist',
-                'id': video_id,
-                'title': unescapeHTML(videos_more_info['title']),
-                'entries': videos,
-            }
-        else:
-            return self._extract_result(videos_info[0], videos_more_info)
 
 
 class OoyalaIE(OoyalaBaseIE):
@@ -117,6 +78,7 @@ class OoyalaIE(OoyalaBaseIE):
                 'ext': 'mp4',
                 'title': 'Explaining Data Recovery from Hard Drives and SSDs',
                 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+                'duration': 853.386,
             },
         }, {
             # Only available for ipad
@@ -125,7 +87,7 @@ class OoyalaIE(OoyalaBaseIE):
                 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
                 'ext': 'mp4',
                 'title': 'Simulation Overview - Levels of Simulation',
-                'description': '',
+                'duration': 194.948,
             },
         },
         {
@@ -136,7 +98,8 @@ class OoyalaIE(OoyalaBaseIE):
             'info_dict': {
                 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
                 'ext': 'mp4',
-                'title': 'Ooyala video',
+                'title': 'Divide Tool Path.mp4',
+                'duration': 204.405,
             }
         }
     ]
@@ -151,9 +114,11 @@ class OoyalaIE(OoyalaBaseIE):
                               ie=cls.ie_key())
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         embed_code = self._match_id(url)
-        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+        domain = smuggled_data.get('domain')
-        return self._extract(player_url, embed_code)
+        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code)
+        return self._extract(content_tree_url, embed_code, domain)
 
 
 class OoyalaExternalIE(OoyalaBaseIE):
@@ -170,7 +135,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
                         .*?&pcode=
                     )
                     (?P<pcode>.+?)
-                    (&|$)
+                    (?:&|$)
                     '''
 
     _TEST = {
@@ -179,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
             'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
             'ext': 'mp4',
             'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
-            'description': '',
+            'duration': 1302000,
         },
         'params': {
             # m3u8 download
@@ -188,9 +153,6 @@ class OoyalaExternalIE(OoyalaBaseIE):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups()
-        partner_id = mobj.group('partner_id')
+        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id)
-        video_id = mobj.group('id')
+        return self._extract(content_tree_url, video_id)
-        pcode = mobj.group('pcode')
-        player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
-        return self._extract(player_url, video_id)

youtube_dl/extractor/pluralsight.py

@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import re
 import json
 import random
 import collections
@@ -14,6 +15,7 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    qualities,
     sanitized_Request,
 )
 
@@ -140,15 +142,28 @@ class PluralsightIE(PluralsightBaseIE):
             'low': {'width': 640, 'height': 480},
             'medium': {'width': 848, 'height': 640},
             'high': {'width': 1024, 'height': 768},
+            'high-widescreen': {'width': 1280, 'height': 720},
         }
 
+        QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',)
+        quality_key = qualities(QUALITIES_PREFERENCE)
+
         AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
 
         ALLOWED_QUALITIES = (
-            AllowedQuality('webm', ('high',)),
+            AllowedQuality('webm', ['high', ]),
-            AllowedQuality('mp4', ('low', 'medium', 'high',)),
+            AllowedQuality('mp4', ['low', 'medium', 'high', ]),
         )
 
+        # Some courses also offer widescreen resolution for high quality (see
+        # https://github.com/rg3/youtube-dl/issues/7766)
+        widescreen = True if re.search(
+            r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False
+        best_quality = 'high-widescreen' if widescreen else 'high'
+        if widescreen:
+            for allowed_quality in ALLOWED_QUALITIES:
+                allowed_quality.qualities.append(best_quality)
+
         # In order to minimize the number of calls to ViewClip API and reduce
         # the probability of being throttled or banned by Pluralsight we will request
         # only single format until formats listing was explicitly requested.
@@ -157,19 +172,19 @@ class PluralsightIE(PluralsightBaseIE):
         else:
             def guess_allowed_qualities():
                 req_format = self._downloader.params.get('format') or 'best'
-                req_format_split = req_format.split('-')
+                req_format_split = req_format.split('-', 1)
                 if len(req_format_split) > 1:
                     req_ext, req_quality = req_format_split
                     for allowed_quality in ALLOWED_QUALITIES:
                         if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
                             return (AllowedQuality(req_ext, (req_quality, )), )
                 req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
-                return (AllowedQuality(req_ext, ('high', )), )
+                return (AllowedQuality(req_ext, (best_quality, )), )
             allowed_qualities = guess_allowed_qualities()
 
         formats = []
-        for ext, qualities in allowed_qualities:
+        for ext, qualities_ in allowed_qualities:
-            for quality in qualities:
+            for quality in qualities_:
                 f = QUALITIES[quality].copy()
                 clip_post = {
                     'a': author,
@@ -205,6 +220,7 @@ class PluralsightIE(PluralsightBaseIE):
                     'url': clip_url,
                     'ext': ext,
                     'format_id': format_id,
+                    'quality': quality_key(quality),
                 })
                 formats.append(f)
         self._sort_formats(formats)

youtube_dl/extractor/pornhub.py

@@ -147,7 +147,8 @@ class PornHubPlaylistIE(InfoExtractor):
 
         entries = [
             self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
-            for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
+            for video_url in set(re.findall(
+                r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
         ]
 
         playlist = self._parse_json(

youtube_dl/extractor/skynewsarabia.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    parse_iso8601,
+    parse_duration,
+)
+
+
+class SkyNewsArabiaBaseIE(InfoExtractor):
+    _IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images'
+
+    def _call_api(self, path, value):
+        return self._download_json('http://api.skynewsarabia.com/web/rest/v2/%s/%s.json' % (path, value), value)
+
+    def _get_limelight_media_id(self, url):
+        return self._search_regex(r'/media/[^/]+/([a-z0-9]{32})', url, 'limelight media id')
+
+    def _get_image_url(self, image_path_template, width='1600', height='1200'):
+        return self._IMAGE_BASE_URL + image_path_template.format(width=width, height=height)
+
+    def _extract_video_info(self, video_data):
+        video_id = compat_str(video_data['id'])
+        topic = video_data.get('topicTitle')
+        return {
+            '_type': 'url_transparent',
+            'url': 'limelight:media:%s' % self._get_limelight_media_id(video_data['videoUrl'][0]['url']),
+            'id': video_id,
+            'title': video_data['headline'],
+            'description': video_data.get('summary'),
+            'thumbnail': self._get_image_url(video_data['mediaAsset']['imageUrl']),
+            'timestamp': parse_iso8601(video_data.get('date')),
+            'duration': parse_duration(video_data.get('runTime')),
+            'tags': video_data.get('tags', []),
+            'categories': [topic] if topic else [],
+            'webpage_url': 'http://www.skynewsarabia.com/web/video/%s' % video_id,
+            'ie_key': 'LimelightMedia',
+        }
+
+
+class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
+    IE_NAME = 'skynewsarabia:video'
+    _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.skynewsarabia.com/web/video/794902/%D9%86%D8%B5%D9%81-%D9%85%D9%84%D9%8A%D9%88%D9%86-%D9%85%D8%B5%D8%A8%D8%A7%D8%AD-%D8%B4%D8%AC%D8%B1%D8%A9-%D9%83%D8%B1%D9%8A%D8%B3%D9%85%D8%A7%D8%B3',
+        'info_dict': {
+            'id': '794902',
+            'ext': 'flv',
+            'title': 'نصف مليون مصباح على شجرة كريسماس',
+            'description': 'md5:22f1b27f0850eeb10c7e59b1f16eb7c6',
+            'upload_date': '20151128',
+            'timestamp': 1448697198,
+            'duration': 2119,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._call_api('video', video_id)
+        return self._extract_video_info(video_data)
+
+
+class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE):
+    IE_NAME = 'skynewsarabia:video'
+    _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.skynewsarabia.com/web/article/794549/%D8%A7%D9%94%D8%AD%D8%AF%D8%A7%D8%AB-%D8%A7%D9%84%D8%B4%D8%B1%D9%82-%D8%A7%D9%84%D8%A7%D9%94%D9%88%D8%B3%D8%B7-%D8%AE%D8%B1%D9%8A%D8%B7%D8%A9-%D8%A7%D9%84%D8%A7%D9%94%D9%84%D8%B9%D8%A7%D8%A8-%D8%A7%D9%84%D8%B0%D9%83%D9%8A%D8%A9',
+        'info_dict': {
+            'id': '794549',
+            'ext': 'flv',
+            'title': 'بالفيديو.. ألعاب ذكية تحاكي واقع المنطقة',
+            'description': 'md5:0c373d29919a851e080ee4edd0c5d97f',
+            'upload_date': '20151126',
+            'timestamp': 1448559336,
+            'duration': 281.6,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.skynewsarabia.com/web/article/794844/%D8%A7%D8%B3%D8%AA%D9%87%D8%AF%D8%A7%D9%81-%D9%82%D9%88%D8%A7%D8%B1%D8%A8-%D8%A7%D9%94%D8%B3%D9%84%D8%AD%D8%A9-%D9%84%D9%85%D9%8A%D9%84%D9%8A%D8%B4%D9%8A%D8%A7%D8%AA-%D8%A7%D9%84%D8%AD%D9%88%D8%AB%D9%8A-%D9%88%D8%B5%D8%A7%D9%84%D8%AD',
+        'info_dict': {
+            'id': '794844',
+            'title': 'إحباط تهريب أسلحة لميليشيات الحوثي وصالح بجنوب اليمن',
+            'description': 'md5:5c927b8b2e805796e7f693538d96fc7e',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        article_data = self._call_api('article', article_id)
+        media_asset = article_data['mediaAsset']
+        if media_asset['type'] == 'VIDEO':
+            topic = article_data.get('topicTitle')
+            return {
+                '_type': 'url_transparent',
+                'url': 'limelight:media:%s' % self._get_limelight_media_id(media_asset['videoUrl'][0]['url']),
+                'id': article_id,
+                'title': article_data['headline'],
+                'description': article_data.get('summary'),
+                'thumbnail': self._get_image_url(media_asset['imageUrl']),
+                'timestamp': parse_iso8601(article_data.get('date')),
+                'tags': article_data.get('tags', []),
+                'categories': [topic] if topic else [],
+                'webpage_url': url,
+                'ie_key': 'LimelightMedia',
+            }
+        entries = [self._extract_video_info(item) for item in article_data.get('inlineItems', []) if item['type'] == 'VIDEO']
+        return self.playlist_result(entries, article_id, article_data['headline'], article_data.get('summary'))

youtube_dl/extractor/spiegel.py

@@ -58,7 +58,8 @@ class SpiegelIE(InfoExtractor):
         description = self._html_search_meta('description', webpage, 'description')
 
         base_url = self._search_regex(
-            r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
+            [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
+            webpage, 'server URL', group='url')
 
         xml_url = base_url + video_id + '.xml'
         idoc = self._download_xml(xml_url, video_id)

youtube_dl/extractor/srf.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class SrfIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
+    _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
     _TESTS = [{
         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
         'md5': '4cd93523723beff51bb4bee974ee238d',
@@ -35,6 +35,20 @@ class SrfIE(InfoExtractor):
             'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
             'timestamp': 1373493600,
         },
+    }, {
+        'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc',
+        'md5': '',
+        'info_dict': {
+            'id': '415bf3d3-6429-4de7-968d-95866e37cfbc',
+            'display_id': 'saegel-ohni-wind-von-jakob-stebler',
+            'ext': 'mp3',
+            'upload_date': '20080518',
+            'title': '«Sägel ohni Wind» von Jakob Stebler',
+            'timestamp': 1211112000,
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
     }, {
         'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
         'only_matching': True,
@@ -44,11 +58,13 @@ class SrfIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
-        display_id = re.match(self._VALID_URL, url).group('display_id') or video_id
+        video_id = mobj.group('id')
+        media_type = mobj.group('media_type')
+        display_id = mobj.group('display_id') or video_id
 
         video_data = self._download_xml(
-            'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id,
+            'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id),
             display_id)
 
         title = xpath_text(
@@ -64,7 +80,7 @@ class SrfIE(InfoExtractor):
             for url_node in item.findall('url'):
                 quality = url_node.attrib['quality']
                 full_url = url_node.text
-                original_ext = determine_ext(full_url)
+                original_ext = determine_ext(full_url).lower()
                 format_id = '%s-%s' % (quality, item.attrib['protocol'])
                 if original_ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(

youtube_dl/extractor/teachingchannel.py

@@ -16,6 +16,7 @@ class TeachingChannelIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'A History of Teaming',
             'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
+            'duration': 422.255,
         },
         'params': {
             # m3u8 download

youtube_dl/extractor/trilulilu.py

@@ -1,80 +1,103 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class TriluliluIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)'
-    _TEST = {
+    _TESTS = [{
-        'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
+        'url': 'http://www.trilulilu.ro/big-buck-bunny-1',
-        'md5': 'c1450a00da251e2769b74b9005601cac',
+        'md5': '68da087b676a6196a413549212f60cc6',
         'info_dict': {
             'id': 'ae2899e124140b',
             'ext': 'mp4',
             'title': 'Big Buck Bunny',
             'description': ':) pentru copilul din noi',
+            'uploader_id': 'chipy',
+            'upload_date': '20120304',
+            'timestamp': 1330830647,
+            'uploader': 'chipy',
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
         },
-    }
+    }, {
+        'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
+        'md5': '929dfb8729dc71750463af88bbbbf4a4',
+        'info_dict': {
+            'id': 'f299710e3c91c5',
+            'ext': 'mp4',
+            'title': 'Adena ft. Morreti - Inocenta',
+            'description': 'pop music',
+            'uploader_id': 'VEVOmixt',
+            'upload_date': '20151204',
+            'uploader': 'VEVOmixt',
+            'timestamp': 1449187937,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
 
-        if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
+        age_limit = 0
-            raise ExtractorError(
+        errors = media_info.get('errors', {})
-                'This video is not available in your country.', expected=True)
+        if errors.get('friends'):
-        elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
             raise ExtractorError('This video is private.', expected=True)
+        elif errors.get('geoblock'):
+            raise ExtractorError('This video is not available in your country.', expected=True)
+        elif errors.get('xxx_unlogged'):
+            age_limit = 18
 
-        flashvars_str = self._search_regex(
+        media_class = media_info.get('class')
-            r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None)
+        if media_class not in ('video', 'audio'):
+            raise ExtractorError('not a video or an audio')
 
-        if flashvars_str:
+        user = media_info.get('user', {})
-            flashvars = self._parse_json(flashvars_str, display_id)
+
+        thumbnail = media_info.get('cover_url')
+        if thumbnail:
+            thumbnail.format(width='1600', height='1200')
+
+        # TODO: get correct ext for audio files
+        stream_type = media_info.get('stream_type')
+        formats = [{
+            'url': media_info['href'],
+            'ext': stream_type,
+        }]
+        if media_info.get('is_hd'):
+            formats.append({
+                'format_id': 'hd',
+                'url': media_info['hrefhd'],
+                'ext': stream_type,
+            })
+        if media_class == 'audio':
+            formats[0]['vcodec'] = 'none'
         else:
-            raise ExtractorError(
+            formats[0]['format_id'] = 'sd'
-                'This page does not contain videos', expected=True)
-
-        if flashvars['isMP3'] == 'true':
-            raise ExtractorError(
-                'Audio downloads are currently not supported', expected=True)
-
-        video_id = flashvars['hash']
-        title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage, default=None)
-
-        format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
-                      'video-formats2' % flashvars)
-        format_doc = self._download_xml(
-            format_url, video_id,
-            note='Downloading formats',
-            errnote='Error while downloading formats')
-
-        video_url_template = (
-            'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
-            '&source=site&hash=%(hash)s&username=%(userid)s&'
-            'key=ministhebest&format=%%s&sig=&exp=' %
-            flashvars)
-        formats = [
-            {
-                'format_id': fnode.text.partition('-')[2],
-                'url': video_url_template % fnode.text,
-                'ext': fnode.text.partition('-')[0]
-            }
-
-            for fnode in format_doc.findall('./formats/format')
-        ]
 
         return {
-            'id': video_id,
+            'id': media_info['identifier'].split('|')[1],
             'display_id': display_id,
             'formats': formats,
-            'title': title,
+            'title': media_info['title'],
-            'description': description,
+            'description': media_info.get('description'),
             'thumbnail': thumbnail,
+            'uploader_id': user.get('username'),
+            'uploader': user.get('fullname'),
+            'timestamp': parse_iso8601(media_info.get('published'), ' '),
+            'duration': int_or_none(media_info.get('duration')),
+            'view_count': int_or_none(media_info.get('count_views')),
+            'like_count': int_or_none(media_info.get('count_likes')),
+            'comment_count': int_or_none(media_info.get('count_comments')),
+            'age_limit': age_limit,
         }

youtube_dl/extractor/udemy.py

@@ -1,14 +1,15 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
+    compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
     sanitized_Request,
 )
 
@@ -18,6 +19,8 @@ class UdemyIE(InfoExtractor):
     _VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
     _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
     _ORIGIN_URL = 'https://www.udemy.com'
+    _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
+    _ALREADY_ENROLLED = '>You are already taking this course.<'
     _NETRC_MACHINE = 'udemy'
 
     _TESTS = [{
@@ -33,6 +36,29 @@ class UdemyIE(InfoExtractor):
         'skip': 'Requires udemy account credentials',
     }]
 
+    def _enroll_course(self, webpage, course_id):
+        enroll_url = self._search_regex(
+            r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/course/subscribe/.+?)\1',
+            webpage, 'enroll url', group='url',
+            default='https://www.udemy.com/course/subscribe/?courseId=%s' % course_id)
+        webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course')
+        if self._SUCCESSFULLY_ENROLLED in webpage:
+            self.to_screen('%s: Successfully enrolled in' % course_id)
+        elif self._ALREADY_ENROLLED in webpage:
+            self.to_screen('%s: Already enrolled in' % course_id)
+
+    def _download_lecture(self, course_id, lecture_id):
+        return self._download_json(
+            'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % (
+                course_id, lecture_id, compat_urllib_parse.urlencode({
+                    'video_only': '',
+                    'auto_play': '',
+                    'fields[lecture]': 'title,description,asset',
+                    'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
+                    'instructorPreviewMode': 'False',
+                })),
+            lecture_id, 'Downloading lecture JSON')
+
     def _handle_error(self, response):
         if not isinstance(response, dict):
             return
@@ -54,6 +80,7 @@ class UdemyIE(InfoExtractor):
                 headers['X-Udemy-Client-Id'] = cookie.value
             elif cookie.name == 'access_token':
                 headers['X-Udemy-Bearer-Token'] = cookie.value
+                headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value
 
         if isinstance(url_or_request, compat_urllib_request.Request):
             for header, value in headers.items():
@@ -71,7 +98,7 @@ class UdemyIE(InfoExtractor):
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
-            self.raise_login_required('Udemy account is required')
+            return
 
         login_popup = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login popup')
@@ -109,44 +136,76 @@ class UdemyIE(InfoExtractor):
     def _real_extract(self, url):
         lecture_id = self._match_id(url)
 
-        lecture = self._download_json(
+        webpage = self._download_webpage(url, lecture_id)
-            'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id,
-            lecture_id, 'Downloading lecture JSON')
 
-        asset_type = lecture.get('assetType') or lecture.get('asset_type')
+        course_id = self._search_regex(
+            r'data-course-id=["\'](\d+)', webpage, 'course id')
+
+        try:
+            lecture = self._download_lecture(course_id, lecture_id)
+        except ExtractorError as e:
+            # Error could possibly mean we are not enrolled in the course
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                self._enroll_course(webpage, course_id)
+                lecture_id = self._download_lecture(course_id, lecture_id)
+            else:
+                raise
+
+        title = lecture['title']
+        description = lecture.get('description')
+
+        asset = lecture['asset']
+
+        asset_type = asset.get('assetType') or asset.get('asset_type')
         if asset_type != 'Video':
             raise ExtractorError(
                 'Lecture %s is not a video' % lecture_id, expected=True)
 
-        asset = lecture['asset']
-
         stream_url = asset.get('streamUrl') or asset.get('stream_url')
-        mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url)
+        if stream_url:
-        if mobj:
+            youtube_url = self._search_regex(
-            return self.url_result(mobj.group(1), 'Youtube')
+                r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None)
+            if youtube_url:
+                return self.url_result(youtube_url, 'Youtube')
 
         video_id = asset['id']
         thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
-        duration = asset['data']['duration']
+        duration = float_or_none(asset.get('data', {}).get('duration'))
+        outputs = asset.get('data', {}).get('outputs', {})
 
-        download_url = asset.get('downloadUrl') or asset.get('download_url')
+        formats = []
+        for format_ in asset.get('download_urls', {}).get('Video', []):
+            video_url = format_.get('file')
+            if not video_url:
+                continue
+            format_id = format_.get('label')
+            f = {
+                'url': format_['file'],
+                'height': int_or_none(format_id),
+            }
+            if format_id:
+                # Some videos contain additional metadata (e.g.
+                # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
+                output = outputs.get(format_id)
+                if isinstance(output, dict):
+                    f.update({
+                        'format_id': '%sp' % (output.get('label') or format_id),
+                        'width': int_or_none(output.get('width')),
+                        'height': int_or_none(output.get('height')),
+                        'vbr': int_or_none(output.get('video_bitrate_in_kbps')),
+                        'vcodec': output.get('video_codec'),
+                        'fps': int_or_none(output.get('frame_rate')),
+                        'abr': int_or_none(output.get('audio_bitrate_in_kbps')),
+                        'acodec': output.get('audio_codec'),
+                        'asr': int_or_none(output.get('audio_sample_rate')),
+                        'tbr': int_or_none(output.get('total_bitrate_in_kbps')),
+                        'filesize': int_or_none(output.get('file_size_in_bytes')),
+                    })
+                else:
+                    f['format_id'] = '%sp' % format_id
+            formats.append(f)
 
-        video = download_url.get('Video') or download_url.get('video')
+        self._sort_formats(formats)
-        video_480p = download_url.get('Video480p') or download_url.get('video_480p')
-
-        formats = [
-            {
-                'url': video_480p[0],
-                'format_id': '360p',
-            },
-            {
-                'url': video[0],
-                'format_id': '720p',
-            },
-        ]
-
-        title = lecture['title']
-        description = lecture['description']
 
         return {
             'id': video_id,
@@ -160,9 +219,7 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
-    _VALID_URL = r'https?://www\.udemy\.com/(?P<coursepath>[\da-z-]+)'
+    _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)'
-    _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
-    _ALREADY_ENROLLED = '>You are already taking this course.<'
     _TESTS = []
 
     @classmethod
@@ -170,24 +227,18 @@ class UdemyCourseIE(UdemyIE):
         return False if UdemyIE.suitable(url) else super(UdemyCourseIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        course_path = self._match_id(url)
-        course_path = mobj.group('coursepath')
+
+        webpage = self._download_webpage(url, course_path)
 
         response = self._download_json(
             'https://www.udemy.com/api-1.1/courses/%s' % course_path,
             course_path, 'Downloading course JSON')
 
-        course_id = int(response['id'])
+        course_id = response['id']
-        course_title = response['title']
+        course_title = response.get('title')
 
-        webpage = self._download_webpage(
+        self._enroll_course(webpage, course_id)
-            'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id,
-            course_id, 'Enrolling in the course')
-
-        if self._SUCCESSFULLY_ENROLLED in webpage:
-            self.to_screen('%s: Successfully enrolled in' % course_id)
-        elif self._ALREADY_ENROLLED in webpage:
-            self.to_screen('%s: Already enrolled in' % course_id)
 
         response = self._download_json(
             'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,

youtube_dl/extractor/vice.py

@@ -15,6 +15,7 @@ class ViceIE(InfoExtractor):
                 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
                 'ext': 'mp4',
                 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+                'duration': 725.983,
             },
             'params': {
                 # Requires ffmpeg (m3u8 manifest)

youtube_dl/extractor/videoweed.py

@@ -1,26 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class VideoWeedIE(NovaMovIE):
-    IE_NAME = 'videoweed'
-    IE_DESC = 'VideoWeed'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
-
-    _HOST = 'www.videoweed.es'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
-
-    _TEST = {
-        'url': 'http://www.videoweed.es/file/b42178afbea14',
-        'md5': 'abd31a2132947262c50429e1d16c1bfd',
-        'info_dict': {
-            'id': 'b42178afbea14',
-            'ext': 'flv',
-            'title': 'optical illusion  dissapeared image magic illusion',
-            'description': ''
-        },
-    }

youtube_dl/extractor/vodlocker.py

@@ -3,11 +3,14 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse
-from ..utils import sanitized_Request
+from ..utils import (
+    ExtractorError,
+    sanitized_Request,
+)
 
 
 class VodlockerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
+    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
 
     _TESTS = [{
         'url': 'http://vodlocker.com/e8wvyzz4sl42',
@@ -24,6 +27,12 @@ class VodlockerIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if any(p in webpage for p in (
+                '>THIS FILE WAS DELETED<',
+                '>File Not Found<',
+                'The file you were looking for could not be found, sorry for any inconvenience.<')):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
         fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':

youtube_dl/extractor/youtube.py

@@ -258,7 +258,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                              |(?:                                             # or the v= param in all its forms
                                  (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
                                  (?:\?|\#!?)                                  # the params delimiter ? or # or #!
-                                 (?:.*?&)??                                   # any other preceding param (like /?s=tuff&v=xxxx)
+                                 (?:.*?[&;])??                                # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
                                  v=
                              )
                          ))
@@ -346,6 +346,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
         '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
@@ -714,6 +715,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
             'only_matching': True,
         },
+        {
+            # Video with yt:stretch=17:0
+            'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
+            'info_dict': {
+                'id': 'Q39EVAstoRM',
+                'ext': 'mp4',
+                'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
+                'description': 'md5:ee18a25c350637c8faff806845bddee9',
+                'upload_date': '20151107',
+                'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
+                'uploader': 'CH GAMER DROID',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'https://www.youtube.com/watch?feature=player_embedded&v=V36LpHqtcDY',
+            'only_matching': True,
+        }
     ]
 
     def __init__(self, *args, **kwargs):
@@ -1459,6 +1480,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             manifest_url = video_info['hlsvp'][0]
             url_map = self._extract_from_m3u8(manifest_url, video_id)
             formats = _map_to_format_list(url_map)
+            # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
+            for a_format in formats:
+                a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
         else:
             raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
@@ -1496,10 +1520,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
             video_webpage)
         if stretched_m:
-            ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
+            w = float(stretched_m.group('w'))
-            for f in formats:
+            h = float(stretched_m.group('h'))
-                if f.get('vcodec') != 'none':
+            # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
-                    f['stretched_ratio'] = ratio
+            # We will only process correct ratios.
+            if w > 0 and h > 0:
+                ratio = w / h
+                for f in formats:
+                    if f.get('vcodec') != 'none':
+                        f['stretched_ratio'] = ratio
 
         self._sort_formats(formats)
 
@@ -1538,7 +1567,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract
                         youtube\.com/
                         (?:
                            (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
-                           \? (?:.*?&)*? (?:p|a|list)=
+                           \? (?:.*?[&;])*? (?:p|a|list)=
                         |  p/
                         )
                         (

youtube_dl/options.py

@@ -338,7 +338,7 @@ def parseOpts(overrideArguments=None):
     video_format.add_option(
         '-F', '--list-formats',
         action='store_true', dest='listformats',
-        help='List all available formats')
+        help='List all available formats of requested videos')
     video_format.add_option(
         '--youtube-include-dash-manifest',
         action='store_true', dest='youtube_include_dash_manifest', default=True,

youtube_dl/utils.py

@@ -663,6 +663,16 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
     return hc
 
 
+def handle_youtubedl_headers(headers):
+    filtered_headers = headers
+
+    if 'Youtubedl-no-compression' in filtered_headers:
+        filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
+        del filtered_headers['Youtubedl-no-compression']
+
+    return filtered_headers
+
+
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
@@ -670,7 +680,7 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     the standard headers to every HTTP request and handles gzipped and
     deflated responses from web servers. If compression is to be avoided in
     a particular request, the original request in the program code only has
-    to include the HTTP header "Youtubedl-No-Compression", which will be
+    to include the HTTP header "Youtubedl-no-compression", which will be
     removed before making the real request.
 
     Part of this code was copied from:
@@ -731,10 +741,8 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
             # The dict keys are capitalized because of this bug by urllib
             if h.capitalize() not in req.headers:
                 req.add_header(h, v)
-        if 'Youtubedl-no-compression' in req.headers:
+
-            if 'Accept-encoding' in req.headers:
+        req.headers = handle_youtubedl_headers(req.headers)
-                del req.headers['Accept-encoding']
-            del req.headers['Youtubedl-no-compression']
 
         if sys.version_info < (2, 7) and '#' in req.get_full_url():
             # Python 2.6 is brain-dead when it comes to fragments

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.11.24'
+__version__ = '2015.12.06'