release 2017.02.11

They should not match e.g. cdnapi.kaltura.computernetworks.com/...

.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 *2017.02.04.1*. 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 Issues with outdated version will be rejected.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 **2017.02.04.1**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.11*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.11**
 
 ### 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 2017.02.04.1
+[debug] youtube-dl version 2017.02.11
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -6,6 +6,7 @@ python:
   - "3.3"
   - "3.4"
   - "3.5"
+  - "3.6"
 sudo: false
 script: nosetests test --verbose
 notifications:

AUTHORS

@@ -201,3 +201,4 @@ Stephen Chen
 Fabian Stahl
 Bagira
 Odd Stråbø
+Philip Herzog

ChangeLog

@@ -1,3 +1,55 @@
+version 2017.02.11
+
+Core
++ [utils] Introduce get_elements_by_class and get_elements_by_attribute
+  utility functions
++ [extractor/common] Skip m3u8 manifests protected with Adobe Flash Access
+
+Extractor
+* [pluralsight:course] Fix extraction (#12075)
++ [bbc] Extract m3u8 formats with 320k audio
+* [facebook] Relax video id matching (#11017, #12055, #12056)
++ [corus] Add support for Corus Entertainment sites (#12060, #9164)
++ [pluralsight] Detect blocked account error message (#12070)
++ [bloomberg] Add another video id pattern (#12062)
+* [extractor/commonmistakes] Restrict URL regular expression (#12050)
++ [tvplayer] Add support for tvplayer.com
+
+
+version 2017.02.10
+
+Extractors
+* [xtube] Fix extraction (#12023)
+* [pornhub] Fix extraction (#12007, #12018)
+* [facebook] Improve JS data regular expression (#12042)
+* [kaltura] Improve embed partner id extraction (#12041)
++ [sprout] Add support for sproutonline.com
+* [6play] Improve extraction
++ [scrippsnetworks:watch] Add support for Scripps Networks sites (#10765)
++ [go] Add support for Adobe Pass authentication (#11468, #10831)
+* [6play] Fix extraction (#12011)
++ [nbc] Add support for Adobe Pass authentication (#12006)
+
+
+version 2017.02.07
+
+Core
+* [extractor/common] Fix audio only with audio group in m3u8 (#11995)
++ [downloader/fragment] Respect --no-part
+* [extractor/common] Speed-up HTML5 media entries extraction (#11979)
+
+Extractors
+* [pornhub] Fix extraction (#11997)
++ [canalplus] Add support for cstar.fr (#11990)
++ [extractor/generic] Improve RTMP support (#11993)
++ [gaskrank] Add support for gaskrank.tv (#11685)
+* [bandcamp] Fix extraction for incomplete albums (#11727)
+* [iwara] Fix extraction (#11781)
+* [googledrive] Fix extraction on Python 3.6
++ [videopress] Add support for videopress.com
++ [afreecatv] Extract RTMP formats
+
+
 version 2017.02.04.1
 
 Extractors

docs/supportedsites.md

@@ -11,6 +11,7 @@
  - **4tube**
  - **56.com**
  - **5min**
+ - **6play**
  - **8tracks**
  - **91porn**
  - **9c9media**
@@ -168,6 +169,7 @@
  - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
+ - **Corus**
  - **Coub**
  - **Cracked**
  - **Crackle**
@@ -282,6 +284,7 @@
  - **Gamersyde**
  - **GameSpot**
  - **GameStar**
+ - **Gaskrank**
  - **Gazeta**
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
@@ -307,7 +310,6 @@
  - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
- - **HGTV**
  - **hgtv.com:show**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
@@ -666,6 +668,7 @@
  - **screen.yahoo:search**: Yahoo screen search
  - **Screencast**
  - **ScreencastOMatic**
+ - **scrippsnetworks:watch**
  - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
@@ -675,7 +678,6 @@
  - **Shared**: shared.sx
  - **ShowRoomLive**
  - **Sina**
- - **SixPlay**
  - **skynewsarabia:article**
  - **skynewsarabia:video**
  - **SkySports**
@@ -710,6 +712,7 @@
  - **SportBoxEmbed**
  - **SportDeutschland**
  - **Sportschau**
+ - **Sprout**
  - **sr:mediathek**: Saarländischer Rundfunk
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
@@ -803,6 +806,7 @@
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
+ - **TVPlayer**
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
@@ -859,6 +863,7 @@
  - **videomore:season**
  - **videomore:video**
  - **VideoPremium**
+ - **VideoPress**
  - **videoweed**: VideoWeed
  - **Vidio**
  - **vidme**

test/test_utils.py

@@ -34,6 +34,9 @@ from youtube_dl.utils import (
     find_xpath_attr,
     fix_xml_ampersands,
     get_element_by_class,
+    get_element_by_attribute,
+    get_elements_by_class,
+    get_elements_by_attribute,
     InAdvancePagedList,
     intlist_to_bytes,
     is_html,
@@ -1124,6 +1127,32 @@ The first line
         self.assertEqual(get_element_by_class('foo', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
 
+    def test_get_element_by_attribute(self):
+        html = '''
+            <span class="foo bar">nice</span>
+        '''
+
+        self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
+        self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
+        self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
+
+    def test_get_elements_by_class(self):
+        html = '''
+            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+        '''
+
+        self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_class('no-such-class', html), [])
+
+    def test_get_elements_by_attribute(self):
+        html = '''
+            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+        '''
+
+        self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
+        self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/downloader/external.py

@@ -275,7 +275,7 @@ class FFmpegFD(ExternalFD):
                 args += ['-f', 'mpegts']
             else:
                 args += ['-f', 'mp4']
-                if (ffpp.basename == 'ffmpeg' and is_outdated_version(ffpp._versions['ffmpeg'], '3.2')) and (not info_dict.get('acodec') or info_dict['acodec'].split('.')[0] in ('aac', 'mp4a')):
+                if (ffpp.basename == 'ffmpeg' and is_outdated_version(ffpp._versions['ffmpeg'], '3.2', False)) and (not info_dict.get('acodec') or info_dict['acodec'].split('.')[0] in ('aac', 'mp4a')):
                     args += ['-bsf:a', 'aac_adtstoasc']
         elif protocol == 'rtmp':
             args += ['-f', 'flv']

youtube_dl/downloader/fragment.py

@@ -61,6 +61,7 @@ class FragmentFD(FileDownloader):
                 'noprogress': True,
                 'ratelimit': self.params.get('ratelimit'),
                 'retries': self.params.get('retries', 0),
+                'nopart': self.params.get('nopart', False),
                 'test': self.params.get('test', False),
             }
         )

youtube_dl/extractor/afreecatv.py

@@ -221,10 +221,23 @@ class AfreecaTVGlobalIE(AfreecaTVIE):
                 s_url = s.get('purl')
                 if not s_url:
                     continue
-                # TODO: extract rtmp formats
-                if s.get('stype') == 'HLS':
+                stype = s.get('stype')
+                if stype == 'HLS':
                     formats.extend(self._extract_m3u8_formats(
-                        s_url, channel_id, 'mp4', fatal=False))
+                        s_url, channel_id, 'mp4', m3u8_id=stype, fatal=False))
+                elif stype == 'RTMP':
+                    format_id = [stype]
+                    label = s.get('label')
+                    if label:
+                        format_id.append(label)
+                    formats.append({
+                        'format_id': '-'.join(format_id),
+                        'url': s_url,
+                        'tbr': int_or_none(s.get('bps')),
+                        'height': int_or_none(s.get('brt')),
+                        'ext': 'flv',
+                        'rtmp_live': True,
+                    })
             self._sort_formats(formats)
 
             info.update({

youtube_dl/extractor/bandcamp.py

@@ -209,6 +209,15 @@ class BandcampAlbumIE(InfoExtractor):
             'id': 'entropy-ep',
         },
         'playlist_mincount': 3,
+    }, {
+        # not all tracks have songs
+        'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
+        'info_dict': {
+            'id': 'we-are-the-plague',
+            'title': 'WE ARE THE PLAGUE',
+            'uploader_id': 'insulters',
+        },
+        'playlist_count': 2,
     }]
 
     def _real_extract(self, url):
@@ -217,12 +226,16 @@ class BandcampAlbumIE(InfoExtractor):
         album_id = mobj.group('album_id')
         playlist_id = album_id or uploader_id
         webpage = self._download_webpage(url, playlist_id)
-        tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
-        if not tracks_paths:
+        track_elements = re.findall(
+            r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage)
+        if not track_elements:
             raise ExtractorError('The page doesn\'t contain any tracks')
+        # Only tracks with duration info have songs
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
-            for t_path in tracks_paths]
+            for elem_content, t_path in track_elements
+            if self._html_search_meta('duration', elem_content, default=None)]
+
         title = self._html_search_regex(
             r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
             webpage, 'title', fatal=False)

youtube_dl/extractor/bbc.py

@@ -225,6 +225,8 @@ class BBCCoUkIE(InfoExtractor):
         }
     ]
 
+    _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
+
     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id
@@ -336,6 +338,15 @@ class BBCCoUkIE(InfoExtractor):
                         formats.extend(self._extract_m3u8_formats(
                             href, programme_id, ext='mp4', entry_protocol='m3u8_native',
                             m3u8_id=format_id, fatal=False))
+                        if re.search(self._USP_RE, href):
+                            usp_formats = self._extract_m3u8_formats(
+                                re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
+                                programme_id, ext='mp4', entry_protocol='m3u8_native',
+                                m3u8_id=format_id, fatal=False)
+                            for f in usp_formats:
+                                if f.get('height') and f['height'] > 720:
+                                    continue
+                                formats.append(f)
                     elif transfer_format == 'hds':
                         formats.extend(self._extract_f4m_formats(
                             href, programme_id, f4m_id=format_id, fatal=False))

youtube_dl/extractor/bloomberg.py

@@ -33,6 +33,10 @@ class BloombergIE(InfoExtractor):
         'params': {
             'format': 'best[format_id^=hds]',
         },
+    }, {
+        # data-bmmrid=
+        'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money',
+        'only_matching': True,
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,
@@ -45,9 +49,10 @@ class BloombergIE(InfoExtractor):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(
-            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
-             r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
-            webpage, 'id', group='url', default=None)
+            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+             r'videoId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+             r'data-bmmrid=(["\'])(?P<id>(?:(?!\1).)+)\1'),
+            webpage, 'id', group='id', default=None)
         if not video_id:
             bplayer_data = self._parse_json(self._search_regex(
                 r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)

youtube_dl/extractor/canalplus.py

@@ -27,6 +27,7 @@ class CanalplusIE(InfoExtractor):
                                     (?:www\.)?d8\.tv|
                                     (?:www\.)?c8\.fr|
                                     (?:www\.)?d17\.tv|
+                                    (?:(?:football|www)\.)?cstar\.fr|
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
                                 player\.canalplus\.fr/#/(?P<id>\d+)
@@ -40,6 +41,7 @@ class CanalplusIE(InfoExtractor):
         'd8': 'd8',
         'c8': 'd8',
         'd17': 'd17',
+        'cstar': 'd17',
         'itele': 'itele',
     }
 
@@ -86,6 +88,19 @@ class CanalplusIE(InfoExtractor):
             'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
             'upload_date': '20161014',
         },
+    }, {
+        'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
+        'info_dict': {
+            'id': '1416769',
+            'display_id': 'pid7566-feminines-videos',
+            'ext': 'mp4',
+            'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
+            'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
+            'upload_date': '20160921',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://m.canalplus.fr/?vid=1398231',
         'only_matching': True,

youtube_dl/extractor/common.py

@@ -1208,6 +1208,9 @@ class InfoExtractor(object):
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
 
+        if '#EXT-X-FAXS-CM:' in m3u8_doc:  # Adobe Flash Access
+            return []
+
         formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
 
         format_url = lambda u: (
@@ -1315,8 +1318,8 @@ class InfoExtractor(object):
                         'abr': abr,
                     })
                 f.update(parse_codecs(last_info.get('CODECS')))
-                if audio_in_video_stream.get(last_info.get('AUDIO')) is False:
-                    # TODO: update acodec for for audio only formats with the same GROUP-ID
+                if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none':
+                    # TODO: update acodec for audio only formats with the same GROUP-ID
                     f['acodec'] = 'none'
                 formats.append(f)
                 last_info = {}
@@ -1959,7 +1962,12 @@ class InfoExtractor(object):
         media_tags = [(media_tag, media_type, '')
                       for media_tag, media_type
                       in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
-        media_tags.extend(re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage))
+        media_tags.extend(re.findall(
+            # We only allow video|audio followed by a whitespace or '>'.
+            # Allowing more characters may end up in significant slow down (see
+            # https://github.com/rg3/youtube-dl/issues/11979, example URL:
+            # http://www.porntrex.com/maps/videositemap.xml).
+            r'(?s)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
         for media_tag, media_type, media_content in media_tags:
             media_info = {
                 'formats': [],

youtube_dl/extractor/commonmistakes.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 class CommonMistakesIE(InfoExtractor):
     IE_DESC = False  # Do not list
     _VALID_URL = r'''(?x)
-        (?:url|URL)
+        (?:url|URL)$
     '''
 
     _TESTS = [{

youtube_dl/extractor/corus.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .theplatform import ThePlatformFeedIE
+from ..utils import int_or_none
+
+
+class CorusIE(ThePlatformFeedIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
+        'md5': '05dcbca777bf1e58c2acbb57168ad3a6',
+        'info_dict': {
+            'id': '870923331648',
+            'ext': 'mp4',
+            'title': 'Movie Night Popcorn with Bryan',
+            'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
+            'uploader': 'SHWM-NEW',
+            'upload_date': '20170206',
+            'timestamp': 1486392197,
+        },
+    }, {
+        'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
+        'only_matching': True,
+    }, {
+        'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
+        'only_matching': True,
+    }]
+
+    _TP_FEEDS = {
+        'globaltv': {
+            'feed_id': 'ChQqrem0lNUp',
+            'account_id': 2269680845,
+        },
+        'etcanada': {
+            'feed_id': 'ChQqrem0lNUp',
+            'account_id': 2269680845,
+        },
+        'hgtv': {
+            'feed_id': 'L0BMHXi2no43',
+            'account_id': 2414428465,
+        },
+        'foodnetwork': {
+            'feed_id': 'ukK8o58zbRmJ',
+            'account_id': 2414429569,
+        },
+        'slice': {
+            'feed_id': '5tUJLgV2YNJ5',
+            'account_id': 2414427935,
+        },
+    }
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        feed_info = self._TP_FEEDS[domain.split('.')[0]]
+        return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: {
+            'episode_number': int_or_none(e.get('pl1$episode')),
+            'season_number': int_or_none(e.get('pl1$season')),
+            'series': e.get('pl1$show'),
+        }, {
+            'HLS': {
+                'manifest': 'm3u',
+            },
+            'DesktopHLS Default': {
+                'manifest': 'm3u',
+            },
+            'MP4 MBR': {
+                'manifest': 'm3u',
+            },
+        }, feed_info['account_id'])

youtube_dl/extractor/extractors.py

@@ -202,6 +202,7 @@ from .commonprotocols import (
     RtmpIE,
 )
 from .condenast import CondeNastIE
+from .corus import CorusIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
 from .criterion import CriterionIE
@@ -349,6 +350,7 @@ from .gameone import (
 from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
+from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
@@ -380,10 +382,7 @@ from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
-from .hgtv import (
-    HGTVIE,
-    HGTVComShowIE,
-)
+from .hgtv import HGTVComShowIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
@@ -837,6 +836,7 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
+from .scrippsnetworks import ScrippsNetworksWatchIE
 from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
@@ -894,6 +894,7 @@ from .sport5 import Sport5IE
 from .sportbox import SportBoxEmbedIE
 from .sportdeutschland import SportDeutschlandIE
 from .sportschau import SportschauIE
+from .sprout import SproutIE
 from .srgssr import (
     SRGSSRIE,
     SRGSSRPlayIE,
@@ -1016,6 +1017,7 @@ from .tvplay import (
     TVPlayIE,
     ViafreeIE,
 )
+from .tvplayer import TVPlayerIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
@@ -1095,6 +1097,7 @@ from .videomore import (
     VideomoreSeasonIE,
 )
 from .videopremium import VideoPremiumIE
+from .videopress import VideoPressIE
 from .vidio import VidioIE
 from .vidme import (
     VidmeIE,

youtube_dl/extractor/facebook.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -134,6 +135,46 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20161030',
             'uploader': 'CNN',
         },
+    }, {
+        # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
+        'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
+        'info_dict': {
+            'id': '1417995061575415',
+            'ext': 'mp4',
+            'title': 'md5:a7b86ca673f51800cd54687b7f4012fe',
+            'timestamp': 1486648217,
+            'upload_date': '20170209',
+            'uploader': 'Yaroslav Korpan',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
+        'info_dict': {
+            'id': '1072691702860471',
+            'ext': 'mp4',
+            'title': 'md5:ae2d22a93fbb12dad20dc393a869739d',
+            'timestamp': 1477305000,
+            'upload_date': '20161024',
+            'uploader': 'La Guía Del Varón',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
+        'info_dict': {
+            'id': '1396382447100162',
+            'ext': 'mp4',
+            'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3',
+            'timestamp': 1486035494,
+            'upload_date': '20170202',
+            'uploader': 'Elisabeth Ahtn',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -249,7 +290,7 @@ class FacebookIE(InfoExtractor):
             for item in instances:
                 if item[1][0] == 'VideoConfig':
                     video_item = item[2][0]
-                    if video_item.get('video_id') == video_id:
+                    if video_item.get('video_id'):
                         return video_item['videoData']
 
         server_js_data = self._parse_json(self._search_regex(
@@ -262,7 +303,7 @@ class FacebookIE(InfoExtractor):
         if not video_data:
             server_js_data = self._parse_json(
                 self._search_regex(
-                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet',
+                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall)',
                     webpage, 'js data', default='{}'),
                 video_id, transform_source=js_to_json, fatal=False)
             if server_js_data:

youtube_dl/extractor/gaskrank.py

@@ -0,0 +1,123 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    js_to_json,
+    unified_strdate,
+)
+
+
+class GaskrankIE(InfoExtractor):
+    """InfoExtractor for gaskrank.tv"""
+    _VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.html?'
+    _TESTS = [
+        {
+            'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
+            'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
+            'info_dict': {
+                'id': '201601/26955',
+                'ext': 'mp4',
+                'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'categories': ['motorrad-fun'],
+                'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
+                'uploader_id': 'Bikefun',
+                'upload_date': '20170110',
+                'uploader_url': None,
+            }
+        },
+        {
+            'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
+            'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
+            'info_dict': {
+                'id': '201106/15920',
+                'ext': 'mp4',
+                'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'categories': ['racing'],
+                'display_id': 'isle-of-man-tt-2011-michael-du-15920',
+                'uploader_id': 'IOM',
+                'upload_date': '20160506',
+                'uploader_url': 'www.iomtt.com',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        """extract information from gaskrank.tv"""
+        def fix_json(code):
+            """Removes trailing comma in json: {{},} --> {{}}"""
+            return re.sub(r',\s*}', r'}', js_to_json(code))
+
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        categories = [re.match(self._VALID_URL, url).group('categories')]
+        title = self._search_regex(
+            r'movieName\s*:\s*\'([^\']*)\'',
+            webpage, 'title')
+        thumbnail = self._search_regex(
+            r'poster\s*:\s*\'([^\']*)\'',
+            webpage, 'thumbnail', default=None)
+
+        mobj = re.search(
+            r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])',
+            webpage)
+        if mobj is not None:
+            uploader_id = mobj.groupdict().get('uploader_id')
+            upload_date = unified_strdate(mobj.groupdict().get('upload_date'))
+
+        uploader_url = self._search_regex(
+            r'Homepage:\s*<[^>]*>(?P<uploader_url>[^<]*)',
+            webpage, 'uploader_url', default=None)
+        tags = re.findall(
+            r'/tv/tags/[^/]+/"\s*>(?P<tag>[^<]*?)<',
+            webpage)
+
+        view_count = self._search_regex(
+            r'class\s*=\s*"gkRight"(?:[^>]*>\s*<[^>]*)*icon-eye-open(?:[^>]*>\s*<[^>]*)*>\s*(?P<view_count>[0-9\.]*)',
+            webpage, 'view_count', default=None)
+        if view_count:
+            view_count = int_or_none(view_count.replace('.', ''))
+
+        average_rating = self._search_regex(
+            r'itemprop\s*=\s*"ratingValue"[^>]*>\s*(?P<average_rating>[0-9,]+)',
+            webpage, 'average_rating')
+        if average_rating:
+            average_rating = float_or_none(average_rating.replace(',', '.'))
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'playlist\s*:\s*\[([^\]]*)\]',
+                webpage, 'playlist', default='{}'),
+            display_id, transform_source=fix_json, fatal=False)
+
+        video_id = self._search_regex(
+            r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
+            playlist.get('0').get('src'), 'video id')
+
+        formats = []
+        for key in playlist:
+            formats.append({
+                'url': playlist[key]['src'],
+                'format_id': key,
+                'quality': playlist[key].get('quality')})
+        self._sort_formats(formats, field_preference=['format_id'])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'display_id': display_id,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'uploader_url': uploader_url,
+            'tags': tags,
+            'view_count': view_count,
+            'average_rating': average_rating,
+        }

youtube_dl/extractor/generic.py

@@ -29,6 +29,7 @@ from ..utils import (
     UnsupportedError,
     xpath_text,
 )
+from .commonprotocols import RtmpIE
 from .brightcove import (
     BrightcoveLegacyIE,
     BrightcoveNewIE,
@@ -81,6 +82,7 @@ from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE
 from .openload import OpenloadIE
+from .videopress import VideoPressIE
 
 
 class GenericIE(InfoExtractor):
@@ -946,6 +948,19 @@ class GenericIE(InfoExtractor):
                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
             },
         },
+        # jwplayer rtmp
+        {
+            'url': 'http://www.suffolk.edu/sjc/',
+            'info_dict': {
+                'id': 'sjclive',
+                'ext': 'flv',
+                'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
+                'uploader': 'www.suffolk.edu',
+            },
+            'params': {
+                'skip_download': True,
+            }
+        },
         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@@ -1473,6 +1488,21 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
             'add_ie': [TwentyMinutenIE.ie_key()],
+        },
+        {
+            # VideoPress embed
+            'url': 'https://en.support.wordpress.com/videopress/',
+            'info_dict': {
+                'id': 'OcobLTqC',
+                'ext': 'm4v',
+                'title': 'IMG_5786',
+                'timestamp': 1435711927,
+                'upload_date': '20150701',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [VideoPressIE.ie_key()],
         }
         # {
         #     # TODO: find another test
@@ -2438,6 +2468,12 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 openload_urls, ie=OpenloadIE.ie_key())
 
+        # Look for VideoPress embeds
+        videopress_urls = VideoPressIE._extract_urls(webpage)
+        if videopress_urls:
+            return _playlist_from_matches(
+                videopress_urls, ie=VideoPressIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')
@@ -2465,6 +2501,8 @@ class GenericIE(InfoExtractor):
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
+            if RtmpIE.suitable(vurl):
+                return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
@@ -2572,6 +2610,15 @@ class GenericIE(InfoExtractor):
                 'age_limit': age_limit,
             }
 
+            if RtmpIE.suitable(video_url):
+                entry_info_dict.update({
+                    '_type': 'url_transparent',
+                    'ie_key': RtmpIE.ie_key(),
+                    'url': video_url,
+                })
+                entries.append(entry_info_dict)
+                continue
+
             ext = determine_ext(video_url)
             if ext == 'smil':
                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)

youtube_dl/extractor/go.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .adobepass import AdobePassIE
 from ..utils import (
     int_or_none,
     determine_ext,
@@ -13,15 +13,30 @@ from ..utils import (
 )
 
 
-class GoIE(InfoExtractor):
-    _BRANDS = {
-        'abc': '001',
-        'freeform': '002',
-        'watchdisneychannel': '004',
-        'watchdisneyjunior': '008',
-        'watchdisneyxd': '009',
+class GoIE(AdobePassIE):
+    _SITE_INFO = {
+        'abc': {
+            'brand': '001',
+            'requestor_id': 'ABC',
+        },
+        'freeform': {
+            'brand': '002',
+            'requestor_id': 'ABCFamily',
+        },
+        'watchdisneychannel': {
+            'brand': '004',
+            'requestor_id': 'Disney',
+        },
+        'watchdisneyjunior': {
+            'brand': '008',
+            'requestor_id': 'DisneyJunior',
+        },
+        'watchdisneyxd': {
+            'brand': '009',
+            'requestor_id': 'DisneyXD',
+        }
     }
-    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
     _TESTS = [{
         'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
         'info_dict': {
@@ -47,7 +62,8 @@ class GoIE(InfoExtractor):
                 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
                 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
                 r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id')
-        brand = self._BRANDS[sub_domain]
+        site_info = self._SITE_INFO[sub_domain]
+        brand = site_info['brand']
         video_data = self._download_json(
             'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
             video_id)['video'][0]
@@ -63,14 +79,26 @@ class GoIE(InfoExtractor):
             if ext == 'm3u8':
                 video_type = video_data.get('type')
                 if video_type == 'lf':
+                    data = {
+                        'video_id': video_data['id'],
+                        'video_type': video_type,
+                        'brand': brand,
+                        'device': '001',
+                    }
+                    if video_data.get('accesslevel') == '1':
+                        requestor_id = site_info['requestor_id']
+                        resource = self._get_mvpd_resource(
+                            requestor_id, title, video_id, None)
+                        auth = self._extract_mvpd_auth(
+                            url, video_id, requestor_id, resource)
+                        data.update({
+                            'token': auth,
+                            'token_type': 'ap',
+                            'adobe_requestor_id': requestor_id,
+                        })
                     entitlement = self._download_json(
                         'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
-                        video_id, data=urlencode_postdata({
-                            'video_id': video_data['id'],
-                            'video_type': video_type,
-                            'brand': brand,
-                            'device': '001',
-                        }))
+                        video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
                     errors = entitlement.get('errors', {}).get('errors', [])
                     if errors:
                         error_message = ', '.join([error['message'] for error in errors])

youtube_dl/extractor/googledrive.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    lowercase_escape,
 )
 
 
@@ -13,12 +14,12 @@ class GoogleDriveIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
     _TESTS = [{
         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
-        'md5': '881f7700aec4f538571fa1e0eed4a7b6',
+        'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
         'info_dict': {
             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
             'ext': 'mp4',
             'title': 'Big Buck Bunny.mp4',
-            'duration': 46,
+            'duration': 45,
         }
     }, {
         # video id is longer than 28 characters
@@ -55,7 +56,7 @@ class GoogleDriveIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
-            'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
+            'http://docs.google.com/file/d/%s' % video_id, video_id)
 
         reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
         if reason:
@@ -74,7 +75,7 @@ class GoogleDriveIE(InfoExtractor):
             resolution = fmt.split('/')[1]
             width, height = resolution.split('x')
             formats.append({
-                'url': fmt_url,
+                'url': lowercase_escape(fmt_url),
                 'format_id': fmt_id,
                 'resolution': resolution,
                 'width': int_or_none(width),

youtube_dl/extractor/hgtv.py

@@ -2,50 +2,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    js_to_json,
-    smuggle_url,
-)
-
-
-class HGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
-    _TEST = {
-        'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
-        'md5': '',
-        'info_dict': {
-            'id': 'aFH__I_5FBOX',
-            'ext': 'mp4',
-            'title': 'Overnight Success',
-            'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
-            'uploader': 'SHWM-NEW',
-            'timestamp': 1470320034,
-            'upload_date': '20160804',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        embed_vars = self._parse_json(self._search_regex(
-            r'(?s)embed_vars\s*=\s*({.*?});',
-            webpage, 'embed vars'), display_id, js_to_json)
-        return {
-            '_type': 'url_transparent',
-            'url': smuggle_url(
-                'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
-                    'force_smil_url': True
-                }),
-            'series': embed_vars.get('show'),
-            'season_number': int_or_none(embed_vars.get('season')),
-            'episode_number': int_or_none(embed_vars.get('episode')),
-            'ie_key': 'ThePlatform',
-        }
 
 
 class HGTVComShowIE(InfoExtractor):

youtube_dl/extractor/iwara.py

@@ -3,14 +3,18 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
-from ..utils import remove_end
+from ..utils import (
+    int_or_none,
+    mimetype2ext,
+    remove_end,
+)
 
 
 class IwaraIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
     _TESTS = [{
         'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
-        'md5': '1d53866b2c514b23ed69e4352fdc9839',
+        # md5 is unstable
         'info_dict': {
             'id': 'amVwUl1EHpAD9RD',
             'ext': 'mp4',
@@ -23,17 +27,17 @@ class IwaraIE(InfoExtractor):
         'info_dict': {
             'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
             'ext': 'mp4',
-            'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
+            'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4',
             'age_limit': 18,
         },
         'add_ie': ['GoogleDrive'],
     }, {
         'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
-        'md5': '1d85f1e5217d2791626cff5ec83bb189',
+        # md5 is unstable
         'info_dict': {
             'id': '6liAP9s2Ojc',
             'ext': 'mp4',
-            'age_limit': 0,
+            'age_limit': 18,
             'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
             'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
             'upload_date': '20160910',
@@ -52,9 +56,9 @@ class IwaraIE(InfoExtractor):
         # ecchi is 'sexy' in Japanese
         age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
 
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id)
 
-        if not entries:
+        if not video_data:
             iframe_url = self._html_search_regex(
                 r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
                 webpage, 'iframe URL', group='url')
@@ -67,11 +71,25 @@ class IwaraIE(InfoExtractor):
         title = remove_end(self._html_search_regex(
             r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
 
-        info_dict = entries[0]
-        info_dict.update({
+        formats = []
+        for a_format in video_data:
+            format_id = a_format.get('resolution')
+            height = int_or_none(self._search_regex(
+                r'(\d+)p', format_id, 'height', default=None))
+            formats.append({
+                'url': a_format['uri'],
+                'format_id': format_id,
+                'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
+                'height': height,
+                'width': int_or_none(height / 9.0 * 16.0 if height else None),
+                'quality': 1 if format_id == 'Source' else 0,
+            })
+
+        self._sort_formats(formats)
+
+        return {
             'id': video_id,
             'title': title,
             'age_limit': age_limit,
-        })
-
-        return info_dict
+            'formats': formats,
+        }

youtube_dl/extractor/kaltura.py

@@ -23,11 +23,11 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)|
                     https?://
-                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/
+                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
                         (?:
                             (?:
                                 # flash player
-                                index\.php/kwidget|
+                                index\.php/(?:kwidget|extwidget/preview)|
                                 # html5 player
                                 html5/html5lib/[^/]+/mwEmbedFrame\.php
                             )
@@ -94,6 +94,14 @@ class KalturaIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+        },
+        {
+            'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
+            'only_matching': True,
         }
     ]
 
@@ -112,7 +120,7 @@ class KalturaIE(InfoExtractor):
             re.search(
                 r'''(?xs)
                     (?P<q1>["\'])
-                        (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/(?:(?!(?P=q1)).)*(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
+                        (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
                     (?P=q1).*?
                     (?:
                         entry_?[Ii]d|
@@ -209,6 +217,8 @@ class KalturaIE(InfoExtractor):
                 partner_id = params['wid'][0][1:]
             elif 'p' in params:
                 partner_id = params['p'][0]
+            elif 'partner_id' in params:
+                partner_id = params['partner_id'][0]
             else:
                 raise ExtractorError('Invalid URL', expected=True)
             if 'entry_id' in params:

youtube_dl/extractor/nbc.py

@@ -4,23 +4,26 @@ import re
 
 from .common import InfoExtractor
 from .theplatform import ThePlatformIE
+from .adobepass import AdobePassIE
+from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     find_xpath_attr,
     lowercase_escape,
     smuggle_url,
     unescapeHTML,
     update_url_query,
+    int_or_none,
 )
 
 
-class NBCIE(InfoExtractor):
+class NBCIE(AdobePassIE):
     _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
 
     _TESTS = [
         {
-            'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
+            'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
             'info_dict': {
-                'id': '112966',
+                'id': '2848237',
                 'ext': 'mp4',
                 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
                 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
@@ -69,7 +72,7 @@ class NBCIE(InfoExtractor):
             # HLS streams requires the 'hdnea3' cookie
             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
             'info_dict': {
-                'id': 'n1806',
+                'id': '101528f5a9e8127b107e98c5e6ce4638',
                 'ext': 'mp4',
                 'title': 'Goliath',
                 'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
@@ -87,21 +90,57 @@ class NBCIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
-            [
-                r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
-                r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
-                r'"embedURL"\s*:\s*"([^"]+)"'
-            ],
-            webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
-        if theplatform_url.startswith('//'):
-            theplatform_url = 'http:' + theplatform_url
-        return {
+        info = {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': smuggle_url(theplatform_url, {'source_url': url}),
             'id': video_id,
         }
+        video_data = None
+        preload = self._search_regex(
+            r'PRELOAD\s*=\s*({.+})', webpage, 'preload data', default=None)
+        if preload:
+            preload_data = self._parse_json(preload, video_id)
+            path = compat_urllib_parse_urlparse(url).path.rstrip('/')
+            entity_id = preload_data.get('xref', {}).get(path)
+            video_data = preload_data.get('entities', {}).get(entity_id)
+        if video_data:
+            query = {
+                'mbr': 'true',
+                'manifest': 'm3u',
+            }
+            video_id = video_data['guid']
+            title = video_data['title']
+            if video_data.get('entitlement') == 'auth':
+                resource = self._get_mvpd_resource(
+                    'nbcentertainment', title, video_id,
+                    video_data.get('vChipRating'))
+                query['auth'] = self._extract_mvpd_auth(
+                    url, video_id, 'nbcentertainment', resource)
+            theplatform_url = smuggle_url(update_url_query(
+                'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
+                query), {'force_smil_url': True})
+            info.update({
+                'id': video_id,
+                'title': title,
+                'url': theplatform_url,
+                'description': video_data.get('description'),
+                'keywords': video_data.get('keywords'),
+                'season_number': int_or_none(video_data.get('seasonNumber')),
+                'episode_number': int_or_none(video_data.get('episodeNumber')),
+                'series': video_data.get('showName'),
+            })
+        else:
+            theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
+                [
+                    r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+                    r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
+                    r'"embedURL"\s*:\s*"([^"]+)"'
+                ],
+                webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
+            if theplatform_url.startswith('//'):
+                theplatform_url = 'http:' + theplatform_url
+            info['url'] = smuggle_url(theplatform_url, {'source_url': url})
+        return info
 
 
 class NBCSportsVPlayerIE(InfoExtractor):

youtube_dl/extractor/pluralsight.py

@@ -18,6 +18,7 @@ from ..utils import (
     parse_duration,
     qualities,
     srt_subtitles_timecode,
+    update_url_query,
     urlencode_postdata,
 )
 
@@ -92,6 +93,10 @@ class PluralsightIE(PluralsightBaseIE):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
+            BLOCKED = 'Your account has been blocked due to suspicious activity'
+            if BLOCKED in response:
+                raise ExtractorError(
+                    'Unable to login: %s' % BLOCKED, expected=True)
             raise ExtractorError('Unable to log in')
 
     def _get_subtitles(self, author, clip_id, lang, name, duration, video_id):
@@ -327,25 +332,44 @@ class PluralsightCourseIE(PluralsightBaseIE):
         # TODO: PSM cookie
 
         course = self._download_json(
-            '%s/data/course/%s' % (self._API_BASE, course_id),
-            course_id, 'Downloading course JSON')
+            '%s/player/functions/rpc' % self._API_BASE, course_id,
+            'Downloading course JSON',
+            data=json.dumps({
+                'fn': 'bootstrapPlayer',
+                'payload': {
+                    'courseId': course_id,
+                }
+            }).encode('utf-8'),
+            headers={
+                'Content-Type': 'application/json;charset=utf-8'
+            })['payload']['course']
 
         title = course['title']
+        course_name = course['name']
+        course_data = course['modules']
         description = course.get('description') or course.get('shortDescription')
 
-        course_data = self._download_json(
-            '%s/data/course/content/%s' % (self._API_BASE, course_id),
-            course_id, 'Downloading course data JSON')
-
         entries = []
         for num, module in enumerate(course_data, 1):
+            author = module.get('author')
+            module_name = module.get('name')
+            if not author or not module_name:
+                continue
             for clip in module.get('clips', []):
-                player_parameters = clip.get('playerParameters')
-                if not player_parameters:
+                clip_index = int_or_none(clip.get('index'))
+                if clip_index is None:
                     continue
+                clip_url = update_url_query(
+                    '%s/player' % self._API_BASE, query={
+                        'mode': 'live',
+                        'course': course_name,
+                        'author': author,
+                        'name': module_name,
+                        'clip': clip_index,
+                    })
                 entries.append({
                     '_type': 'url_transparent',
-                    'url': '%s/training/player?%s' % (self._API_BASE, player_parameters),
+                    'url': clip_url,
                     'ie_key': PluralsightIE.ie_key(),
                     'chapter': module.get('title'),
                     'chapter_number': num,

youtube_dl/extractor/pornhub.py

@@ -156,7 +156,18 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))
+        video_variables = {}
+        for video_variablename, quote, video_variable in re.findall(
+                r'(player_quality_[0-9]{3,4}p\w+)\s*=\s*(["\'])(.+?)\2;', webpage):
+            video_variables[video_variablename] = video_variable
+
+        video_urls = []
+        for encoded_video_url in re.findall(
+                r'player_quality_[0-9]{3,4}p\s*=(.+?);', webpage):
+            for varname, varval in video_variables.items():
+                encoded_video_url = encoded_video_url.replace(varname, varval)
+            video_urls.append(re.sub(r'[\s+]', '', encoded_video_url))
+
         if webpage.find('"encrypted":true') != -1:
             password = compat_urllib_parse_unquote_plus(
                 self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))

youtube_dl/extractor/scrippsnetworks.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .adobepass import AdobePassIE
+from ..utils import (
+    int_or_none,
+    smuggle_url,
+    update_url_query,
+)
+
+
+class ScrippsNetworksWatchIE(AdobePassIE):
+    IE_NAME = 'scrippsnetworks:watch'
+    _VALID_URL = r'https?://watch\.(?:hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv)\.com/player\.[A-Z0-9]+\.html#(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://watch.hgtv.com/player.HNT.html#0256538',
+        'md5': '26545fd676d939954c6808274bdb905a',
+        'info_dict': {
+            'id': '0256538',
+            'ext': 'mp4',
+            'title': 'Seeking a Wow House',
+            'description': 'Buyers retiring in Palm Springs, California, want a modern house with major wow factor. They\'re also looking for a pool and a large, open floorplan with tall windows looking out at the views.',
+            'uploader': 'SCNI',
+            'upload_date': '20170207',
+            'timestamp': 1486450493,
+        },
+        'skip': 'requires TV provider authentication',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        channel = self._parse_json(self._search_regex(
+            r'"channels"\s*:\s*(\[.+\])',
+            webpage, 'channels'), video_id)[0]
+        video_data = next(v for v in channel['videos'] if v.get('nlvid') == video_id)
+        title = video_data['title']
+        release_url = video_data['releaseUrl']
+        if video_data.get('restricted'):
+            requestor_id = self._search_regex(
+                r'requestorId\s*=\s*"([^"]+)";', webpage, 'requestor id')
+            resource = self._get_mvpd_resource(
+                requestor_id, title, video_id,
+                video_data.get('ratings', [{}])[0].get('rating'))
+            auth = self._extract_mvpd_auth(
+                url, video_id, requestor_id, resource)
+            release_url = update_url_query(release_url, {'auth': auth})
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'url': smuggle_url(release_url, {'force_smil_url': True}),
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailUrl'),
+            'series': video_data.get('showTitle'),
+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episodeNumber')),
+            'ie_key': 'ThePlatform',
+        }

youtube_dl/extractor/sixplay.py

@@ -1,64 +1,101 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    qualities,
-    int_or_none,
-    mimetype2ext,
     determine_ext,
+    int_or_none,
+    try_get,
+    qualities,
 )
 
 
 class SixPlayIE(InfoExtractor):
+    IE_NAME = '6play'
     _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://www.6play.fr/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320',
+        'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',
         'md5': '42310bffe4ba3982db112b9cd3467328',
         'info_dict': {
-            'id': '11495320',
+            'id': '11638450',
             'ext': 'mp4',
-            'title': 'Jamel et ses amis au Marrakech du rire 2015',
-            'description': 'md5:ba2149d5c321d5201b78070ee839d872',
+            'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6',
+            'description': 'md5:308853f6a5f9e2d55a30fc0654de415f',
+            'duration': 39,
+            'series': 'Le meilleur pâtissier',
+        },
+        'params': {
+            'skip_download': True,
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        clip_data = self._download_json(
-            'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id,
-            video_id)
-        video_data = clip_data['videoInfo']
 
+        data = self._download_json(
+            'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id,
+            video_id, query={
+                'csa': 5,
+                'with': 'clips',
+            })
+
+        clip_data = data['clips'][0]
+        title = clip_data['title']
+
+        urls = []
         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []
-        for source in clip_data['sources']:
-            source_type, source_url = source.get('type'), source.get('src')
-            if not source_url or source_type == 'hls/primetime':
+        for asset in clip_data['assets']:
+            asset_url = asset.get('full_physical_path')
+            protocol = asset.get('protocol')
+            if not asset_url or protocol == 'primetime' or asset_url in urls:
                 continue
-            ext = mimetype2ext(source_type) or determine_ext(source_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    source_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
-                formats.extend(self._extract_f4m_formats(
-                    source_url.replace('.m3u8', '.f4m'),
-                    video_id, f4m_id='hds', fatal=False))
-            elif ext == 'mp4':
-                quality = source.get('quality')
+            urls.append(asset_url)
+            container = asset.get('video_container')
+            ext = determine_ext(asset_url)
+            if container == 'm3u8' or ext == 'm3u8':
+                if protocol == 'usp':
+                    asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
+                    formats.extend(self._extract_m3u8_formats(
+                        asset_url, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                    formats.extend(self._extract_f4m_formats(
+                        asset_url.replace('.m3u8', '.f4m'),
+                        video_id, f4m_id='hds', fatal=False))
+                    formats.extend(self._extract_mpd_formats(
+                        asset_url.replace('.m3u8', '.mpd'),
+                        video_id, mpd_id='dash', fatal=False))
+                    formats.extend(self._extract_ism_formats(
+                        re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
+                        video_id, ism_id='mss', fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        asset_url, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+            elif container == 'mp4' or ext == 'mp4':
+                quality = asset.get('video_quality')
                 formats.append({
-                    'url': source_url,
+                    'url': asset_url,
                     'format_id': quality,
                     'quality': quality_key(quality),
                     'ext': ext,
                 })
         self._sort_formats(formats)
 
+        def get(getter):
+            for src in (data, clip_data):
+                v = try_get(src, getter, compat_str)
+                if v:
+                    return v
+
         return {
             'id': video_id,
-            'title': video_data['title'].strip(),
-            'description': video_data.get('description'),
-            'duration': int_or_none(video_data.get('duration')),
-            'series': video_data.get('titlePgm'),
+            'title': title,
+            'description': get(lambda x: x['description']),
+            'duration': int_or_none(clip_data.get('duration')),
+            'series': get(lambda x: x['program']['title']),
             'formats': formats,
         }

youtube_dl/extractor/sportbox.py

@@ -4,11 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import (
-    js_to_json,
-    unified_strdate,
-)
+from ..utils import js_to_json
 
 
 class SportBoxEmbedIE(InfoExtractor):

youtube_dl/extractor/sprout.py

@@ -0,0 +1,52 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .adobepass import AdobePassIE
+from ..utils import (
+    extract_attributes,
+    update_url_query,
+    smuggle_url,
+)
+
+
+class SproutIE(AdobePassIE):
+    _VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
+        'md5': '74bf14128578d1e040c3ebc82088f45f',
+        'info_dict': {
+            'id': '9dexnwtmh8_X',
+            'ext': 'mp4',
+            'title': 'A Cowboy Adventure',
+            'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.',
+            'timestamp': 1437758640,
+            'upload_date': '20150724',
+            'uploader': 'NBCU-SPROUT-NEW',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_component = self._search_regex(
+            r'(?s)(<div[^>]+data-component="video"[^>]*?>)',
+            webpage, 'video component', default=None)
+        if video_component:
+            options = self._parse_json(extract_attributes(
+                video_component)['data-options'], video_id)
+            theplatform_url = options['video']
+            query = {
+                'mbr': 'true',
+                'manifest': 'm3u',
+            }
+            if options.get('protected'):
+                query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout')
+            theplatform_url = smuggle_url(update_url_query(
+                theplatform_url, query), {'force_smil_url': True})
+        else:
+            iframe = self._search_regex(
+                r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)',
+                webpage, 'iframe')
+            theplatform_url = extract_attributes(iframe)['src']
+
+        return self.url_result(theplatform_url, 'ThePlatform')

youtube_dl/extractor/theplatform.py

@@ -306,9 +306,10 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
         },
     }]
 
-    def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
+    def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None):
         real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
         entry = self._download_json(real_url, video_id)['entries'][0]
+        main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None
 
         formats = []
         subtitles = {}
@@ -333,7 +334,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
                 if asset_type in asset_types_query:
                     query.update(asset_types_query[asset_type])
                 cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
-                    smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
+                    main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
                 formats.extend(cur_formats)
                 subtitles = self._merge_subtitles(subtitles, cur_subtitles)
 

youtube_dl/extractor/tvplayer.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError
+from ..utils import (
+    extract_attributes,
+    urlencode_postdata,
+    ExtractorError,
+)
+
+
+class TVPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://tvplayer.com/watch/bbcone',
+        'info_dict': {
+            'id': '89',
+            'ext': 'mp4',
+            'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        current_channel = extract_attributes(self._search_regex(
+            r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)',
+            webpage, 'channel element'))
+        title = current_channel['data-name']
+
+        resource_id = self._search_regex(
+            r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id')
+        platform = self._search_regex(
+            r'platform\s*=\s*"([^"]+)"', webpage, 'platform')
+        token = self._search_regex(
+            r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null')
+        validate = self._search_regex(
+            r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null')
+
+        try:
+            response = self._download_json(
+                'http://api.tvplayer.com/api/v2/stream/live',
+                resource_id, headers={
+                    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                }, data=urlencode_postdata({
+                    'service': 1,
+                    'platform': platform,
+                    'id': resource_id,
+                    'token': token,
+                    'validate': validate,
+                }))['tvplayer']['response']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                response = self._parse_json(
+                    e.cause.read().decode(), resource_id)['tvplayer']['response']
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
+            raise
+
+        formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': resource_id,
+            'display_id': display_id,
+            'title': self._live_title(title),
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/videopress.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    float_or_none,
+    parse_age_limit,
+    qualities,
+    try_get,
+    unified_timestamp,
+    urljoin,
+)
+
+
+class VideoPressIE(InfoExtractor):
+    _VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
+    _TESTS = [{
+        'url': 'https://videopress.com/embed/kUJmAcSf',
+        'md5': '706956a6c875873d51010921310e4bc6',
+        'info_dict': {
+            'id': 'kUJmAcSf',
+            'ext': 'mp4',
+            'title': 'VideoPress Demo',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 634.6,
+            'timestamp': 1434983935,
+            'upload_date': '20150622',
+            'age_limit': 0,
+        },
+    }, {
+        # 17+, requires birth_* params
+        'url': 'https://videopress.com/embed/iH3gstfZ',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
+            webpage)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
+            video_id, query={
+                'birth_month': random.randint(1, 12),
+                'birth_day': random.randint(1, 31),
+                'birth_year': random.randint(1950, 1995),
+            })
+
+        title = video['title']
+
+        def base_url(scheme):
+            return try_get(
+                video, lambda x: x['file_url_base'][scheme], compat_str)
+
+        base_url = base_url('https') or base_url('http')
+
+        QUALITIES = ('std', 'dvd', 'hd')
+        quality = qualities(QUALITIES)
+
+        formats = []
+        for format_id, f in video['files'].items():
+            if not isinstance(f, dict):
+                continue
+            for ext, path in f.items():
+                if ext in ('mp4', 'ogg'):
+                    formats.append({
+                        'url': urljoin(base_url, path),
+                        'format_id': '%s-%s' % (format_id, ext),
+                        'ext': determine_ext(path, ext),
+                        'quality': quality(format_id),
+                    })
+        original_url = try_get(video, lambda x: x['original'], compat_str)
+        if original_url:
+            formats.append({
+                'url': original_url,
+                'format_id': 'original',
+                'quality': len(QUALITIES),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': video.get('poster'),
+            'duration': float_or_none(video.get('duration'), 1000),
+            'timestamp': unified_timestamp(video.get('upload_date')),
+            'age_limit': parse_age_limit(video.get('rating')),
+            'formats': formats,
+        }

youtube_dl/extractor/xtube.py

@@ -53,14 +53,15 @@ class XTubeIE(InfoExtractor):
 
         if not display_id:
             display_id = video_id
-            url = 'http://www.xtube.com/watch.php?v=%s' % video_id
+            url = 'http://www.xtube.com/video-watch/-%s' % video_id
 
         req = sanitized_Request(url)
         req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
         webpage = self._download_webpage(req, display_id)
 
         sources = self._parse_json(self._search_regex(
-            r'sources\s*:\s*({.+?}),', webpage, 'sources'), video_id)
+            r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
+            webpage, 'sources', group='sources'), video_id)
 
         formats = []
         for format_id, format_url in sources.items():
@@ -81,10 +82,10 @@ class XTubeIE(InfoExtractor):
              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
             webpage, 'uploader', fatal=False)
         duration = parse_duration(self._search_regex(
-            r'<dt>Runtime:</dt>\s*<dd>([^<]+)</dd>',
+            r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
             webpage, 'duration', fatal=False))
         view_count = str_to_int(self._search_regex(
-            r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>',
+            r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._html_search_regex(
             r'>Comments? \(([\d,\.]+)\)<',

youtube_dl/utils.py

@@ -337,17 +337,30 @@ def get_element_by_id(id, html):
 
 
 def get_element_by_class(class_name, html):
-    return get_element_by_attribute(
+    """Return the content of the first tag with the specified class in the passed HTML document"""
+    retval = get_elements_by_class(class_name, html)
+    return retval[0] if retval else None
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
+    retval = get_elements_by_attribute(attribute, value, html, escape_value)
+    return retval[0] if retval else None
+
+
+def get_elements_by_class(class_name, html):
+    """Return the content of all tags with the specified class in the passed HTML document as a list"""
+    return get_elements_by_attribute(
         'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
-def get_element_by_attribute(attribute, value, html, escape_value=True):
+def get_elements_by_attribute(attribute, value, html, escape_value=True):
     """Return the content of the tag with the specified attribute in the passed HTML document"""
 
     value = re.escape(value) if escape_value else value
 
-    m = re.search(r'''(?xs)
+    retlist = []
+    for m in re.finditer(r'''(?xs)
         <([a-zA-Z0-9:._-]+)
          (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
          \s+%s=['"]?%s['"]?
@@ -355,16 +368,15 @@ def get_element_by_attribute(attribute, value, html, escape_value=True):
         \s*>
         (?P<content>.*?)
         </\1>
-    ''' % (re.escape(attribute), value), html)
+    ''' % (re.escape(attribute), value), html):
+        res = m.group('content')
 
-    if not m:
-        return None
-    res = m.group('content')
+        if res.startswith('"') or res.startswith("'"):
+            res = res[1:-1]
 
-    if res.startswith('"') or res.startswith("'"):
-        res = res[1:-1]
+        retlist.append(unescapeHTML(res))
 
-    return unescapeHTML(res)
+    return retlist
 
 
 class HTMLAttributeParser(compat_HTMLParser):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.02.04.1'
+__version__ = '2017.02.11'