Merge branch 'master' of https://github.com/rg3/youtube-dl

AUTHORS

@@ -167,3 +167,4 @@ Kacper Michajłow
 José Joaquín Atria
 Viťas Strádal
 Kagami Hiiragi
+Philip Huppert

youtube_dl/extractor/ard.py

@@ -83,7 +83,7 @@ class ARDMediathekIE(InfoExtractor):
         subtitle_url = media_info.get('_subtitleUrl')
         if subtitle_url:
             subtitles['de'] = [{
-                'ext': 'srt',
+                'ext': 'ttml',
                 'url': subtitle_url,
             }]
 

youtube_dl/extractor/arte.py

@@ -337,7 +337,7 @@ class ArteTVEmbedIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:embed'
     _VALID_URL = r'''(?x)
         http://www\.arte\.tv
-        /playerv2/embed\.php\?json_url=
+        /(?:playerv2/embed|arte_vp/index)\.php\?json_url=
         (?P<json_url>
             http://arte\.tv/papi/tvguide/videos/stream/player/
             (?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*

youtube_dl/extractor/extractors.py

@@ -336,7 +336,6 @@ from .ivi import (
 )
 from .ivideon import IvideonIE
 from .izlesene import IzleseneIE
-from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .jwplatform import JWPlatformIE
@@ -584,6 +583,7 @@ from .pornhub import (
 from .pornotube import PornotubeIE
 from .pornovoisines import PornoVoisinesIE
 from .pornoxo import PornoXOIE
+from .presstv import PressTVIE
 from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE

youtube_dl/extractor/generic.py

@@ -1128,6 +1128,18 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # Another form of arte.tv embed
+        {
+            'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
+            'md5': '850bfe45417ddf221288c88a0cffe2e2',
+            'info_dict': {
+                'id': '030273-562_PLUS7-F',
+                'ext': 'mp4',
+                'title': 'ARTE Reportage - Nulle part, en France',
+                'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
+                'upload_date': '20160409',
+            },
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -1702,7 +1714,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded arte.tv player
         mobj = re.search(
-            r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
+            r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'ArteTVEmbed')

youtube_dl/extractor/goshgay.py

@@ -14,13 +14,13 @@ class GoshgayIE(InfoExtractor):
     _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
     _TEST = {
         'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
-        'md5': '027fcc54459dff0feb0bc06a7aeda680',
+        'md5': '4b6db9a0a333142eb9f15913142b0ed1',
         'info_dict': {
             'id': '299069',
             'ext': 'flv',
             'title': 'DIESEL SFW XXX Video',
             'thumbnail': 're:^http://.*\.jpg$',
-            'duration': 79,
+            'duration': 80,
             'age_limit': 18,
         }
     }
@@ -47,5 +47,5 @@ class GoshgayIE(InfoExtractor):
             'title': title,
             'thumbnail': thumbnail,
             'duration': duration,
-            'age_limit': self._family_friendly_search(webpage),
+            'age_limit': 18,
         }

youtube_dl/extractor/groupon.py

@@ -16,14 +16,14 @@ class GrouponIE(InfoExtractor):
         'playlist': [{
             'info_dict': {
                 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Bikram Yoga Huntington Beach | Orange County',
                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
                 'duration': 44.961,
             },
         }],
         'params': {
-            'skip_download': 'HLS',
+            'skip_download': 'HDS',
         }
     }
 
@@ -32,7 +32,7 @@ class GrouponIE(InfoExtractor):
         webpage = self._download_webpage(url, playlist_id)
 
         payload = self._parse_json(self._search_regex(
-            r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id)
+            r'(?:var\s+|window\.)payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id)
         videos = payload['carousel'].get('dealVideos', [])
         entries = []
         for v in videos:

youtube_dl/extractor/howstuffworks.py

@@ -24,6 +24,7 @@ class HowStuffWorksIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 161,
             },
+            'skip': 'Video broken',
         },
         {
             'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm',

youtube_dl/extractor/izlesene.py

@@ -29,7 +29,7 @@ class IzleseneIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
-                'thumbnail': 're:^http://.*\.jpg',
+                'thumbnail': 're:^https?://.*\.jpg',
                 'uploader_id': 'pelikzzle',
                 'timestamp': int,
                 'upload_date': '20140702',
@@ -44,8 +44,7 @@ class IzleseneIE(InfoExtractor):
                 'id': '17997',
                 'ext': 'mp4',
                 'title': 'Tarkan Dortmund 2006 Konseri',
-                'description': 'Tarkan Dortmund 2006 Konseri',
+                'thumbnail': 're:^https://.*\.jpg',
-                'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
                 'timestamp': int,
                 'upload_date': '20061112',
@@ -62,7 +61,7 @@ class IzleseneIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = self._og_search_title(webpage)
-        description = self._og_search_description(webpage)
+        description = self._og_search_description(webpage, default=None)
         thumbnail = self._proto_relative_url(
             self._og_search_thumbnail(webpage), scheme='http:')
 

youtube_dl/extractor/jadorecettepub.py

@@ -1,47 +0,0 @@
-# coding: utf-8
-
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from .youtube import YoutubeIE
-
-
-class JadoreCettePubIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
-
-    _TEST = {
-        'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
-        'md5': '401286a06067c70b44076044b66515de',
-        'info_dict': {
-            'id': 'jLMja3tr7a4',
-            'ext': 'mp4',
-            'title': 'La pire utilisation de Star Wars',
-            'description': "Jadorecettepub.com vous a gratifié de plusieurs pubs géniales utilisant Star Wars et Dark Vador plus particulièrement... Mais l'heure est venue de vous proposer une version totalement massacrée, venue du Japon.  Quand les Japonais détruisent l'image de Star Wars pour vendre du thon en boite, ça promet...",
-        },
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        title = self._html_search_regex(
-            r'<span style="font-size: x-large;"><b>(.*?)</b></span>',
-            webpage, 'title')
-        description = self._html_search_regex(
-            r'(?s)<div id="fb-root">(.*?)<script>', webpage, 'description',
-            fatal=False)
-        real_url = self._search_regex(
-            r'\[/postlink\](.*)endofvid', webpage, 'video URL')
-        video_id = YoutubeIE.extract_id(real_url)
-
-        return {
-            '_type': 'url_transparent',
-            'url': real_url,
-            'id': video_id,
-            'title': title,
-            'description': description,
-        }

youtube_dl/extractor/mixcloud.py

@@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     ExtractorError,
     HEADRequest,
+    NO_DEFAULT,
     parse_count,
     str_to_int,
 )
@@ -63,8 +64,17 @@ class MixcloudIE(InfoExtractor):
 
         webpage = self._download_webpage(url, track_id)
 
+        message = self._html_search_regex(
+            r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
+            webpage, 'error message', default=None)
+
         preview_url = self._search_regex(
-            r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
+            r'\s(?:data-preview-url|m-preview)="([^"]+)"',
+            webpage, 'preview url', default=None if message else NO_DEFAULT)
+
+        if message:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
+
         song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
         song_url = song_url.replace('/previews/', '/c/originals/')
         if not self._check_url(song_url, track_id, 'mp3'):

youtube_dl/extractor/neteasemusic.py

@@ -89,6 +89,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'timestamp': 1431878400,
             'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
         },
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'No lyrics translation.',
         'url': 'http://music.163.com/#/song?id=29822014',
@@ -101,6 +102,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'timestamp': 1419523200,
             'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
         },
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'No lyrics.',
         'url': 'http://music.163.com/song?id=17241424',
@@ -112,6 +114,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'upload_date': '20080211',
             'timestamp': 1202745600,
         },
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'Has translated name.',
         'url': 'http://music.163.com/#/song?id=22735043',
@@ -124,7 +127,8 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'upload_date': '20100127',
             'timestamp': 1264608000,
             'alt_title': '说出愿望吧(Genie)',
-        }
+        },
+        'skip': 'Blocked outside Mainland China',
     }]
 
     def _process_lyrics(self, lyrics_info):
@@ -192,6 +196,7 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
             'title': 'B\'day',
         },
         'playlist_count': 23,
+        'skip': 'Blocked outside Mainland China',
     }
 
     def _real_extract(self, url):
@@ -223,6 +228,7 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
             'title': '张惠妹 - aMEI;阿密特',
         },
         'playlist_count': 50,
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'Singer has translated name.',
         'url': 'http://music.163.com/#/artist?id=124098',
@@ -231,6 +237,7 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
             'title': '李昇基 - 이승기',
         },
         'playlist_count': 50,
+        'skip': 'Blocked outside Mainland China',
     }]
 
     def _real_extract(self, url):
@@ -266,6 +273,7 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE):
             'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
         },
         'playlist_count': 99,
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'Toplist/Charts sample',
         'url': 'http://music.163.com/#/discover/toplist?id=3733003',
@@ -275,6 +283,7 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE):
             'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
         },
         'playlist_count': 50,
+        'skip': 'Blocked outside Mainland China',
     }]
 
     def _real_extract(self, url):
@@ -314,6 +323,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
             'creator': '白雅言',
             'upload_date': '20150520',
         },
+        'skip': 'Blocked outside Mainland China',
     }
 
     def _real_extract(self, url):
@@ -357,6 +367,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
             'upload_date': '20150613',
             'duration': 900,
         },
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'This program has accompanying songs.',
         'url': 'http://music.163.com/#/program?id=10141022',
@@ -366,6 +377,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
             'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
         },
         'playlist_count': 4,
+        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'This program has accompanying songs.',
         'url': 'http://music.163.com/#/program?id=10141022',
@@ -379,7 +391,8 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
         },
         'params': {
             'noplaylist': True
-        }
+        },
+        'skip': 'Blocked outside Mainland China',
     }]
 
     def _real_extract(self, url):
@@ -438,6 +451,7 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
             'description': 'md5:766220985cbd16fdd552f64c578a6b15'
         },
         'playlist_mincount': 40,
+        'skip': 'Blocked outside Mainland China',
     }
     _PAGE_SIZE = 1000
 

youtube_dl/extractor/presstv.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import remove_start
+
+
+class PressTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
+
+    _TEST = {
+        'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
+        'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
+        'info_dict': {
+            'id': '459911',
+            'display_id': 'Australian-sewerage-treatment-facility-',
+            'ext': 'mp4',
+            'title': 'Organic mattresses used to clean waste water',
+            'upload_date': '20160409',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'description': 'md5:20002e654bbafb6908395a5c0cfcd125'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        # extract video URL from webpage
+        video_url = self._hidden_inputs(webpage)['inpPlayback']
+
+        # build list of available formats
+        # specified in http://www.presstv.ir/Scripts/playback.js
+        base_url = 'http://192.99.219.222:82/presstv'
+        _formats = [
+            (180, '_low200.mp4'),
+            (360, '_low400.mp4'),
+            (720, '_low800.mp4'),
+            (1080, '.mp4')
+        ]
+
+        formats = [{
+            'url': base_url + video_url[:-4] + extension,
+            'format_id': '%dp' % height,
+            'height': height,
+        } for height, extension in _formats]
+
+        # extract video metadata
+        title = remove_start(
+            self._html_search_meta('title', webpage, fatal=True), 'PressTV-')
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+
+        upload_date = '%04d%02d%02d' % (
+            int(mobj.group('y')),
+            int(mobj.group('m')),
+            int(mobj.group('d')),
+        )
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'description': description
+        }

youtube_dl/extractor/youtube.py

@@ -1884,7 +1884,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         if video:
             return video
 
-        if playlist_id.startswith('RD') or playlist_id.startswith('UL'):
+        if playlist_id.startswith(('RD', 'UL', 'PU')):
             # Mixes require a custom extraction process
             return self._extract_mix(playlist_id)