Merge pull request #21 from rg3/master

update

.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 *2016.11.04*. 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 Issues with outdated version will be rejected.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 *2016.11.08*. 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 Issues with outdated version will be rejected.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 **2016.11.04**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.11.08**
 
 ### 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 2016.11.04
+[debug] youtube-dl version 2016.11.08
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,19 @@
+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

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.
 

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/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/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/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/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/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/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__ = '2016.11.04'
+__version__ = '2016.11.08'