release 2017.01.28

- extract vtt subtitles
- extract multiple resolutions for thumbnails
- pass geo verification proxy headers
- add support for mobile urls

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.24**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.28*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.28**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.01.24
+[debug] youtube-dl version 2017.01.28
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,38 @@
+version 2017.01.28
+
+Core
+* [utils] Improve parse_duration
+
+Extractors
+* [crunchyroll] Improve series and season metadata extraction (#11832)
+* [soundcloud] Improve formats extraction and extract audio bitrate
++ [soundcloud] Extract HLS formats
+* [soundcloud] Fix track URL extraction (#11852)
++ [twitch:vod] Expand URL regular expressions (#11846)
+* [aenetworks] Fix season episodes extraction (#11669)
++ [tva] Add support for videos.tva.ca (#11842)
+* [jamendo] Improve and extract more metadata (#11836)
++ [disney] Add support for Disney sites (#7409, #11801, #4975, #11000)
+* [vevo] Remove request to old API and catch API v2 errors
++ [cmt,mtv,southpark] Add support for episode URLs (#11837)
++ [youtube] Add fallback for duration extraction (#11841)
+
+
+version 2017.01.25
+
+Extractors
++ [openload] Fallback video extension to mp4
++ [extractor/generic] Add support for Openload embeds (#11536, #11812)
+* [srgssr] Fix rts video extraction (#11831)
++ [afreecatv:global] Add support for afreeca.tv (#11807)
++ [crackle] Extract vtt subtitles
++ [crackle] Extract multiple resolutions for thumbnails
++ [crackle] Add support for mobile URLs
++ [konserthusetplay] Extract subtitles (#11823)
++ [konserthusetplay] Add support for HLS videos (#11823)
+* [vimeo:review] Fix config URL extraction (#11821)
+
+
 version 2017.01.24
 
 Extractors

docs/supportedsites.md

@@ -33,7 +33,8 @@
  - **AdobeTVVideo**
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
- - **AfreecaTV**: afreecatv.com
+ - **afreecatv**: afreecatv.com
+ - **afreecatv:global**: afreecatv.com
  - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
@@ -201,6 +202,7 @@
  - **Digiteka**
  - **Discovery**
  - **DiscoveryGo**
+ - **Disney**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
  - **DPlay**
@@ -784,6 +786,7 @@
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
  - **TVC**

test/test_utils.py

@@ -510,6 +510,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
         self.assertEqual(parse_duration('87 Min.'), 5220)
         self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
+        self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(

youtube_dl/extractor/aenetworks.py

@@ -87,7 +87,7 @@ class AENetworksIE(AENetworksBaseIE):
                     self._html_search_meta('aetn:SeriesTitle', webpage))
             elif url_parts_len == 2:
                 entries = []
-                for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
+                for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)
                     episode_url = compat_urlparse.urljoin(
                         url, episode_attributes['data-canonical'])

youtube_dl/extractor/afreecatv.py

@@ -18,6 +18,7 @@ from ..utils import (
 
 
 class AfreecaTVIE(InfoExtractor):
+    IE_NAME = 'afreecatv'
     IE_DESC = 'afreecatv.com'
     _VALID_URL = r'''(?x)
                     https?://
@@ -143,3 +144,94 @@ class AfreecaTVIE(InfoExtractor):
                 expected=True)
 
         return info
+
+
+class AfreecaTVGlobalIE(AfreecaTVIE):
+    IE_NAME = 'afreecatv:global'
+    _VALID_URL = r'https?://(?:www\.)?afreeca\.tv/(?P<channel_id>\d+)(?:/v/(?P<video_id>\d+))?'
+    _TESTS = [{
+        'url': 'http://afreeca.tv/36853014/v/58301',
+        'info_dict': {
+            'id': '58301',
+            'title': 'tryhard top100',
+            'uploader_id': '36853014',
+            'uploader': 'makgi Hearthstone Live!',
+        },
+        'playlist_count': 3,
+    }]
+
+    def _real_extract(self, url):
+        channel_id, video_id = re.match(self._VALID_URL, url).groups()
+        video_type = 'video' if video_id else 'live'
+        query = {
+            'pt': 'view',
+            'bid': channel_id,
+        }
+        if video_id:
+            query['vno'] = video_id
+        video_data = self._download_json(
+            'http://api.afreeca.tv/%s/view_%s.php' % (video_type, video_type),
+            video_id or channel_id, query=query)['channel']
+
+        if video_data.get('result') != 1:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, video_data['remsg']))
+
+        title = video_data['title']
+
+        info = {
+            'thumbnail': video_data.get('thumb'),
+            'view_count': int_or_none(video_data.get('vcnt')),
+            'age_limit': int_or_none(video_data.get('grade')),
+            'uploader_id': channel_id,
+            'uploader': video_data.get('cname'),
+        }
+
+        if video_id:
+            entries = []
+            for i, f in enumerate(video_data.get('flist', [])):
+                video_key = self.parse_video_key(f.get('key', ''))
+                f_url = f.get('file')
+                if not video_key or not f_url:
+                    continue
+                entries.append({
+                    'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
+                    'title': title,
+                    'upload_date': video_key.get('upload_date'),
+                    'duration': int_or_none(f.get('length')),
+                    'url': f_url,
+                    'protocol': 'm3u8_native',
+                    'ext': 'mp4',
+                })
+
+            info.update({
+                'id': video_id,
+                'title': title,
+                'duration': int_or_none(video_data.get('length')),
+            })
+            if len(entries) > 1:
+                info['_type'] = 'multi_video'
+                info['entries'] = entries
+            elif len(entries) == 1:
+                i = entries[0].copy()
+                i.update(info)
+                info = i
+        else:
+            formats = []
+            for s in video_data.get('strm', []):
+                s_url = s.get('purl')
+                if not s_url:
+                    continue
+                # TODO: extract rtmp formats
+                if s.get('stype') == 'HLS':
+                    formats.extend(self._extract_m3u8_formats(
+                        s_url, channel_id, 'mp4', fatal=False))
+            self._sort_formats(formats)
+
+            info.update({
+                'id': channel_id,
+                'title': self._live_title(title),
+                'is_live': True,
+                'formats': formats,
+            })
+
+        return info

youtube_dl/extractor/cmt.py

@@ -5,7 +5,7 @@ from .mtv import MTVIE
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|full-episodes|video-clips)/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',

youtube_dl/extractor/crackle.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class CrackleIE(InfoExtractor):
-    _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
+    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
         'info_dict': {
@@ -31,8 +31,32 @@ class CrackleIE(InfoExtractor):
         }
     }
 
+    _THUMBNAIL_RES = [
+        (120, 90),
+        (208, 156),
+        (220, 124),
+        (220, 220),
+        (240, 180),
+        (250, 141),
+        (315, 236),
+        (320, 180),
+        (360, 203),
+        (400, 300),
+        (421, 316),
+        (460, 330),
+        (460, 460),
+        (462, 260),
+        (480, 270),
+        (587, 330),
+        (640, 480),
+        (700, 330),
+        (700, 394),
+        (854, 480),
+        (1024, 1024),
+        (1920, 1080),
+    ]
+
     # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
-    _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
     _MEDIA_FILE_SLOTS = {
         'c544.flv': {
             'width': 544,
@@ -61,17 +85,25 @@ class CrackleIE(InfoExtractor):
 
         item = self._download_xml(
             'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
-            video_id).find('i')
+            video_id, headers=self.geo_verification_headers()).find('i')
         title = item.attrib['t']
 
         subtitles = {}
         formats = self._extract_m3u8_formats(
             'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
             video_id, 'mp4', m3u8_id='hls', fatal=None)
-        thumbnail = None
+        thumbnails = []
         path = item.attrib.get('p')
         if path:
-            thumbnail = self._THUMBNAIL_TEMPLATE % path
+            for width, height in self._THUMBNAIL_RES:
+                res = '%dx%d' % (width, height)
+                thumbnails.append({
+                    'id': res,
+                    'url': 'http://images-us-am.crackle.com/%stnl_%s.jpg' % (path, res),
+                    'width': width,
+                    'height': height,
+                    'resolution': res,
+                })
             http_base_url = 'http://ahttp.crackle.com/' + path
             for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
                 formats.append({
@@ -86,10 +118,11 @@ class CrackleIE(InfoExtractor):
                 if locale and v:
                     if locale not in subtitles:
                         subtitles[locale] = []
-                    subtitles[locale] = [{
-                        'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
-                        'ext': 'ttml',
-                    }]
+                    for url_ext, ext in (('vtt', 'vtt'), ('xml', 'tt')):
+                        subtitles.setdefault(locale, []).append({
+                            'url': '%s/%s%s_%s.%s' % (config_doc.attrib['strSubtitleServer'], path, locale, v, url_ext),
+                            'ext': ext,
+                        })
         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 
         return {
@@ -100,7 +133,7 @@ class CrackleIE(InfoExtractor):
             'series': item.attrib.get('sn'),
             'season_number': int_or_none(item.attrib.get('se')),
             'episode_number': int_or_none(item.attrib.get('ep')),
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/crunchyroll.py

@@ -166,6 +166,25 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
+        'info_dict': {
+            'id': '727589',
+            'ext': 'mp4',
+            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
+            'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Kadokawa Pictures Inc.',
+            'upload_date': '20170118',
+            'series': "KONOSUBA -God's blessing on this wonderful world!",
+            'season_number': 2,
+            'episode': 'Give Me Deliverance from this Judicial Injustice!',
+            'episode_number': 1,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -439,6 +458,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         subtitles = self.extract_subtitles(video_id, webpage)
 
+        # webpage provide more accurate data than series_title from XML
+        series = self._html_search_regex(
+            r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
+            webpage, 'series', default=xpath_text(metadata, 'series_title'))
+
+        episode = xpath_text(metadata, 'episode_title')
+        episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+
+        season_number = int_or_none(self._search_regex(
+            r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
+            webpage, 'season number', default=None))
+
         return {
             'id': video_id,
             'title': video_title,
@@ -446,9 +477,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'thumbnail': xpath_text(metadata, 'episode_image_url'),
             'uploader': video_uploader,
             'upload_date': video_upload_date,
-            'series': xpath_text(metadata, 'series_title'),
-            'episode': xpath_text(metadata, 'episode_title'),
-            'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),
+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/disney.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    compat_str,
+    determine_ext,
+)
+
+
+class DisneyIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
+    _TESTS = [{
+        'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
+        'info_dict': {
+            'id': '545ed1857afee5a0ec239977',
+            'ext': 'mp4',
+            'title': 'Moana - Trailer',
+            'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
+            'upload_date': '20170112',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(
+            'http://%s/embed/%s' % (domain, video_id), video_id)
+        video_data = self._parse_json(self._search_regex(
+            r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
+
+        for external in video_data.get('externals', []):
+            if external.get('source') == 'vevo':
+                return self.url_result('vevo:' + external['data_id'], 'Vevo')
+
+        title = video_data['title']
+
+        formats = []
+        for flavor in video_data.get('flavors', []):
+            flavor_format = flavor.get('format')
+            flavor_url = flavor.get('url')
+            if not flavor_url or not re.match(r'https?://', flavor_url):
+                continue
+            tbr = int_or_none(flavor.get('bitrate'))
+            if tbr == 99999:
+                formats.extend(self._extract_m3u8_formats(
+                    flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
+                continue
+            format_id = []
+            if flavor_format:
+                format_id.append(flavor_format)
+            if tbr:
+                format_id.append(compat_str(tbr))
+            ext = determine_ext(flavor_url)
+            if flavor_format == 'applehttp' or ext == 'm3u8':
+                ext = 'mp4'
+            width = int_or_none(flavor.get('width'))
+            height = int_or_none(flavor.get('height'))
+            formats.append({
+                'format_id': '-'.join(format_id),
+                'url': flavor_url,
+                'width': width,
+                'height': height,
+                'tbr': tbr,
+                'ext': ext,
+                'vcodec': 'none' if (width == 0 and height == 0) else None,
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for caption in video_data.get('captions', []):
+            caption_url = caption.get('url')
+            caption_format = caption.get('format')
+            if not caption_url or caption_format.startswith('unknown'):
+                continue
+            subtitles.setdefault(caption.get('language', 'en'), []).append({
+                'url': caption_url,
+                'ext': {
+                    'webvtt': 'vtt',
+                }.get(caption_format, caption_format),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description') or video_data.get('short_desc'),
+            'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
+            'duration': int_or_none(video_data.get('duration_sec')),
+            'upload_date': unified_strdate(video_data.get('publish_date')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/extractors.py

@@ -30,7 +30,10 @@ from .aenetworks import (
     AENetworksIE,
     HistoryTopicIE,
 )
-from .afreecatv import AfreecaTVIE
+from .afreecatv import (
+    AfreecaTVIE,
+    AfreecaTVGlobalIE,
+)
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -248,6 +251,7 @@ from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .discoverygo import DiscoveryGoIE
+from .disney import DisneyIE
 from .dispeak import DigitallySpeakingIE
 from .dropbox import DropboxIE
 from .dw import (
@@ -981,6 +985,7 @@ from .tv2 import (
 )
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tva import TVAIE
 from .tvanouvelles import (
     TVANouvellesIE,
     TVANouvellesArticleIE,

youtube_dl/extractor/generic.py

@@ -80,6 +80,7 @@ from .piksel import PikselIE
 from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE
+from .openload import OpenloadIE
 
 
 class GenericIE(InfoExtractor):
@@ -2431,6 +2432,12 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 twentymin_urls, ie=TwentyMinutenIE.ie_key())
 
+        # Look for Openload embeds
+        openload_urls = OpenloadIE._extract_urls(webpage)
+        if openload_urls:
+            return _playlist_from_matches(
+                openload_urls, ie=OpenloadIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/jamendo.py

@@ -5,9 +5,27 @@ import re
 
 from ..compat import compat_urlparse
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
-class JamendoIE(InfoExtractor):
+class JamendoBaseIE(InfoExtractor):
+    def _extract_meta(self, webpage, fatal=True):
+        title = self._og_search_title(
+            webpage, default=None) or self._search_regex(
+            r'<title>([^<]+)', webpage,
+            'title', default=None)
+        if title:
+            title = self._search_regex(
+                r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
+        if not title:
+            title = self._html_search_meta(
+                'name', webpage, 'title', fatal=fatal)
+        mobj = re.search(r'(.+) - (.+)', title or '')
+        artist, second = mobj.groups() if mobj else [None] * 2
+        return title, artist, second
+
+
+class JamendoIE(JamendoBaseIE):
     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
@@ -16,7 +34,10 @@ class JamendoIE(InfoExtractor):
             'id': '196219',
             'display_id': 'stories-from-emona-i',
             'ext': 'flac',
-            'title': 'Stories from Emona I',
+            'title': 'Maya Filipič - Stories from Emona I',
+            'artist': 'Maya Filipič',
+            'track': 'Stories from Emona I',
+            'duration': 210,
             'thumbnail': r're:^https?://.*\.jpg'
         }
     }
@@ -28,7 +49,7 @@ class JamendoIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._html_search_meta('name', webpage, 'title')
+        title, artist, track = self._extract_meta(webpage)
 
         formats = [{
             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@@ -46,37 +67,47 @@ class JamendoIE(InfoExtractor):
 
         thumbnail = self._html_search_meta(
             'image', webpage, 'thumbnail', fatal=False)
+        duration = parse_duration(self._search_regex(
+            r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': track_id,
             'display_id': display_id,
             'thumbnail': thumbnail,
             'title': title,
+            'duration': duration,
+            'artist': artist,
+            'track': track,
             'formats': formats
         }
 
 
-class JamendoAlbumIE(InfoExtractor):
+class JamendoAlbumIE(JamendoBaseIE):
     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
         'info_dict': {
             'id': '121486',
-            'title': 'Duck On Cover'
+            'title': 'Shearer - Duck On Cover'
         },
         'playlist': [{
             'md5': 'e1a2fcb42bda30dfac990212924149a8',
             'info_dict': {
                 'id': '1032333',
                 'ext': 'flac',
-                'title': 'Warmachine'
+                'title': 'Shearer - Warmachine',
+                'artist': 'Shearer',
+                'track': 'Warmachine',
             }
         }, {
             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
             'info_dict': {
                 'id': '1032330',
                 'ext': 'flac',
-                'title': 'Without Your Ghost'
+                'title': 'Shearer - Without Your Ghost',
+                'artist': 'Shearer',
+                'track': 'Without Your Ghost',
             }
         }],
         'params': {
@@ -90,18 +121,18 @@ class JamendoAlbumIE(InfoExtractor):
 
         webpage = self._download_webpage(url, mobj.group('display_id'))
 
-        title = self._html_search_meta('name', webpage, 'title')
+        title, artist, album = self._extract_meta(webpage, fatal=False)
 
-        entries = [
-            self.url_result(
-                compat_urlparse.urljoin(url, m.group('path')),
-                ie=JamendoIE.ie_key(),
-                video_id=self._search_regex(
-                    r'/track/(\d+)', m.group('path'),
-                    'track id', default=None))
-            for m in re.finditer(
-                r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
-                webpage)
-        ]
+        entries = [{
+            '_type': 'url_transparent',
+            'url': compat_urlparse.urljoin(url, m.group('path')),
+            'ie_key': JamendoIE.ie_key(),
+            'id': self._search_regex(
+                r'/track/(\d+)', m.group('path'), 'track id', default=None),
+            'artist': artist,
+            'album': album,
+        } for m in re.finditer(
+            r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
+            webpage)]
 
         return self.playlist_result(entries, album_id, title)

youtube_dl/extractor/konserthusetplay.py

@@ -2,7 +2,9 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     float_or_none,
     int_or_none,
 )
@@ -42,12 +44,18 @@ class KonserthusetPlayIE(InfoExtractor):
         player_config = media['playerconfig']
         playlist = player_config['playlist']
 
-        source = next(f for f in playlist if f.get('bitrates'))
+        source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
 
         FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
 
         formats = []
 
+        m3u8_url = source.get('url')
+        if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
         fallback_url = source.get('fallbackUrl')
         fallback_format_id = None
         if fallback_url:
@@ -97,6 +105,13 @@ class KonserthusetPlayIE(InfoExtractor):
         thumbnail = media.get('image')
         duration = float_or_none(media.get('duration'), 1000)
 
+        subtitles = {}
+        captions = source.get('captionsAvailableLanguages')
+        if isinstance(captions, dict):
+            for lang, subtitle_url in captions.items():
+                if lang != 'none' and isinstance(subtitle_url, compat_str):
+                    subtitles.setdefault(lang, []).append({'url': subtitle_url})
+
         return {
             'id': video_id,
             'title': title,
@@ -104,4 +119,5 @@ class KonserthusetPlayIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/mtv.py

@@ -304,7 +304,7 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
 
 class MTVIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtv'
-    _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|full-episodes)/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
 
     _TESTS = [{
@@ -321,6 +321,9 @@ class MTVIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
         'only_matching': True,
+    }, {
+        'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
+        'only_matching': True,
     }]
 
 

youtube_dl/extractor/openload.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_chr
 from ..utils import (
@@ -56,6 +58,12 @@ class OpenloadIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
+            webpage)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
@@ -93,7 +101,7 @@ class OpenloadIE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
-            'ext': determine_ext(title),
+            'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
         }
         return info_dict

youtube_dl/extractor/soundcloud.py

@@ -173,46 +173,54 @@ class SoundcloudIE(InfoExtractor):
             })
 
         # We have to retrieve the url
-        streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
-                       'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
         format_dict = self._download_json(
-            streams_url,
-            track_id, 'Downloading track url')
+            'http://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
+            track_id, 'Downloading track url', query={
+                'client_id': self._CLIENT_ID,
+                'secret_token': secret_token,
+            })
 
         for key, stream_url in format_dict.items():
+            abr = int_or_none(self._search_regex(
+                r'_(\d+)_url', key, 'audio bitrate', default=None))
             if key.startswith('http'):
-                formats.append({
+                stream_formats = [{
                     'format_id': key,
                     'ext': ext,
                     'url': stream_url,
-                    'vcodec': 'none',
-                })
+                }]
             elif key.startswith('rtmp'):
                 # The url doesn't have an rtmp app, we have to extract the playpath
                 url, path = stream_url.split('mp3:', 1)
-                formats.append({
+                stream_formats = [{
                     'format_id': key,
                     'url': url,
                     'play_path': 'mp3:' + path,
                     'ext': 'flv',
-                    'vcodec': 'none',
-                })
+                }]
+            elif key.startswith('hls'):
+                stream_formats = self._extract_m3u8_formats(
+                    stream_url, track_id, 'mp3', entry_protocol='m3u8_native',
+                    m3u8_id=key, fatal=False)
+            else:
+                continue
 
-            if not formats:
-                # We fallback to the stream_url in the original info, this
-                # cannot be always used, sometimes it can give an HTTP 404 error
-                formats.append({
-                    'format_id': 'fallback',
-                    'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
-                    'ext': ext,
-                    'vcodec': 'none',
-                })
+            for f in stream_formats:
+                f['abr'] = abr
 
-            for f in formats:
-                if f['format_id'].startswith('http'):
-                    f['protocol'] = 'http'
-                if f['format_id'].startswith('rtmp'):
-                    f['protocol'] = 'rtmp'
+            formats.extend(stream_formats)
+
+        if not formats:
+            # We fallback to the stream_url in the original info, this
+            # cannot be always used, sometimes it can give an HTTP 404 error
+            formats.append({
+                'format_id': 'fallback',
+                'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+                'ext': ext,
+            })
+
+        for f in formats:
+            f['vcodec'] = 'none'
 
         self._check_formats(formats, track_id)
         self._sort_formats(formats)

youtube_dl/extractor/southpark.py

@@ -6,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
 
 class SouthParkIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.cc.com'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
@@ -75,7 +75,7 @@ class SouthParkDeIE(SouthParkIE):
 
 class SouthParkNlIE(SouthParkIE):
     IE_NAME = 'southpark.nl'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/'
 
     _TESTS = [{

youtube_dl/extractor/srgssr.py

@@ -48,9 +48,6 @@ class SRGSSRIE(InfoExtractor):
     def _real_extract(self, url):
         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
 
-        if bu == 'rts':
-            return self.url_result('rts:%s' % media_id, 'RTS')
-
         media_data = self.get_media_data(bu, media_type, media_id)
 
         metadata = media_data['AssetMetadatas']['AssetMetadata'][0]

youtube_dl/extractor/tva.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    smuggle_url,
+)
+
+
+class TVAIE(InfoExtractor):
+    _VALID_URL = r'https?://videos\.tva\.ca/episode/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://videos.tva.ca/episode/85538',
+        'info_dict': {
+            'id': '85538',
+            'ext': 'mp4',
+            'title': 'Épisode du 25 janvier 2017',
+            'description': 'md5:e9e7fb5532ab37984d2dc87229cadf98',
+            'upload_date': '20170126',
+            'timestamp': 1485442329,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            "https://d18jmrhziuoi7p.cloudfront.net/isl/api/v1/dataservice/Items('%s')" % video_id,
+            video_id, query={
+                '$expand': 'Metadata,CustomId',
+                '$select': 'Metadata,Id,Title,ShortDescription,LongDescription,CreatedDate,CustomId,AverageUserRating,Categories,ShowName',
+                '$format': 'json',
+            })
+        metadata = video_data.get('Metadata', {})
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': video_data['Title'],
+            'url': smuggle_url('ooyala:' + video_data['CustomId'], {'supportedformats': 'm3u8,hds'}),
+            'description': video_data.get('LongDescription') or video_data.get('ShortDescription'),
+            'series': video_data.get('ShowName'),
+            'episode': metadata.get('EpisodeTitle'),
+            'episode_number': int_or_none(metadata.get('EpisodeNumber')),
+            'categories': video_data.get('Categories'),
+            'average_rating': video_data.get('AverageUserRating'),
+            'timestamp': parse_iso8601(video_data.get('CreatedDate')),
+            'ie_key': 'Ooyala',
+        }

youtube_dl/extractor/twitch.py

@@ -209,7 +209,7 @@ class TwitchVodIE(TwitchItemBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?twitch\.tv/[^/]+/v/|
+                            (?:www\.)?twitch\.tv/(?:[^/]+/v|videos)/|
                             player\.twitch\.tv/\?.*?\bvideo=v
                         )
                         (?P<id>\d+)
@@ -259,6 +259,9 @@ class TwitchVodIE(TwitchItemBaseIE):
     }, {
         'url': 'http://player.twitch.tv/?t=5m10s&video=v6528877',
         'only_matching': True,
+    }, {
+        'url': 'https://www.twitch.tv/videos/6528877',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/vevo.py

@@ -4,9 +4,9 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_etree_fromstring,
     compat_str,
     compat_urlparse,
+    compat_HTTPError,
 )
 from ..utils import (
     ExtractorError,
@@ -140,21 +140,6 @@ class VevoIE(VevoBaseIE):
         'url': 'http://www.vevo.com/watch/INS171400764',
         'only_matching': True,
     }]
-    _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com'
-    _SOURCE_TYPES = {
-        0: 'youtube',
-        1: 'brightcove',
-        2: 'http',
-        3: 'hls_ios',
-        4: 'hls',
-        5: 'smil',  # http
-        7: 'f4m_cc',
-        8: 'f4m_ak',
-        9: 'f4m_l3',
-        10: 'ism',
-        13: 'smil',  # rtmp
-        18: 'dash',
-    }
     _VERSIONS = {
         0: 'youtube',  # only in AuthenticateVideo videoVersions
         1: 'level3',
@@ -163,41 +148,6 @@ class VevoIE(VevoBaseIE):
         4: 'amazon',
     }
 
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        formats = []
-        els = smil.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
-        for el in els:
-            src = el.attrib['src']
-            m = re.match(r'''(?xi)
-                (?P<ext>[a-z0-9]+):
-                (?P<path>
-                    [/a-z0-9]+     # The directory and main part of the URL
-                    _(?P<tbr>[0-9]+)k
-                    _(?P<width>[0-9]+)x(?P<height>[0-9]+)
-                    _(?P<vcodec>[a-z0-9]+)
-                    _(?P<vbr>[0-9]+)
-                    _(?P<acodec>[a-z0-9]+)
-                    _(?P<abr>[0-9]+)
-                    \.[a-z0-9]+  # File extension
-                )''', src)
-            if not m:
-                continue
-
-            format_url = self._SMIL_BASE_URL + m.group('path')
-            formats.append({
-                'url': format_url,
-                'format_id': 'smil_' + m.group('tbr'),
-                'vcodec': m.group('vcodec'),
-                'acodec': m.group('acodec'),
-                'tbr': int(m.group('tbr')),
-                'vbr': int(m.group('vbr')),
-                'abr': int(m.group('abr')),
-                'ext': m.group('ext'),
-                'width': int(m.group('width')),
-                'height': int(m.group('height')),
-            })
-        return formats
-
     def _initialize_api(self, video_id):
         req = sanitized_Request(
             'http://www.vevo.com/auth', data=b'')
@@ -214,148 +164,91 @@ class VevoIE(VevoBaseIE):
         self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
 
     def _call_api(self, path, *args, **kwargs):
-        return self._download_json(self._api_url_template % path, *args, **kwargs)
+        try:
+            data = self._download_json(self._api_url_template % path, *args, **kwargs)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                errors = self._parse_json(e.cause.read().decode(), None)['errors']
+                error_message = ', '.join([error['message'] for error in errors])
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
+            raise
+        return data
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        json_url = 'http://api.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
-        response = self._download_json(
-            json_url, video_id, 'Downloading video info',
-            'Unable to download info', fatal=False) or {}
-        video_info = response.get('video') or {}
+        self._initialize_api(video_id)
+
+        video_info = self._call_api(
+            'video/%s' % video_id, video_id, 'Downloading api video info',
+            'Failed to download video info')
+
+        video_versions = self._call_api(
+            'video/%s/streams' % video_id, video_id,
+            'Downloading video versions info',
+            'Failed to download video versions info',
+            fatal=False)
+
+        # Some videos are only available via webpage (e.g.
+        # https://github.com/rg3/youtube-dl/issues/9366)
+        if not video_versions:
+            webpage = self._download_webpage(url, video_id)
+            video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
+
+        uploader = None
         artist = None
         featured_artist = None
-        uploader = None
-        view_count = None
+        artists = video_info.get('artists')
+        for curr_artist in artists:
+            if curr_artist.get('role') == 'Featured':
+                featured_artist = curr_artist['name']
+            else:
+                artist = uploader = curr_artist['name']
+
         formats = []
+        for video_version in video_versions:
+            version = self._VERSIONS.get(video_version['version'])
+            version_url = video_version.get('url')
+            if not version_url:
+                continue
 
-        if not video_info:
-            try:
-                self._initialize_api(video_id)
-            except ExtractorError:
-                ytid = response.get('errorInfo', {}).get('ytid')
-                if ytid:
-                    self.report_warning(
-                        'Video is geoblocked, trying with the YouTube video %s' % ytid)
-                    return self.url_result(ytid, 'Youtube', ytid)
-
-                raise
-
-            video_info = self._call_api(
-                'video/%s' % video_id, video_id, 'Downloading api video info',
-                'Failed to download video info')
-
-            video_versions = self._call_api(
-                'video/%s/streams' % video_id, video_id,
-                'Downloading video versions info',
-                'Failed to download video versions info',
-                fatal=False)
-
-            # Some videos are only available via webpage (e.g.
-            # https://github.com/rg3/youtube-dl/issues/9366)
-            if not video_versions:
-                webpage = self._download_webpage(url, video_id)
-                video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
-
-            timestamp = parse_iso8601(video_info.get('releaseDate'))
-            artists = video_info.get('artists')
-            for curr_artist in artists:
-                if curr_artist.get('role') == 'Featured':
-                    featured_artist = curr_artist['name']
-                else:
-                    artist = uploader = curr_artist['name']
-            view_count = int_or_none(video_info.get('views', {}).get('total'))
-
-            for video_version in video_versions:
-                version = self._VERSIONS.get(video_version['version'])
-                version_url = video_version.get('url')
-                if not version_url:
+            if '.ism' in version_url:
+                continue
+            elif '.mpd' in version_url:
+                formats.extend(self._extract_mpd_formats(
+                    version_url, video_id, mpd_id='dash-%s' % version,
+                    note='Downloading %s MPD information' % version,
+                    errnote='Failed to download %s MPD information' % version,
+                    fatal=False))
+            elif '.m3u8' in version_url:
+                formats.extend(self._extract_m3u8_formats(
+                    version_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls-%s' % version,
+                    note='Downloading %s m3u8 information' % version,
+                    errnote='Failed to download %s m3u8 information' % version,
+                    fatal=False))
+            else:
+                m = re.search(r'''(?xi)
+                    _(?P<width>[0-9]+)x(?P<height>[0-9]+)
+                    _(?P<vcodec>[a-z0-9]+)
+                    _(?P<vbr>[0-9]+)
+                    _(?P<acodec>[a-z0-9]+)
+                    _(?P<abr>[0-9]+)
+                    \.(?P<ext>[a-z0-9]+)''', version_url)
+                if not m:
                     continue
 
-                if '.ism' in version_url:
-                    continue
-                elif '.mpd' in version_url:
-                    formats.extend(self._extract_mpd_formats(
-                        version_url, video_id, mpd_id='dash-%s' % version,
-                        note='Downloading %s MPD information' % version,
-                        errnote='Failed to download %s MPD information' % version,
-                        fatal=False))
-                elif '.m3u8' in version_url:
-                    formats.extend(self._extract_m3u8_formats(
-                        version_url, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls-%s' % version,
-                        note='Downloading %s m3u8 information' % version,
-                        errnote='Failed to download %s m3u8 information' % version,
-                        fatal=False))
-                else:
-                    m = re.search(r'''(?xi)
-                        _(?P<width>[0-9]+)x(?P<height>[0-9]+)
-                        _(?P<vcodec>[a-z0-9]+)
-                        _(?P<vbr>[0-9]+)
-                        _(?P<acodec>[a-z0-9]+)
-                        _(?P<abr>[0-9]+)
-                        \.(?P<ext>[a-z0-9]+)''', version_url)
-                    if not m:
-                        continue
-
-                    formats.append({
-                        'url': version_url,
-                        'format_id': 'http-%s-%s' % (version, video_version['quality']),
-                        'vcodec': m.group('vcodec'),
-                        'acodec': m.group('acodec'),
-                        'vbr': int(m.group('vbr')),
-                        'abr': int(m.group('abr')),
-                        'ext': m.group('ext'),
-                        'width': int(m.group('width')),
-                        'height': int(m.group('height')),
-                    })
-        else:
-            timestamp = int_or_none(self._search_regex(
-                r'/Date\((\d+)\)/',
-                video_info['releaseDate'], 'release date', fatal=False),
-                scale=1000)
-            artists = video_info.get('mainArtists')
-            if artists:
-                artist = uploader = artists[0]['artistName']
-
-            featured_artists = video_info.get('featuredArtists')
-            if featured_artists:
-                featured_artist = featured_artists[0]['artistName']
-
-            smil_parsed = False
-            for video_version in video_info['videoVersions']:
-                version = self._VERSIONS.get(video_version['version'])
-                if version == 'youtube':
-                    continue
-                else:
-                    source_type = self._SOURCE_TYPES.get(video_version['sourceType'])
-                    renditions = compat_etree_fromstring(video_version['data'])
-                    if source_type == 'http':
-                        for rend in renditions.findall('rendition'):
-                            attr = rend.attrib
-                            formats.append({
-                                'url': attr['url'],
-                                'format_id': 'http-%s-%s' % (version, attr['name']),
-                                'height': int_or_none(attr.get('frameheight')),
-                                'width': int_or_none(attr.get('frameWidth')),
-                                'tbr': int_or_none(attr.get('totalBitrate')),
-                                'vbr': int_or_none(attr.get('videoBitrate')),
-                                'abr': int_or_none(attr.get('audioBitrate')),
-                                'vcodec': attr.get('videoCodec'),
-                                'acodec': attr.get('audioCodec'),
-                            })
-                    elif source_type == 'hls':
-                        formats.extend(self._extract_m3u8_formats(
-                            renditions.find('rendition').attrib['url'], video_id,
-                            'mp4', 'm3u8_native', m3u8_id='hls-%s' % version,
-                            note='Downloading %s m3u8 information' % version,
-                            errnote='Failed to download %s m3u8 information' % version,
-                            fatal=False))
-                    elif source_type == 'smil' and version == 'level3' and not smil_parsed:
-                        formats.extend(self._extract_smil_formats(
-                            renditions.find('rendition').attrib['url'], video_id, False))
-                        smil_parsed = True
+                formats.append({
+                    'url': version_url,
+                    'format_id': 'http-%s-%s' % (version, video_version['quality']),
+                    'vcodec': m.group('vcodec'),
+                    'acodec': m.group('acodec'),
+                    'vbr': int(m.group('vbr')),
+                    'abr': int(m.group('abr')),
+                    'ext': m.group('ext'),
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                })
         self._sort_formats(formats)
 
         track = video_info['title']
@@ -376,17 +269,15 @@ class VevoIE(VevoBaseIE):
         else:
             age_limit = None
 
-        duration = video_info.get('duration')
-
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'),
-            'timestamp': timestamp,
+            'timestamp': parse_iso8601(video_info.get('releaseDate')),
             'uploader': uploader,
-            'duration': duration,
-            'view_count': view_count,
+            'duration': int_or_none(video_info.get('duration')),
+            'view_count': int_or_none(video_info.get('views', {}).get('total')),
             'age_limit': age_limit,
             'track': track,
             'artist': uploader,

youtube_dl/extractor/vimeo.py

@@ -884,10 +884,14 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
 
     def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
         webpage = self._download_webpage(webpage_url, video_id)
-        data = self._parse_json(self._search_regex(
-            r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
-            default=NO_DEFAULT if video_password_verified else '{}'), video_id)
-        config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
+        config_url = self._html_search_regex(
+            r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'config URL', default=None, group='url')
+        if not config_url:
+            data = self._parse_json(self._search_regex(
+                r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
+                default=NO_DEFAULT if video_password_verified else '{}'), video_id)
+            config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
         if config_url is None:
             self._verify_video_password(webpage_url, video_id, webpage)
             config_url = self._get_config_url(

youtube_dl/extractor/youtube.py

@@ -40,6 +40,7 @@ from ..utils import (
     sanitized_Request,
     smuggle_url,
     str_to_int,
+    try_get,
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
@@ -383,6 +384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
+                'duration': 10,
                 'like_count': int,
                 'dislike_count': int,
                 'start_time': 1,
@@ -402,6 +404,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
                          'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
                          'iconic ep', 'iconic', 'love', 'it'],
+                'duration': 180,
                 'uploader': 'Icona Pop',
                 'uploader_id': 'IconaPop',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
@@ -419,6 +422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
                 'alt_title': 'Tunnel Vision',
                 'description': 'md5:64249768eec3bc4276236606ea996373',
+                'duration': 419,
                 'uploader': 'justintimberlakeVEVO',
                 'uploader_id': 'justintimberlakeVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
@@ -458,6 +462,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
+                'duration': 10,
                 'like_count': int,
                 'dislike_count': int,
             },
@@ -493,6 +498,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'm4a',
                 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
                 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
+                'duration': 244,
                 'uploader': 'AfrojackVEVO',
                 'uploader_id': 'AfrojackVEVO',
                 'upload_date': '20131011',
@@ -512,6 +518,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Taylor Swift - Shake It Off',
                 'alt_title': 'Shake It Off',
                 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
+                'duration': 242,
                 'uploader': 'TaylorSwiftVEVO',
                 'uploader_id': 'TaylorSwiftVEVO',
                 'upload_date': '20140818',
@@ -529,6 +536,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': 'T4XJQO3qol8',
                 'ext': 'mp4',
+                'duration': 219,
                 'upload_date': '20100909',
                 'uploader': 'The Amazing Atheist',
                 'uploader_id': 'TheAmazingAtheist',
@@ -546,6 +554,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
                 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
+                'duration': 142,
                 'uploader': 'The Witcher',
                 'uploader_id': 'WitcherGame',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
@@ -562,6 +571,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
+                'duration': 247,
                 'uploader': 'LloydVEVO',
                 'uploader_id': 'LloydVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
@@ -576,6 +586,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': '__2ABJjxzNo',
                 'ext': 'mp4',
+                'duration': 266,
                 'upload_date': '20100430',
                 'uploader_id': 'deadmau5',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
@@ -596,6 +607,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': 'lqQg6PlCWgI',
                 'ext': 'mp4',
+                'duration': 6085,
                 'upload_date': '20150827',
                 'uploader_id': 'olympic',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
@@ -615,6 +627,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': '_b-2C3KPAM0',
                 'ext': 'mp4',
                 'stretched_ratio': 16 / 9.,
+                'duration': 85,
                 'upload_date': '20110310',
                 'uploader_id': 'AllenMeow',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
@@ -649,6 +662,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'md5:7b81415841e02ecd4313668cde88737a',
                 'description': 'md5:116377fd2963b81ec4ce64b542173306',
+                'duration': 220,
                 'upload_date': '20150625',
                 'uploader_id': 'dorappi2000',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
@@ -691,6 +705,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7335,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -703,6 +718,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7337,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -715,6 +731,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7337,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -727,6 +744,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (zim)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7334,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -768,6 +786,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
                 'alt_title': 'Dark Walk',
                 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
+                'duration': 133,
                 'upload_date': '20151119',
                 'uploader_id': 'IronSoulElf',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
@@ -809,10 +828,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
                 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
+                'duration': 721,
                 'upload_date': '20150127',
                 'uploader_id': 'BerkmanCenter',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
-                'uploader': 'BerkmanCenter',
+                'uploader': 'The Berkman Klein Center for Internet & Society',
                 'license': 'Creative Commons Attribution license (reuse allowed)',
             },
             'params': {
@@ -827,6 +847,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
                 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
+                'duration': 4060,
                 'upload_date': '20151119',
                 'uploader': 'Bernie 2016',
                 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
@@ -871,7 +892,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'iqKdEhx-dD4',
                 'ext': 'mp4',
                 'title': 'Isolation - Mind Field (Ep 1)',
-                'description': 'md5:3a72f23c086a1496c9e2c54a25fa0822',
+                'description': 'md5:8013b7ddea787342608f63a13ddc9492',
+                'duration': 2085,
                 'upload_date': '20170118',
                 'uploader': 'Vsauce',
                 'uploader_id': 'Vsauce',
@@ -1516,11 +1538,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_subtitles = self.extract_subtitles(video_id, video_webpage)
         automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
 
-        if 'length_seconds' not in video_info:
-            self._downloader.report_warning('unable to extract video duration')
-            video_duration = None
-        else:
-            video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
+        video_duration = try_get(
+            video_info, lambda x: int_or_none(x['length_seconds'][0]))
+        if not video_duration:
+            video_duration = parse_duration(self._html_search_meta(
+                'duration', video_webpage, 'video duration'))
 
         # annotations
         video_annotations = None

youtube_dl/utils.py

@@ -1773,7 +1773,7 @@ def parse_duration(s):
     s = s.strip()
 
     days, hours, mins, secs, ms = [None] * 5
-    m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?$', s)
+    m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
     if m:
         days, hours, mins, secs, ms = m.groups()
     else:
@@ -1790,11 +1790,11 @@ def parse_duration(s):
                 )?
                 (?:
                     (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
-                )?$''', s)
+                )?Z?$''', s)
         if m:
             days, hours, mins, secs, ms = m.groups()
         else:
-            m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)$', s)
+            m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
             if m:
                 hours, mins = m.groups()
             else:

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.01.24'
+__version__ = '2017.01.28'