Merge branch 'master' into adobepass

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.11.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.11.14.1*. 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 Issues with outdated version will be rejected.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 **2016.11.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.11.14.1**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.11.02
+[debug] youtube-dl version 2016.11.14.1
 [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

@@ -1,6 +1,60 @@
-version <unreleased>
+version 2016.11.14.1
+
+Core
++ [downoader/fragment,f4m,hls] Respect HTTP headers from info dict
+* [extractor/common] Fix media templates with Bandwidth substitution pattern in
+  MPD manifests (#11175)
+* [extractor/common] Improve thumbnail extraction from JSON-LD
 
 Extractors
++ [nrk] Workaround geo restriction
++ [nrk] Improve error detection and messages
++ [afreecatv] Add support for vod.afreecatv.com (#11174)
+* [cda] Fix and improve extraction (#10929, #10936)
+* [plays] Fix extraction (#11165)
+* [eagleplatform] Fix extraction (#11160)
++ [audioboom] Recognize /posts/ URLs (#11149)
+
+
+version 2016.11.08.1
+
+Extractors
+* [espn:article] Fix support for espn.com articles
+* [franceculture] Fix extraction (#11140)
+
+
+version 2016.11.08
+
+Extractors
+* [tmz:article] Fix extraction (#11052)
+* [espn] Fix extraction (#11041)
+* [mitele] Fix extraction after website redesign (#10824)
+- [ard] Remove age restriction check (#11129)
+* [generic] Improve support for pornhub.com embeds (#11100)
++ [generic] Add support for redtube.com embeds (#11099)
++ [generic] Add support for drtuber.com embeds (#11098)
++ [redtube] Add support for embed URLs
++ [drtuber] Add support for embed URLs
++ [yahoo] Improve content id extraction (#11088)
+* [toutv] Relax URL regular expression (#11121)
+
+
+version 2016.11.04
+
+Core
+* [extractor/common] Tolerate malformed RESOLUTION attribute in m3u8
+  manifests (#11113)
+* [downloader/ism] Fix AVC Decoder Configuration Record
+
+Extractors
++ [fox9] Add support for fox9.com (#11110)
++ [anvato] Extract more metadata and improve formats extraction
+* [vodlocker] Improve removed videos detection (#11106)
++ [vzaar] Add support for vzaar.com (#11093)
++ [vice] Add support for uplynk preplay videos (#11101)
+* [tubitv] Fix extraction (#11061)
++ [shahid] Add support for authentication (#11091)
++ [radiocanada] Add subtitles support (#11096)
 + [generic] Add support for ISM manifests
 
 

README.md

@@ -758,7 +758,7 @@ Once the video is fully downloaded, use any video player, such as [mpv](https://
 
 ### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
 
-It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies.  Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies and/or HTTP headers. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`.
 
 It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
 

docs/supportedsites.md

@@ -225,6 +225,7 @@
  - **EroProfile**
  - **Escapist**
  - **ESPN**
+ - **ESPNArticle**
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
@@ -247,6 +248,7 @@
  - **FootyRoom**
  - **Formula1**
  - **FOX**
+ - **FOX9**
  - **Foxgay**
  - **foxnews**: Fox News and Fox Business Video
  - **foxnews:article**
@@ -870,6 +872,7 @@
  - **vube**: Vube.com
  - **VuClip**
  - **VyboryMos**
+ - **Vzaar**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**

youtube_dl/downloader/f4m.py

@@ -314,7 +314,8 @@ class F4mFD(FragmentFD):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
         self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
-        urlh = self.ydl.urlopen(man_url)
+
+        urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
         man_url = urlh.geturl()
         # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
         # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
@@ -387,7 +388,10 @@ class F4mFD(FragmentFD):
             url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
             frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
             try:
-                success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
+                success = ctx['dl'].download(frag_filename, {
+                    'url': url_parsed.geturl(),
+                    'http_headers': info_dict.get('http_headers'),
+                })
                 if not success:
                     return False
                 (down, frag_sanitized) = sanitize_open(frag_filename, 'rb')

youtube_dl/downloader/fragment.py

@@ -9,6 +9,7 @@ from ..utils import (
     error_to_compat_str,
     encodeFilename,
     sanitize_open,
+    sanitized_Request,
 )
 
 
@@ -37,6 +38,10 @@ class FragmentFD(FileDownloader):
     def report_skip_fragment(self, fragment_name):
         self.to_screen('[download] Skipping fragment %s...' % fragment_name)
 
+    def _prepare_url(self, info_dict, url):
+        headers = info_dict.get('http_headers')
+        return sanitized_Request(url, None, headers) if headers else url
+
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)
         self._start_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -59,7 +59,8 @@ class HlsFD(FragmentFD):
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
-        manifest = self.ydl.urlopen(man_url).read()
+
+        manifest = self.ydl.urlopen(self._prepare_url(info_dict, man_url)).read()
 
         s = manifest.decode('utf-8', 'ignore')
 
@@ -112,7 +113,10 @@ class HlsFD(FragmentFD):
                     count = 0
                     while count <= fragment_retries:
                         try:
-                            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                            success = ctx['dl'].download(frag_filename, {
+                                'url': frag_url,
+                                'http_headers': info_dict.get('http_headers'),
+                            })
                             if not success:
                                 return False
                             down, frag_sanitized = sanitize_open(frag_filename, 'rb')

youtube_dl/extractor/afreecatv.py

@@ -11,6 +11,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
+    update_url_query,
     xpath_element,
     xpath_text,
 )
@@ -18,12 +19,18 @@ from ..utils import (
 
 class AfreecaTVIE(InfoExtractor):
     IE_DESC = 'afreecatv.com'
-    _VALID_URL = r'''(?x)^
+    _VALID_URL = r'''(?x)
-        https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
+                    https?://
-        (?:
+                        (?:
-            /app/(?:index|read_ucc_bbs)\.cgi|
+                            (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
-            /player/[Pp]layer\.(?:swf|html))
+                            (?:
-        \?.*?\bnTitleNo=(?P<id>\d+)'''
+                                /app/(?:index|read_ucc_bbs)\.cgi|
+                                /player/[Pp]layer\.(?:swf|html)
+                            )\?.*?\bnTitleNo=|
+                            vod\.afreecatv\.com/PLAYER/STATION/
+                        )
+                        (?P<id>\d+)
+                    '''
     _TESTS = [{
         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
@@ -66,6 +73,9 @@ class AfreecaTVIE(InfoExtractor):
     }, {
         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
         'only_matching': True,
+    }, {
+        'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -83,7 +93,9 @@ class AfreecaTVIE(InfoExtractor):
         info_url = compat_urlparse.urlunparse(parsed_url._replace(
             netloc='afbbs.afreecatv.com:8080',
             path='/api/video/get_video_info.php'))
-        video_xml = self._download_xml(info_url, video_id)
+
+        video_xml = self._download_xml(
+            update_url_query(info_url, {'nTitleNo': video_id}), video_id)
 
         if xpath_element(video_xml, './track/video/file') is None:
             raise ExtractorError('Specified AfreecaTV video does not exist',

youtube_dl/extractor/anvato.py

@@ -157,22 +157,16 @@ class AnvatoIE(InfoExtractor):
             video_data_url, video_id, transform_source=strip_jsonp,
             data=json.dumps(payload).encode('utf-8'))
 
-    def _extract_anvato_videos(self, webpage, video_id):
+    def _get_anvato_videos(self, access_key, video_id):
-        anvplayer_data = self._parse_json(self._html_search_regex(
-            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
-            'Anvato player data'), video_id)
-
-        video_id = anvplayer_data['video']
-        access_key = anvplayer_data['accessKey']
-
         video_data = self._get_video_json(access_key, video_id)
 
         formats = []
         for published_url in video_data['published_urls']:
             video_url = published_url['embed_url']
+            media_format = published_url.get('format')
             ext = determine_ext(video_url)
 
-            if ext == 'smil':
+            if ext == 'smil' or media_format == 'smil':
                 formats.extend(self._extract_smil_formats(video_url, video_id))
                 continue
 
@@ -183,7 +177,7 @@ class AnvatoIE(InfoExtractor):
                 'tbr': tbr if tbr != 0 else None,
             }
 
-            if ext == 'm3u8':
+            if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
                 # Not using _extract_m3u8_formats here as individual media
                 # playlists are also included in published_urls.
                 if tbr is None:
@@ -194,7 +188,7 @@ class AnvatoIE(InfoExtractor):
                         'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
                         'ext': 'mp4',
                     })
-            elif ext == 'mp3':
+            elif ext == 'mp3' or media_format == 'mp3':
                 a_format['vcodec'] = 'none'
             else:
                 a_format.update({
@@ -218,7 +212,19 @@ class AnvatoIE(InfoExtractor):
             'formats': formats,
             'title': video_data.get('def_title'),
             'description': video_data.get('def_description'),
+            'tags': video_data.get('def_tags', '').split(','),
             'categories': video_data.get('categories'),
             'thumbnail': video_data.get('thumbnail'),
+            'timestamp': int_or_none(video_data.get(
+                'ts_published') or video_data.get('ts_added')),
+            'uploader': video_data.get('mcp_id'),
+            'duration': int_or_none(video_data.get('duration')),
             'subtitles': subtitles,
         }
+
+    def _extract_anvato_videos(self, webpage, video_id):
+        anvplayer_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
+            'Anvato player data'), video_id)
+        return self._get_anvato_videos(
+            anvplayer_data['accessKey'], anvplayer_data['video'])

youtube_dl/extractor/ard.py

@@ -178,8 +178,6 @@ class ARDMediathekIE(InfoExtractor):
             ('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
             ('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
              'Video %s is no longer available'),
-            ('Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.',
-             'This program is only suitable for those aged 12 and older. Video %s is therefore only available between 8 pm and 6 am.'),
         )
 
         for pattern, message in ERRORS:

youtube_dl/extractor/audioboom.py

@@ -6,8 +6,8 @@ from ..utils import float_or_none
 
 
 class AudioBoomIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
         'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
         'info_dict': {
@@ -19,7 +19,10 @@ class AudioBoomIE(InfoExtractor):
             'uploader': 'Steve Czaban',
             'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
         }
-    }
+    }, {
+        'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/cbslocal.py

@@ -22,6 +22,7 @@ class CBSLocalIE(AnvatoIE):
             'thumbnail': 're:^https?://.*',
             'timestamp': 1463440500,
             'upload_date': '20160516',
+            'uploader': 'CBS',
             'subtitles': {
                 'en': 'mincount:5',
             },
@@ -35,6 +36,7 @@ class CBSLocalIE(AnvatoIE):
                 'Syndication\\Curb.tv',
                 'Content\\News'
             ],
+            'tags': ['CBS 2 News Evening'],
         },
     }, {
         # SendtoNews embed

youtube_dl/extractor/cda.py

@@ -5,14 +5,16 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    decode_packed_codes,
     ExtractorError,
-    parse_duration
+    float_or_none,
+    int_or_none,
+    parse_duration,
 )
 
 
 class CDAIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _BASE_URL = 'http://www.cda.pl/'
     _TESTS = [{
         'url': 'http://www.cda.pl/video/5749950c',
         'md5': '6f844bf51b15f31fae165365707ae970',
@@ -21,6 +23,9 @@ class CDAIE(InfoExtractor):
             'ext': 'mp4',
             'height': 720,
             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
+            'description': 'md5:269ccd135d550da90d1662651fcb9772',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'average_rating': float,
             'duration': 39
         }
     }, {
@@ -30,6 +35,11 @@ class CDAIE(InfoExtractor):
             'id': '57413289',
             'ext': 'mp4',
             'title': 'Lądowanie na lotnisku na Maderze',
+            'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'crash404',
+            'view_count': int,
+            'average_rating': float,
             'duration': 137
         }
     }, {
@@ -39,31 +49,55 @@ class CDAIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+        self._set_cookie('cda.pl', 'cda.player', 'html5')
+        webpage = self._download_webpage(
+            self._BASE_URL + '/video/' + video_id, video_id)
 
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
-        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
-
         formats = []
 
+        uploader = self._search_regex(r'''(?x)
+            <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
+            (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
+            <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
+        ''', webpage, 'uploader', default=None, group='uploader')
+        view_count = self._search_regex(
+            r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
+            'view_count', default=None)
+        average_rating = self._search_regex(
+            r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
+            webpage, 'rating', fatal=False, group='rating_value')
+
         info_dict = {
             'id': video_id,
-            'title': title,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'uploader': uploader,
+            'view_count': int_or_none(view_count),
+            'average_rating': float_or_none(average_rating),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'duration': None,
         }
 
         def extract_format(page, version):
-            unpacked = decode_packed_codes(page)
+            json_str = self._search_regex(
-            format_url = self._search_regex(
+                r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
-                r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked,
+                '%s player_json' % version, fatal=False, group='player_data')
-                '%s url' % version, fatal=False, group='url')
+            if not json_str:
-            if not format_url:
+                return
+            player_data = self._parse_json(
+                json_str, '%s player_data' % version, fatal=False)
+            if not player_data:
+                return
+            video = player_data.get('video')
+            if not video or 'file' not in video:
+                self.report_warning('Unable to extract %s version information' % version)
                 return
             f = {
-                'url': format_url,
+                'url': video['file'],
             }
             m = re.search(
                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
@@ -75,9 +109,7 @@ class CDAIE(InfoExtractor):
                 })
             info_dict['formats'].append(f)
             if not info_dict['duration']:
-                info_dict['duration'] = parse_duration(self._search_regex(
+                info_dict['duration'] = parse_duration(video.get('duration'))
-                    r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1",
-                    unpacked, 'duration', fatal=False, group='duration'))
 
         extract_format(webpage, 'default')
 
@@ -85,7 +117,8 @@ class CDAIE(InfoExtractor):
                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
                 webpage):
             webpage = self._download_webpage(
-                href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+                self._BASE_URL + href, video_id,
+                'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
                 # Manually report warning because empty page is returned when
                 # invalid version is requested.

youtube_dl/extractor/common.py

@@ -886,7 +886,7 @@ class InfoExtractor(object):
                         'url': e.get('contentUrl'),
                         'title': unescapeHTML(e.get('name')),
                         'description': unescapeHTML(e.get('description')),
-                        'thumbnail': e.get('thumbnailUrl'),
+                        'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
                         'duration': parse_duration(e.get('duration')),
                         'timestamp': unified_timestamp(e.get('uploadDate')),
                         'filesize': float_or_none(e.get('contentSize')),
@@ -1280,9 +1280,10 @@ class InfoExtractor(object):
                 }
                 resolution = last_info.get('RESOLUTION')
                 if resolution:
-                    width_str, height_str = resolution.split('x')
+                    mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
-                    f['width'] = int(width_str)
+                    if mobj:
-                    f['height'] = int(height_str)
+                        f['width'] = int(mobj.group('width'))
+                        f['height'] = int(mobj.group('height'))
                 # Unified Streaming Platform
                 mobj = re.search(
                     r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url'])
@@ -1702,7 +1703,7 @@ class InfoExtractor(object):
                                 representation_ms_info['fragments'] = [{
                                     'url': media_template % {
                                         'Number': segment_number,
-                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
                                     },
                                     'duration': segment_duration,
                                 } for segment_number in range(
@@ -1720,7 +1721,7 @@ class InfoExtractor(object):
                                 def add_segment_url():
                                     segment_url = media_template % {
                                         'Time': segment_time,
-                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
                                         'Number': segment_number,
                                     }
                                     representation_ms_info['fragments'].append({

youtube_dl/extractor/drtuber.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class DrTuberIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
@@ -25,20 +25,30 @@ class DrTuberIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.drtuber.com/embed/489939',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
+            webpage)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(
+            'http://www.drtuber.com/video/%s' % video_id, display_id)
 
         video_url = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            (r'class="title_watch"[^>]*><p>([^<]+)<',
+            (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
              r'<p[^>]+class="title_substrate">([^<]+)</p>',
              r'<title>([^<]+) - \d+'),
             webpage, 'title')

youtube_dl/extractor/eagleplatform.py

@@ -4,11 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
-    url_basename,
 )
 
 
@@ -77,7 +79,7 @@ class EaglePlatformIE(InfoExtractor):
         if status != 200:
             raise ExtractorError(' '.join(response['errors']), expected=True)
 
-    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
         try:
             response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
         except ExtractorError as ee:
@@ -116,29 +118,38 @@ class EaglePlatformIE(InfoExtractor):
 
         m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
         m3u8_formats = self._extract_m3u8_formats(
-            m3u8_url, video_id,
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
-            'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+            m3u8_id='hls', fatal=False)
         formats.extend(m3u8_formats)
 
-        mp4_url = self._get_video_url(
+        m3u8_formats_dict = {}
+        for f in m3u8_formats:
+            if f.get('height') is not None:
+                m3u8_formats_dict[f['height']] = f
+
+        mp4_data = self._download_json(
             # Secure mp4 URL is constructed according to Player.prototype.mp4 from
             # http://lentaru.media.eagleplatform.com/player/player.js
-            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8),
+            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
-            video_id, 'Downloading mp4 JSON')
+            video_id, 'Downloading mp4 JSON', fatal=False)
-        mp4_url_basename = url_basename(mp4_url)
+        if mp4_data:
-        for m3u8_format in m3u8_formats:
+            for format_id, format_url in mp4_data.get('data', {}).items():
-            mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url'])
+                if not isinstance(format_url, compat_str):
-            if mobj:
-                http_format = m3u8_format.copy()
-                video_url = mp4_url.replace(mp4_url_basename, mobj.group(1))
-                if not self._is_valid_url(video_url, video_id):
                     continue
-                http_format.update({
+                height = int_or_none(format_id)
-                    'url': video_url,
+                if height is not None and m3u8_formats_dict.get(height):
-                    'format_id': m3u8_format['format_id'].replace('hls', 'http'),
+                    f = m3u8_formats_dict[height].copy()
-                    'protocol': 'http',
+                    f.update({
-                })
+                        'format_id': f['format_id'].replace('hls', 'http'),
-                formats.append(http_format)
+                        'protocol': 'http',
+                    })
+                else:
+                    f = {
+                        'format_id': 'http-%s' % format_id,
+                        'height': int_or_none(format_id),
+                    }
+                f['url'] = format_url
+                formats.append(f)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/espn.py

@@ -1,38 +1,117 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    unified_timestamp,
+)
 
 
 class ESPNIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/video/clip(?:\?.*?\bid=|/_/id/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://espn.go.com/video/clip?id=10365079',
-        'md5': '60e5d097a523e767d06479335d1bdc58',
         'info_dict': {
-            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'id': '10365079',
             'ext': 'mp4',
             'title': '30 for 30 Shorts: Judging Jewell',
-            'description': None,
+            'description': 'md5:39370c2e016cb4ecf498ffe75bef7f0f',
+            'timestamp': 1390936111,
+            'upload_date': '20140128',
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['OoyalaExternal'],
     }, {
         # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season
         'url': 'http://espn.go.com/video/clip?id=2743663',
-        'md5': 'f4ac89b59afc7e2d7dbb049523df6768',
         'info_dict': {
-            'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg',
+            'id': '2743663',
             'ext': 'mp4',
             'title': 'Must-See Moments: Best of the MLS season',
+            'description': 'md5:4c2d7232beaea572632bec41004f0aeb',
+            'timestamp': 1449446454,
+            'upload_date': '20151207',
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['OoyalaExternal'],
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
+        'url': 'http://www.espn.com/video/clip?id=10365079',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/video/clip/_/id/17989860',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        clip = self._download_json(
+            'http://api-app.espn.com/v1/video/clips/%s' % video_id,
+            video_id)['videos'][0]
+
+        title = clip['headline']
+
+        format_urls = set()
+        formats = []
+
+        def traverse_source(source, base_source_id=None):
+            for source_id, source in source.items():
+                if isinstance(source, compat_str):
+                    extract_source(source, base_source_id)
+                elif isinstance(source, dict):
+                    traverse_source(
+                        source,
+                        '%s-%s' % (base_source_id, source_id)
+                        if base_source_id else source_id)
+
+        def extract_source(source_url, source_id=None):
+            if source_url in format_urls:
+                return
+            format_urls.add(source_url)
+            ext = determine_ext(source_url)
+            if ext == 'smil':
+                formats.extend(self._extract_smil_formats(
+                    source_url, video_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    source_url, video_id, f4m_id=source_id, fatal=False))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id=source_id, fatal=False))
+            else:
+                formats.append({
+                    'url': source_url,
+                    'format_id': source_id,
+                })
+
+        traverse_source(clip['links']['source'])
+        self._sort_formats(formats)
+
+        description = clip.get('caption') or clip.get('description')
+        thumbnail = clip.get('thumbnail')
+        duration = int_or_none(clip.get('duration'))
+        timestamp = unified_timestamp(clip.get('originalPublishDate'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class ESPNArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
         'only_matching': True,
     }, {
@@ -47,11 +126,12 @@ class ESPNIE(InfoExtractor):
     }, {
         'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
         'only_matching': True,
-    }, {
-        'url': 'http://www.espn.com/video/clip?id=10365079',
-        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if ESPNIE.suitable(url) else super(ESPNArticleIE, cls).suitable(url)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -61,23 +141,5 @@ class ESPNIE(InfoExtractor):
             r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)',
             webpage, 'video id', group='id')
 
-        cms = 'espn'
+        return self.url_result(
-        if 'data-source="intl"' in webpage:
+            'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())
-            cms = 'intl'
-        player_url = 'https://espn.go.com/video/iframe/twitter/?id=%s&cms=%s' % (video_id, cms)
-        player = self._download_webpage(
-            player_url, video_id)
-
-        pcode = self._search_regex(
-            r'["\']pcode=([^"\']+)["\']', player, 'pcode')
-
-        title = remove_end(
-            self._og_search_title(webpage),
-            '- ESPN Video').strip()
-
-        return {
-            '_type': 'url_transparent',
-            'url': 'ooyalaexternal:%s:%s:%s' % (cms, video_id, pcode),
-            'ie_key': 'OoyalaExternal',
-            'title': title,
-        }

youtube_dl/extractor/extractors.py

@@ -267,7 +267,10 @@ from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
-from .espn import ESPNIE
+from .espn import (
+    ESPNIE,
+    ESPNArticleIE,
+)
 from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
@@ -296,6 +299,7 @@ from .footyroom import FootyRoomIE
 from .formula1 import Formula1IE
 from .fourtube import FourTubeIE
 from .fox import FOXIE
+from .fox9 import FOX9IE
 from .foxgay import FoxgayIE
 from .foxnews import (
     FoxNewsIE,

youtube_dl/extractor/fox9.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .anvato import AnvatoIE
+from ..utils import js_to_json
+
+
+class FOX9IE(AnvatoIE):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
+    _TESTS = [{
+        'url': 'http://www.fox9.com/news/215123287-story',
+        'md5': 'd6e1b2572c3bab8a849c9103615dd243',
+        'info_dict': {
+            'id': '314473',
+            'ext': 'mp4',
+            'title': 'Bear climbs tree in downtown Duluth',
+            'description': 'md5:6a36bfb5073a411758a752455408ac90',
+            'duration': 51,
+            'timestamp': 1478123580,
+            'upload_date': '20161102',
+            'uploader': 'EPFOX',
+            'categories': ['News', 'Sports'],
+            'tags': ['news', 'video'],
+        },
+    }, {
+        'url': 'http://www.fox9.com/news/investigators/214070684-story',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._parse_json(
+            self._search_regex(
+                r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;',
+                webpage, 'anvato playlist'),
+            video_id, transform_source=js_to_json)[0]['video']
+
+        return self._get_anvato_videos(
+            'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
+            video_id)

youtube_dl/extractor/franceculture.py

@@ -29,7 +29,7 @@ class FranceCultureIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         video_url = self._search_regex(
-            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
+            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"',
             webpage, 'video path')
 
         title = self._og_search_title(webpage)
@@ -38,7 +38,7 @@ class FranceCultureIE(InfoExtractor):
             '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
             webpage, 'upload date', fatal=False))
         thumbnail = self._search_regex(
-            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
+            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',

youtube_dl/extractor/generic.py

@@ -47,6 +47,8 @@ from .svt import SVTIE
 from .pornhub import PornHubIE
 from .xhamster import XHamsterEmbedIE
 from .tnaflix import TNAFlixNetworkEmbedIE
+from .drtuber import DrTuberIE
+from .redtube import RedTubeIE
 from .vimeo import VimeoIE
 from .dailymotion import (
     DailymotionIE,
@@ -1981,11 +1983,6 @@ class GenericIE(InfoExtractor):
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
-        # Look for embedded PornHub player
-        pornhub_url = PornHubIE._extract_url(webpage)
-        if pornhub_url:
-            return self.url_result(pornhub_url, 'PornHub')
-
         # Look for embedded XHamster player
         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
         if xhamster_urls:
@@ -1996,6 +1993,21 @@ class GenericIE(InfoExtractor):
         if tnaflix_urls:
             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
 
+        # Look for embedded PornHub player
+        pornhub_urls = PornHubIE._extract_urls(webpage)
+        if pornhub_urls:
+            return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
+
+        # Look for embedded DrTuber player
+        drtuber_urls = DrTuberIE._extract_urls(webpage)
+        if drtuber_urls:
+            return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
+
+        # Look for embedded RedTube player
+        redtube_urls = RedTubeIE._extract_urls(webpage)
+        if redtube_urls:
+            return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
+
         # Look for embedded Tvigle player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)

youtube_dl/extractor/mitele.py

@@ -1,19 +1,20 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import uuid
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_str,
     compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
-    get_element_by_attribute,
     int_or_none,
-    remove_start,
     extract_attributes,
     determine_ext,
+    smuggle_url,
+    parse_duration,
 )
 
 
@@ -72,16 +73,14 @@ class MiTeleBaseIE(InfoExtractor):
         }
 
 
-class MiTeleIE(MiTeleBaseIE):
+class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/programas-tv/(?:[^/]+/)(?P<id>[^/]+)/player'
 
     _TESTS = [{
-        'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
+        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
-        # MD5 is unstable
         'info_dict': {
-            'id': '0NF1jJnxS1Wu3pHrmvFyw2',
+            'id': '57b0dfb9c715da65618b4afa',
-            'display_id': 'programa-144',
             'ext': 'mp4',
             'title': 'Tor, la web invisible',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
@@ -91,57 +90,71 @@ class MiTeleIE(MiTeleBaseIE):
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
         },
+        'add_ie': ['Ooyala'],
     }, {
         # no explicit title
-        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
+        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
         'info_dict': {
-            'id': 'eLZSwoEd1S3pVyUm8lc6F',
+            'id': '57b0de3dc915da14058b4876',
-            'display_id': 'programa-226',
             'ext': 'mp4',
-            'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
+            'title': 'Cuarto Milenio Temporada 6 Programa 226',
-            'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
+            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
             'series': 'Cuarto Milenio',
             'season': 'Temporada 6',
             'episode': 'Programa 226',
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
-            'duration': 7312,
+            'duration': 7313,
         },
         'params': {
             'skip_download': True,
         },
+        'add_ie': ['Ooyala'],
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
 
-        webpage = self._download_webpage(url, display_id)
+        gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
+        gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
+        # Get a appKey/uuid for getting the session key
+        appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
+        appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
+        uid = compat_str(uuid.uuid4())
+        session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
+        session_json = self._download_json(session_url, video_id, 'Downloading session keys')
+        sessionKey = compat_str(session_json['sessionKey'])
 
-        info = self._get_player_info(url, webpage)
+        paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
+        paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
+        ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
+        data_p = (
+            'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
+            '/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
+        data = self._download_json(data_p, video_id, 'Downloading data JSON')
+        source = data['hits']['hits'][0]['_source']
+        embedCode = source['offers'][0]['embed_codes'][0]
 
-        title = self._search_regex(
+        titles = source['localizable_titles'][0]
-            r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
+        title = titles.get('title_medium') or titles['title_long']
-            webpage, 'title', default=None)
+        episode = titles['title_sort_name']
+        description = titles['summary_long']
+        titles_series = source['localizable_titles_series'][0]
+        series = titles_series['title_long']
+        titles_season = source['localizable_titles_season'][0]
+        season = titles_season['title_medium']
+        duration = parse_duration(source['videos'][0]['duration'])
 
-        mobj = re.search(r'''(?sx)
+        return {
-                            class="Destacado-text"[^>]*>.*?<h1>\s*
+            '_type': 'url_transparent',
-                            <span>(?P<series>[^<]+)</span>\s*
+            # for some reason only HLS is supported
-                            <span>(?P<season>[^<]+)</span>\s*
+            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
-                            <span>(?P<episode>[^<]+)</span>''', webpage)
+            'id': video_id,
-        series, season, episode = mobj.groups() if mobj else [None] * 3
-
-        if not title:
-            if mobj:
-                title = '%s - %s - %s' % (series, season, episode)
-            else:
-                title = remove_start(self._search_regex(
-                    r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
-
-        info.update({
-            'display_id': display_id,
             'title': title,
-            'description': get_element_by_attribute('class', 'text', webpage),
+            'description': description,
             'series': series,
             'season': season,
             'episode': episode,
-        })
+            'duration': duration,
-        return info
+            'thumbnail': source['images'][0]['url'],
+        }

youtube_dl/extractor/nrk.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
 import re
 
 from .common import InfoExtractor
@@ -14,6 +15,25 @@ from ..utils import (
 
 
 class NRKBaseIE(InfoExtractor):
+    _faked_ip = None
+
+    def _download_webpage_handle(self, *args, **kwargs):
+        # NRK checks X-Forwarded-For HTTP header in order to figure out the
+        # origin of the client behind proxy. This allows to bypass geo
+        # restriction by faking this header's value to some Norway IP.
+        # We will do so once we encounter any geo restriction error.
+        if self._faked_ip:
+            # NB: str is intentional
+            kwargs.setdefault(str('headers'), {})['X-Forwarded-For'] = self._faked_ip
+        return super(NRKBaseIE, self)._download_webpage_handle(*args, **kwargs)
+
+    def _fake_ip(self):
+        # Use fake IP from 37.191.128.0/17 in order to workaround geo
+        # restriction
+        def octet(lb=0, ub=255):
+            return random.randint(lb, ub)
+        self._faked_ip = '37.191.%d.%d' % (octet(128), octet())
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -24,6 +44,8 @@ class NRKBaseIE(InfoExtractor):
         title = data.get('fullTitle') or data.get('mainTitle') or data['title']
         video_id = data.get('id') or video_id
 
+        http_headers = {'X-Forwarded-For': self._faked_ip} if self._faked_ip else {}
+
         entries = []
 
         media_assets = data.get('mediaAssets')
@@ -54,6 +76,7 @@ class NRKBaseIE(InfoExtractor):
                     'duration': duration,
                     'subtitles': subtitles,
                     'formats': formats,
+                    'http_headers': http_headers,
                 })
 
         if not entries:
@@ -70,10 +93,23 @@ class NRKBaseIE(InfoExtractor):
                 }]
 
         if not entries:
-            if data.get('usageRights', {}).get('isGeoBlocked'):
+            message_type = data.get('messageType', '')
-                raise ExtractorError(
+            # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
-                    'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
+            if 'IsGeoBlocked' in message_type and not self._faked_ip:
-                    expected=True)
+                self.report_warning(
+                    'Video is geo restricted, trying to fake IP')
+                self._fake_ip()
+                return self._real_extract(url)
+
+            MESSAGES = {
+                'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
+                'ProgramRightsHasExpired': 'Programmet har gått ut',
+                'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
+            }
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, MESSAGES.get(
+                    message_type, message_type)),
+                expected=True)
 
         conviva = data.get('convivaStatistics') or {}
         series = conviva.get('seriesName') or data.get('seriesTitle')

youtube_dl/extractor/ooyala.py

@@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
     _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
     _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
 
-    def _extract(self, content_tree_url, video_id, domain='example.org'):
+    def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
         content_tree = self._download_json(content_tree_url, video_id)['content_tree']
         metadata = content_tree[list(content_tree)[0]]
         embed_code = metadata['embed_code']
@@ -29,7 +29,7 @@ class OoyalaBaseIE(InfoExtractor):
             self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
             compat_urllib_parse_urlencode({
                 'domain': domain,
-                'supportedFormats': 'mp4,rtmp,m3u8,hds',
+                'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
             }), video_id)
 
         cur_auth_data = auth_data['authorization_data'][embed_code]
@@ -145,8 +145,9 @@ class OoyalaIE(OoyalaBaseIE):
         url, smuggled_data = unsmuggle_url(url, {})
         embed_code = self._match_id(url)
         domain = smuggled_data.get('domain')
+        supportedformats = smuggled_data.get('supportedformats')
         content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
-        return self._extract(content_tree_url, embed_code, domain)
+        return self._extract(content_tree_url, embed_code, domain, supportedformats)
 
 
 class OoyalaExternalIE(OoyalaBaseIE):

youtube_dl/extractor/plays.py

@@ -8,30 +8,31 @@ from ..utils import int_or_none
 
 
 class PlaysTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})'
+    _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})'
-    _TEST = {
+    _TESTS = [{
-        'url': 'http://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
+        'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
         'md5': 'dfeac1198506652b5257a62762cec7bc',
         'info_dict': {
             'id': '56af17f56c95335490',
             'ext': 'mp4',
-            'title': 'When you outplay the Azir wall',
+            'title': 'Bjergsen - When you outplay the Azir wall',
             'description': 'Posted by Bjergsen',
         }
-    }
+    }, {
+        'url': 'https://plays.tv/embeds/56af17f56c95335490',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'https://plays.tv/video/%s' % video_id, video_id)
+
+        info = self._search_json_ld(webpage, video_id,)
 
-        title = self._og_search_title(webpage)
-        content = self._parse_json(
-            self._search_regex(
-                r'R\.bindContent\(({.+?})\);', webpage,
-                'content'), video_id)['content']
         mpd_url, sources = re.search(
             r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
-            content).groups()
+            webpage).groups()
         formats = self._extract_mpd_formats(
             self._proto_relative_url(mpd_url), video_id, mpd_id='DASH')
         for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources):
@@ -42,10 +43,11 @@ class PlaysTVIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
-        return {
+        info.update({
             'id': video_id,
-            'title': title,
             'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage),
             'formats': formats,
-        }
+        })
+
+        return info

youtube_dl/extractor/pornhub.py

@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
                             (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
-                        (?P<id>[0-9a-z]+)
+                        (?P<id>[\da-z]+)
                     '''
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
@@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @classmethod
+    @staticmethod
-    def _extract_url(cls, webpage):
+    def _extract_urls(webpage):
-        mobj = re.search(
+        return re.findall(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
-        if mobj:
+            webpage)
-            return mobj.group('url')
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(

youtube_dl/extractor/redtube.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -10,8 +12,8 @@ from ..utils import (
 
 
 class RedTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.redtube.com/66418',
         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {
@@ -23,11 +25,21 @@ class RedTubeIE(InfoExtractor):
             'view_count': int,
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
+            webpage)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.redtube.com/%s' % video_id, video_id)
 
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)

youtube_dl/extractor/tmz.py

@@ -32,12 +32,15 @@ class TMZArticleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
     _TEST = {
         'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
-        'md5': 'e482a414a38db73087450e3a6ce69d00',
+        'md5': '3316ff838ae5bb7f642537825e1e90d2',
         'info_dict': {
             'id': '0_6snoelag',
-            'ext': 'mp4',
+            'ext': 'mov',
             'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
             'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake.  She\'s watching me."',
+            'timestamp': 1429467813,
+            'upload_date': '20150419',
+            'uploader_id': 'batchUser',
         }
     }
 
@@ -45,12 +48,9 @@ class TMZArticleIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        embedded_video_info_str = self._html_search_regex(
+        embedded_video_info = self._parse_json(self._html_search_regex(
-            r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
+            r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
-
+            video_id)
-        embedded_video_info = self._parse_json(
-            embedded_video_info_str, video_id,
-            transform_source=lambda s: s.replace('\\', ''))
 
         return self.url_result(
             'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])

youtube_dl/extractor/toutv.py

@@ -15,11 +15,11 @@ from ..utils import (
 class TouTvIE(InfoExtractor):
     _NETRC_MACHINE = 'toutv'
     IE_NAME = 'tou.tv'
-    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)'
+    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+E[0-9]+)?)'
     _access_token = None
     _claims = None
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
         'info_dict': {
             'id': '122017',
@@ -33,7 +33,10 @@ class TouTvIE(InfoExtractor):
             'skip_download': True,
         },
         'skip': '404 Not Found',
-    }
+    }, {
+        'url': 'http://ici.tou.tv/hackers',
+        'only_matching': True,
+    }]
 
     def _real_initialize(self):
         email, password = self._get_login_info()

youtube_dl/extractor/vlive.py

@@ -17,7 +17,7 @@ from ..compat import compat_urllib_parse_urlencode
 class VLiveIE(InfoExtractor):
     IE_NAME = 'vlive'
     _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.vlive.tv/video/1326',
         'md5': 'cc7314812855ce56de70a06a27314983',
         'info_dict': {
@@ -27,7 +27,20 @@ class VLiveIE(InfoExtractor):
             'creator': "Girl's Day",
             'view_count': int,
         },
-    }
+    }, {
+        'url': 'http://www.vlive.tv/video/16937',
+        'info_dict': {
+            'id': '16937',
+            'ext': 'mp4',
+            'title': '[V LIVE] 첸백시 걍방',
+            'creator': 'EXO',
+            'view_count': int,
+            'subtitles': 'mincount:12',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -116,7 +129,7 @@ class VLiveIE(InfoExtractor):
 
         subtitles = {}
         for caption in playinfo.get('captions', {}).get('list', []):
-            lang = dict_get(caption, ('language', 'locale', 'country', 'label'))
+            lang = dict_get(caption, ('locale', 'language', 'country', 'label'))
             if lang and caption.get('source'):
                 subtitles[lang] = [{
                     'ext': 'vtt',

youtube_dl/extractor/yahoo.py

@@ -201,6 +201,32 @@ class YahooIE(InfoExtractor):
             },
             'skip': 'redirect to https://www.yahoo.com/music',
         },
+        {
+            # yahoo://article/
+            'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html',
+            'info_dict': {
+                'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
+                'ext': 'mp4',
+                'title': "'True Story' Trailer",
+                'description': 'True Story',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # ytwnews://cavideo/
+            'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
+            'info_dict': {
+                'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff',
+                'ext': 'mp4',
+                'title': '單車天使 - 中文版預',
+                'description': '中文版預',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
     ]
 
     def _real_extract(self, url):
@@ -269,7 +295,8 @@ class YahooIE(InfoExtractor):
                     r'"first_videoid"\s*:\s*"([^"]+)"',
                     r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
                     r'<article[^>]data-uuid=["\']([^"\']+)',
-                    r'yahoo://article/view\?.*\buuid=([^&"\']+)',
+                    r'<meta[^<>]+yahoo://article/view\?.*\buuid=([^&"\']+)',
+                    r'<meta[^<>]+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']',
                 ]
                 video_id = self._search_regex(
                     CONTENT_ID_REGEXES, webpage, 'content ID')

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.11.02'
+__version__ = '2016.11.14.1'