release 2016.06.19

Removed print statement from code.

Replaced two regex searches with the corret ones.

Removed some unnecessary semicolumns

fixed title extraction

refactored everything to search_regex

processed comments on commit 5650b0d, fixed feedback from flake8

Improved regexes and returns info dict now.

Added support for closertotruth interview URL

Added support for episodes page

.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 *2016.06.18.1*. 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 Issues with outdated version will be rejected.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 **2016.06.18.1**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.19*. 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 Issues with outdated version will be rejected.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 **2016.06.19**
 
 ### 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 2016.06.18.1
+[debug] youtube-dl version 2016.06.19
 [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: {}

README.md

@@ -44,7 +44,7 @@ Or with [MacPorts](https://www.macports.org/):
 Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
-**youtube-dl** is a small command-line program to download videos from
+**youtube-dl** is a command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
 your Unix box, on Windows or on Mac OS X. It is released to the public domain,

docs/supportedsites.md

@@ -44,8 +44,8 @@
  - **appletrailers:section**
  - **archive.org**: archive.org videos
  - **ARD**
- - **ARD:mediathek**: Saarländischer Rundfunk
  - **ARD:mediathek**
+ - **ARD:mediathek**: Saarländischer Rundfunk
  - **arte.tv**
  - **arte.tv:+7**
  - **arte.tv:cinema**
@@ -128,6 +128,7 @@
  - **cliphunter**
  - **ClipRs**
  - **Clipsyndicate**
+ - **CloserToTruth**
  - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
@@ -521,6 +522,7 @@
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
  - **R7**
+ - **R7Article**
  - **radio.de**
  - **radiobremen**
  - **radiocanada**

youtube_dl/extractor/adobetv.py

@@ -156,7 +156,10 @@ class AdobeTVVideoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(url + '?format=json', video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        video_data = self._parse_json(self._search_regex(
+            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
 
         formats = [{
             'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),

youtube_dl/extractor/aftonbladet.py

@@ -24,10 +24,10 @@ class AftonbladetIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         # find internal video meta data
-        meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+        meta_url = 'http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json'
         player_config = self._parse_json(self._html_search_regex(
             r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
-        internal_meta_id = player_config['videoId']
+        internal_meta_id = player_config['aptomaVideoId']
         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')

youtube_dl/extractor/ard.py

@@ -8,7 +8,6 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
-    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
@@ -274,41 +273,3 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
-
-
-class SportschauIE(ARDMediathekIE):
-    IE_NAME = 'Sportschau'
-    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
-    _TESTS = [{
-        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
-        'info_dict': {
-            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
-            'ext': 'mp4',
-            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        base_url = mobj.group('baseurl')
-
-        webpage = self._download_webpage(url, video_id)
-        title = get_element_by_attribute('class', 'headline', webpage)
-        description = self._html_search_meta('description', webpage, 'description')
-
-        info = self._extract_media_info(
-            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
-
-        info.update({
-            'title': title,
-            'description': description,
-        })
-
-        return info

youtube_dl/extractor/arte.py

@@ -180,11 +180,14 @@ class ArteTVBaseIE(InfoExtractor):
 
 class ArteTVPlus7IE(ArteTVBaseIE):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
         'only_matching': True,
+    }, {
+        'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -240,10 +243,10 @@ class ArteTVPlus7IE(ArteTVBaseIE):
             return self._extract_from_json_url(json_url, video_id, lang, title=title)
         # Different kind of embed URL (e.g.
         # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
-        embed_url = self._search_regex(
-            r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1',
-            webpage, 'embed url', group='url')
-        return self.url_result(embed_url)
+        entries = [
+            self.url_result(url)
+            for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
+        return self.playlist_result(entries)
 
 
 # It also uses the arte_vp_url url from the webpage to extract the information
@@ -252,22 +255,17 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
     _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
-        'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
+        'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
         'info_dict': {
-            'id': '72176',
+            'id': '057405-001-A',
             'ext': 'mp4',
-            'title': 'Folge 2 - Corporate Design',
-            'upload_date': '20131004',
+            'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
+            'upload_date': '20150716',
         },
     }, {
         'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
-        'info_dict': {
-            'id': '160676',
-            'ext': 'mp4',
-            'title': 'Monty Python live (mostly)',
-            'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n',
-            'upload_date': '20140805',
-        }
+        'playlist_count': 11,
+        'add_ie': ['Youtube'],
     }, {
         'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
         'only_matching': True,
@@ -349,14 +347,13 @@ class ArteTVCinemaIE(ArteTVPlus7IE):
     _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
 
     _TESTS = [{
-        'url': 'http://cinema.arte.tv/de/node/38291',
-        'md5': '6b275511a5107c60bacbeeda368c3aa1',
+        'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
+        'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
         'info_dict': {
-            'id': '055876-000_PWA12025-D',
+            'id': '062494-000-A',
             'ext': 'mp4',
-            'title': 'Tod auf dem Nil',
-            'upload_date': '20160122',
-            'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
+            'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
+            'upload_date': '20150807',
         },
     }]
 

youtube_dl/extractor/azubu.py

@@ -46,6 +46,7 @@ class AzubuIE(InfoExtractor):
                 'uploader_id': 272749,
                 'view_count': int,
             },
+            'skip': 'Channel offline',
         },
     ]
 
@@ -56,22 +57,26 @@ class AzubuIE(InfoExtractor):
             'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
 
         title = data['title'].strip()
-        description = data['description']
-        thumbnail = data['thumbnail']
-        view_count = data['view_count']
-        uploader = data['user']['username']
-        uploader_id = data['user']['id']
+        description = data.get('description')
+        thumbnail = data.get('thumbnail')
+        view_count = data.get('view_count')
+        user = data.get('user', {})
+        uploader = user.get('username')
+        uploader_id = user.get('id')
 
         stream_params = json.loads(data['stream_params'])
 
-        timestamp = float_or_none(stream_params['creationDate'], 1000)
-        duration = float_or_none(stream_params['length'], 1000)
+        timestamp = float_or_none(stream_params.get('creationDate'), 1000)
+        duration = float_or_none(stream_params.get('length'), 1000)
 
         renditions = stream_params.get('renditions') or []
         video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
         if video:
             renditions.append(video)
 
+        if not renditions and not user.get('channel', {}).get('is_live', True):
+            raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True)
+
         formats = [{
             'url': fmt['url'],
             'width': fmt['frameWidth'],

youtube_dl/extractor/bbc.py

@@ -192,6 +192,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'Now it\'s really geo-restricted',
         }, {
             # compact player (https://github.com/rg3/youtube-dl/issues/8147)
             'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',

youtube_dl/extractor/bet.py

@@ -1,31 +1,27 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
-from ..utils import (
-    xpath_text,
-    xpath_with_ns,
-    int_or_none,
-    parse_iso8601,
-)
+from .mtv import MTVServicesInfoExtractor
+from ..utils import unified_strdate
+from ..compat import compat_urllib_parse_urlencode
 
 
-class BetIE(InfoExtractor):
+class BetIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
     _TESTS = [
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': 'news/national/2014/a-conversation-with-president-obama',
+                'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
                 'title': 'A Conversation With President Obama',
-                'description': 'md5:699d0652a350cf3e491cd15cc745b5da',
+                'description': 'President Obama urges persistence in confronting racism and bias.',
                 'duration': 1534,
-                'timestamp': 1418075340,
                 'upload_date': '20141208',
-                'uploader': 'admin',
                 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -35,16 +31,17 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': 'news/national/2014/justice-for-ferguson-a-community-reacts',
+                'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
                 'description': 'A BET News special.',
                 'duration': 1696,
-                'timestamp': 1416942360,
                 'upload_date': '20141125',
-                'uploader': 'admin',
                 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -53,57 +50,32 @@ class BetIE(InfoExtractor):
         }
     ]
 
+    _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
+
+    def _get_feed_query(self, uri):
+        return compat_urllib_parse_urlencode({
+            'uuid': uri,
+        })
+
+    def _extract_mgid(self, webpage):
+        return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
+
         webpage = self._download_webpage(url, display_id)
+        mgid = self._extract_mgid(webpage)
+        videos_info = self._get_videos_info(mgid)
 
-        media_url = compat_urllib_parse_unquote(self._search_regex(
-            [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
-            webpage, 'media URL'))
+        info_dict = videos_info['entries'][0]
 
-        video_id = self._search_regex(
-            r'/video/(.*)/_jcr_content/', media_url, 'video id')
+        upload_date = unified_strdate(self._html_search_meta('date', webpage))
+        description = self._html_search_meta('description', webpage)
 
-        mrss = self._download_xml(media_url, display_id)
-
-        item = mrss.find('./channel/item')
-
-        NS_MAP = {
-            'dc': 'http://purl.org/dc/elements/1.1/',
-            'media': 'http://search.yahoo.com/mrss/',
-            'ka': 'http://kickapps.com/karss',
-        }
-
-        title = xpath_text(item, './title', 'title')
-        description = xpath_text(
-            item, './description', 'description', fatal=False)
-
-        timestamp = parse_iso8601(xpath_text(
-            item, xpath_with_ns('./dc:date', NS_MAP),
-            'upload date', fatal=False))
-        uploader = xpath_text(
-            item, xpath_with_ns('./dc:creator', NS_MAP),
-            'uploader', fatal=False)
-
-        media_content = item.find(
-            xpath_with_ns('./media:content', NS_MAP))
-        duration = int_or_none(media_content.get('duration'))
-        smil_url = media_content.get('url')
-
-        thumbnail = media_content.find(
-            xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
-
-        formats = self._extract_smil_formats(smil_url, display_id)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
+        info_dict.update({
             'display_id': display_id,
-            'title': title,
             'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'duration': duration,
-            'formats': formats,
-        }
+            'upload_date': upload_date,
+        })
+
+        return info_dict

youtube_dl/extractor/br.py

@@ -29,7 +29,8 @@ class BRIE(InfoExtractor):
                 'duration': 180,
                 'uploader': 'Reinhard Weber',
                 'upload_date': '20150422',
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
@@ -40,7 +41,8 @@ class BRIE(InfoExtractor):
                 'title': 'Manfred Schreiber ist tot',
                 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
                 'duration': 26,
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
@@ -51,7 +53,8 @@ class BRIE(InfoExtractor):
                 'title': 'Kurzweilig und sehr bewegend',
                 'description': 'md5:0351996e3283d64adeb38ede91fac54e',
                 'duration': 296,
-            }
+            },
+            'skip': '404 not found',
         },
         {
             'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',

youtube_dl/extractor/closertotruth.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class CloserToTruthIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
+        'info_dict': {
+            'id': '0_zof1ktre',
+            'display_id': 'solutions-the-mind-body-problem',
+            'ext': 'mov',
+            'title': 'Solutions to the Mind-Body Problem?',
+            'upload_date': '20140221',
+            'timestamp': 1392956007,
+            'uploader_id': 'CTTXML'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://closertotruth.com/episodes/how-do-brains-work',
+        'info_dict': {
+            'id': '0_iuxai6g6',
+            'display_id': 'how-do-brains-work',
+            'ext': 'mov',
+            'title': 'How do Brains Work?',
+            'upload_date': '20140221',
+            'timestamp': 1392956024,
+            'uploader_id': 'CTTXML'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://closertotruth.com/interviews/1725',
+        'info_dict': {
+            'id': '1725',
+            'title': 'AyaFr-002',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        partner_id = self._search_regex(
+            r'<script[^>]+src=["\'].*?\b(?:partner_id|p)/(\d+)',
+            webpage, 'kaltura partner_id')
+
+        title = self._search_regex(
+            r'<title>(.+?)\s*\|\s*.+?</title>', webpage, 'video title')
+
+        select = self._search_regex(
+            r'(?s)<select[^>]+id="select-version"[^>]*>(.+?)</select>',
+            webpage, 'select version', default=None)
+        if select:
+            entry_ids = set()
+            entries = []
+            for mobj in re.finditer(
+                    r'<option[^>]+value=(["\'])(?P<id>[0-9a-z_]+)(?:#.+?)?\1[^>]*>(?P<title>[^<]+)',
+                    webpage):
+                entry_id = mobj.group('id')
+                if entry_id in entry_ids:
+                    continue
+                entry_ids.add(entry_id)
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': 'kaltura:%s:%s' % (partner_id, entry_id),
+                    'ie_key': 'Kaltura',
+                    'title': mobj.group('title'),
+                })
+            if entries:
+                return self.playlist_result(entries, display_id, title)
+
+        entry_id = self._search_regex(
+            r'<a[^>]+id=(["\'])embed-kaltura\1[^>]+data-kaltura=(["\'])(?P<id>[0-9a-z_]+)\2',
+            webpage, 'kaltura entry_id', group='id')
+
+        return {
+            '_type': 'url_transparent',
+            'display_id': display_id,
+            'url': 'kaltura:%s:%s' % (partner_id, entry_id),
+            'ie_key': 'Kaltura',
+            'title': title
+        }

youtube_dl/extractor/extractors.py

@@ -44,7 +44,6 @@ from .archiveorg import ArchiveOrgIE
 from .ard import (
     ARDIE,
     ARDMediathekIE,
-    SportschauIE,
 )
 from .arte import (
     ArteTvIE,
@@ -141,6 +140,7 @@ from .cliprs import ClipRsIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .closertotruth import CloserToTruthIE
 from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .clyp import ClypIE
@@ -631,7 +631,10 @@ from .qqmusic import (
     QQMusicToplistIE,
     QQMusicPlaylistIE,
 )
-from .r7 import R7IE
+from .r7 import (
+    R7IE,
+    R7ArticleIE,
+)
 from .radiocanada import (
     RadioCanadaIE,
     RadioCanadaAudioVideoIE,
@@ -747,6 +750,7 @@ from .sportbox import (
     SportBoxEmbedIE,
 )
 from .sportdeutschland import SportDeutschlandIE
+from .sportschau import SportschauIE
 from .srgssr import (
     SRGSSRIE,
     SRGSSRPlayIE,

youtube_dl/extractor/mtv.py

@@ -85,9 +85,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 rtmp_video_url = rendition.find('./src').text
                 if rtmp_video_url.endswith('siteunavail.png'):
                     continue
+                new_url = self._transform_rtmp_url(rtmp_video_url)
                 formats.append({
-                    'ext': ext,
-                    'url': self._transform_rtmp_url(rtmp_video_url),
+                    'ext': 'flv' if new_url.startswith('rtmp') else ext,
+                    'url': new_url,
                     'format_id': rendition.get('bitrate'),
                     'width': int(rendition.get('width')),
                     'height': int(rendition.get('height')),

youtube_dl/extractor/r7.py

@@ -2,22 +2,19 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    js_to_json,
-    unescapeHTML,
-    int_or_none,
-)
+from ..utils import int_or_none
 
 
 class R7IE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://
+    _VALID_URL = r'''(?x)
+                        https?://
                         (?:
                             (?:[a-zA-Z]+)\.r7\.com(?:/[^/]+)+/idmedia/|
                             noticias\.r7\.com(?:/[^/]+)+/[^/]+-|
                             player\.r7\.com/video/i/
                         )
                         (?P<id>[\da-f]{24})
-                        '''
+                    '''
     _TESTS = [{
         'url': 'http://videos.r7.com/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-/idmedia/54e7050b0cf2ff57e0279389.html',
         'md5': '403c4e393617e8e8ddc748978ee8efde',
@@ -25,6 +22,7 @@ class R7IE(InfoExtractor):
             'id': '54e7050b0cf2ff57e0279389',
             'ext': 'mp4',
             'title': 'Policiais humilham suspeito à beira da morte: "Morre com dignidade"',
+            'description': 'md5:01812008664be76a6479aa58ec865b72',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 98,
             'like_count': int,
@@ -44,45 +42,72 @@ class R7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            'http://player.r7.com/video/i/%s' % video_id, video_id)
+        video = self._download_json(
+            'http://player-api.r7.com/video/i/%s' % video_id, video_id)
 
-        item = self._parse_json(js_to_json(self._search_regex(
-            r'(?s)var\s+item\s*=\s*({.+?});', webpage, 'player')), video_id)
-
-        title = unescapeHTML(item['title'])
-        thumbnail = item.get('init', {}).get('thumbUri')
-        duration = None
-
-        statistics = item.get('statistics', {})
-        like_count = int_or_none(statistics.get('likes'))
-        view_count = int_or_none(statistics.get('views'))
+        title = video['title']
 
         formats = []
-        for format_key, format_dict in item['playlist'][0].items():
-            src = format_dict.get('src')
-            if not src:
-                continue
-            format_id = format_dict.get('format') or format_key
-            if duration is None:
-                duration = format_dict.get('duration')
-            if '.f4m' in src:
-                formats.extend(self._extract_f4m_formats(src, video_id, preference=-1))
-            elif src.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(src, video_id, 'mp4', preference=-2))
-            else:
-                formats.append({
-                    'url': src,
-                    'format_id': format_id,
-                })
+        media_url_hls = video.get('media_url_hls')
+        if media_url_hls:
+            formats.extend(self._extract_m3u8_formats(
+                media_url_hls, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        media_url = video.get('media_url')
+        if media_url:
+            f = {
+                'url': media_url,
+                'format_id': 'http',
+            }
+            # m3u8 format always matches the http format, let's copy metadata from
+            # one to another
+            m3u8_formats = list(filter(
+                lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+                formats))
+            if len(m3u8_formats) == 1:
+                f_copy = m3u8_formats[0].copy()
+                f_copy.update(f)
+                f_copy['protocol'] = 'http'
+                f = f_copy
+            formats.append(f)
         self._sort_formats(formats)
 
+        description = video.get('description')
+        thumbnail = video.get('thumb')
+        duration = int_or_none(video.get('media_duration'))
+        like_count = int_or_none(video.get('likes'))
+        view_count = int_or_none(video.get('views'))
+
         return {
             'id': video_id,
             'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'duration': duration,
             'like_count': like_count,
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class R7ArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[a-zA-Z]+)\.r7\.com/(?:[^/]+/)+[^/?#&]+-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://tv.r7.com/record-play/balanco-geral/videos/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-16102015',
+        'only_matching': True,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if R7IE.suitable(url) else super(R7ArticleIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'<div[^>]+(?:id=["\']player-|class=["\']embed["\'][^>]+id=["\'])([\da-f]{24})',
+            webpage, 'video id')
+
+        return self.url_result('http://player.r7.com/video/i/%s' % video_id, R7IE.ie_key())

youtube_dl/extractor/sportschau.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .wdr import WDRBaseIE
+from ..utils import get_element_by_attribute
+
+
+class SportschauIE(WDRBaseIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video-?(?P<id>[^/#?]+)\.html'
+    _TEST = {
+        'url': 'http://www.sportschau.de/uefaeuro2016/videos/video-dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100.html',
+        'info_dict': {
+            'id': 'mdb-1140188',
+            'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100',
+            'ext': 'mp4',
+            'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen',
+            'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.',
+            'upload_date': '20160615',
+        },
+        'skip': 'Geo-restricted to Germany',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_wdr_video(webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info

youtube_dl/extractor/wdr.py

@@ -15,7 +15,87 @@ from ..utils import (
 )
 
 
-class WDRIE(InfoExtractor):
+class WDRBaseIE(InfoExtractor):
+    def _extract_wdr_video(self, webpage, display_id):
+        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
+        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
+        json_metadata = self._html_search_regex(
+            r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
+            webpage, 'media link', default=None, flags=re.MULTILINE)
+
+        if not json_metadata:
+            return
+
+        media_link_obj = self._parse_json(json_metadata, display_id,
+                                          transform_source=js_to_json)
+        jsonp_url = media_link_obj['mediaObj']['url']
+
+        metadata = self._download_json(
+            jsonp_url, 'metadata', transform_source=strip_jsonp)
+
+        metadata_tracker_data = metadata['trackerData']
+        metadata_media_resource = metadata['mediaResource']
+
+        formats = []
+
+        # check if the metadata contains a direct URL to a file
+        for kind, media_resource in metadata_media_resource.items():
+            if kind not in ('dflt', 'alt'):
+                continue
+
+            for tag_name, medium_url in media_resource.items():
+                if tag_name not in ('videoURL', 'audioURL'):
+                    continue
+
+                ext = determine_ext(medium_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        medium_url, display_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls'))
+                elif ext == 'f4m':
+                    manifest_url = update_url_query(
+                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
+                    formats.extend(self._extract_f4m_formats(
+                        manifest_url, display_id, f4m_id='hds', fatal=False))
+                elif ext == 'smil':
+                    formats.extend(self._extract_smil_formats(
+                        medium_url, 'stream', fatal=False))
+                else:
+                    a_format = {
+                        'url': medium_url
+                    }
+                    if ext == 'unknown_video':
+                        urlh = self._request_webpage(
+                            medium_url, display_id, note='Determining extension')
+                        ext = urlhandle_detect_ext(urlh)
+                        a_format['ext'] = ext
+                    formats.append(a_format)
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        caption_url = metadata_media_resource.get('captionURL')
+        if caption_url:
+            subtitles['de'] = [{
+                'url': caption_url,
+                'ext': 'ttml',
+            }]
+
+        title = metadata_tracker_data['trackerClipTitle']
+
+        return {
+            'id': metadata_tracker_data.get('trackerClipId', display_id),
+            'display_id': display_id,
+            'title': title,
+            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
+            'formats': formats,
+            'subtitles': subtitles,
+            'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
+        }
+
+
+class WDRIE(WDRBaseIE):
     _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
     _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
     _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
@@ -91,10 +171,10 @@ class WDRIE(InfoExtractor):
         },
         {
             'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
-            # HDS download, MD5 is unstable
+            'md5': '803138901f6368ee497b4d195bb164f2',
             'info_dict': {
                 'id': 'mdb-186083',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'upload_date': '20130919',
                 'title': 'Sachgeschichte - Achterbahn ',
                 'description': '- Die Sendung mit der Maus -',
@@ -120,14 +200,9 @@ class WDRIE(InfoExtractor):
         display_id = mobj.group('display_id')
         webpage = self._download_webpage(url, display_id)
 
-        # for wdr.de the data-extension is in a tag with the class "mediaLink"
-        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
-        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
-        json_metadata = self._html_search_regex(
-            r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
-            webpage, 'media link', default=None, flags=re.MULTILINE)
+        info_dict = self._extract_wdr_video(webpage, display_id)
 
-        if not json_metadata:
+        if not info_dict:
             entries = [
                 self.url_result(page_url + href[0], 'WDR')
                 for href in re.findall(
@@ -140,86 +215,22 @@ class WDRIE(InfoExtractor):
 
             raise ExtractorError('No downloadable streams found', expected=True)
 
-        media_link_obj = self._parse_json(json_metadata, display_id,
-                                          transform_source=js_to_json)
-        jsonp_url = media_link_obj['mediaObj']['url']
-
-        metadata = self._download_json(
-            jsonp_url, 'metadata', transform_source=strip_jsonp)
-
-        metadata_tracker_data = metadata['trackerData']
-        metadata_media_resource = metadata['mediaResource']
-
-        formats = []
-
-        # check if the metadata contains a direct URL to a file
-        for kind, media_resource in metadata_media_resource.items():
-            if kind not in ('dflt', 'alt'):
-                continue
-
-            for tag_name, medium_url in media_resource.items():
-                if tag_name not in ('videoURL', 'audioURL'):
-                    continue
-
-                ext = determine_ext(medium_url)
-                if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        medium_url, display_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls'))
-                elif ext == 'f4m':
-                    manifest_url = update_url_query(
-                        medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
-                    formats.extend(self._extract_f4m_formats(
-                        manifest_url, display_id, f4m_id='hds', fatal=False))
-                elif ext == 'smil':
-                    formats.extend(self._extract_smil_formats(
-                        medium_url, 'stream', fatal=False))
-                else:
-                    a_format = {
-                        'url': medium_url
-                    }
-                    if ext == 'unknown_video':
-                        urlh = self._request_webpage(
-                            medium_url, display_id, note='Determining extension')
-                        ext = urlhandle_detect_ext(urlh)
-                        a_format['ext'] = ext
-                    formats.append(a_format)
-
-        self._sort_formats(formats)
-
-        subtitles = {}
-        caption_url = metadata_media_resource.get('captionURL')
-        if caption_url:
-            subtitles['de'] = [{
-                'url': caption_url,
-                'ext': 'ttml',
-            }]
-
-        title = metadata_tracker_data.get('trackerClipTitle')
         is_live = url_type == 'live'
 
         if is_live:
-            title = self._live_title(title)
-            upload_date = None
-        elif 'trackerClipAirTime' in metadata_tracker_data:
-            upload_date = metadata_tracker_data['trackerClipAirTime']
-        else:
-            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
+            info_dict.update({
+                'title': self._live_title(info_dict['title']),
+                'upload_date': None,
+            })
+        elif 'upload_date' not in info_dict:
+            info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
 
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
-
-        return {
-            'id': metadata_tracker_data.get('trackerClipId', display_id),
-            'display_id': display_id,
-            'title': title,
-            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
-            'formats': formats,
-            'upload_date': upload_date,
+        info_dict.update({
             'description': self._html_search_meta('Description', webpage),
             'is_live': is_live,
-            'subtitles': subtitles,
-        }
+        })
+
+        return info_dict
 
 
 class WDRMobileIE(InfoExtractor):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.06.18.1'
+__version__ = '2016.06.19'