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

[youtube-dl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 759691365b3258f4d6fce045e4877c5798313341..392ad36486c8e953f4d3bed341353a3b5d11e65a 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -34,13 +34,21 @@ from .brightcove import BrightcoveIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE

+from .tvc import TVCIE

 from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
 from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE

+from .myvi import MyviIE

 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .svt import SVTIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .svt import SVTIE

+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .snagfilms import SnagFilmsEmbedIE

 
 
 class GenericIE(InfoExtractor):
 
 
 class GenericIE(InfoExtractor):


@@ -291,6 +299,15 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },

+        # TVC embed
+        {
+            'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
+            'info_dict': {
+                'id': '55304',
+                'ext': 'mp4',
+                'title': 'Дошкольное воспитание',
+            },
+        },

         # SportBox embed
         {
             'url': 'http://www.vestifinance.ru/articles/25753',
         # SportBox embed
         {
             'url': 'http://www.vestifinance.ru/articles/25753',


@@ -322,6 +339,26 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },

+        # Myvi.ru embed
+        {
+            'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
+            'info_dict': {
+                'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
+                'ext': 'mp4',
+                'title': 'Ужастики, русский трейлер (2015)',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 153,
+            }
+        },
+        # XHamster embed
+        {
+            'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
+            'info_dict': {
+                'id': 'showthread',
+                'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+            },
+            'playlist_mincount': 7,
+        },

         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',


@@ -644,6 +681,18 @@ class GenericIE(InfoExtractor):
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },

+        # Kaltura embed (different embed code)
+        {
+            'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+            'info_dict': {
+                'id': '1_a52wc67y',
+                'ext': 'flv',
+                'upload_date': '20150127',
+                'uploader_id': 'PremierMedia',
+                'timestamp': int,
+                'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+            },
+        },

         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',


@@ -801,6 +850,50 @@ class GenericIE(InfoExtractor):
                 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
                 'uploader': 'Rogers Sportsnet',
             },
                 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
                 'uploader': 'Rogers Sportsnet',
             },

+        },
+        # Dailymotion Cloud video
+        {
+            'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+            'md5': '49444254273501a64675a7e68c502681',
+            'info_dict': {
+                'id': '5585de919473990de4bee11b',
+                'ext': 'mp4',
+                'title': 'Le débat',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+            }
+        },
+        # OnionStudios embed
+        {
+            'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+            'info_dict': {
+                'id': '2855',
+                'ext': 'mp4',
+                'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+                'uploader': 'ClickHole',
+                'uploader_id': 'clickhole',
+            }
+        },
+        # SnagFilms embed
+        {
+            'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
+            'info_dict': {
+                'id': '74849a00-85a9-11e1-9660-123139220831',
+                'ext': 'mp4',
+                'title': '#whilewewatch',
+            }
+        },
+        # AdobeTVVideo embed
+        {
+            'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+            'md5': '43662b577c018ad707a63766462b1e87',
+            'info_dict': {
+                'id': '2456',
+                'ext': 'mp4',
+                'title': 'New experience with Acrobat DC',
+                'description': 'New experience with Acrobat DC',
+                'duration': 248.667,
+            },

         }
     ]
 
         }
     ]
 


@@ -968,7 +1061,9 @@ class GenericIE(InfoExtractor):
             }
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             }
 
         if not self._downloader.params.get('test', False) and not is_intentional:

-            self._downloader.report_warning('Falling back on generic information extractor.')
+            force = self._downloader.params.get('force_generic_extractor', False)
+            self._downloader.report_warning(
+                '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))

 
         if not full_response:
             request = compat_urllib_request.Request(url)
 
         if not full_response:
             request = compat_urllib_request.Request(url)


@@ -1073,23 +1168,14 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded rtl.nl player
         matches = re.findall(
 
         # Look for embedded rtl.nl player
         matches = re.findall(

-            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+            r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',

             webpage)
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
             webpage)
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 

-        # Look for embedded (iframe) Vimeo player
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
-        if mobj:
-            player_url = unescapeHTML(mobj.group('url'))
-            surl = smuggle_url(player_url, {'Referer': url})
-            return self.url_result(surl)
-        # Look for embedded (swf embed) Vimeo player
-        mobj = re.search(
-            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
-        if mobj:
-            return self.url_result(mobj.group(1))
+        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+        if vimeo_url is not None:
+            return self.url_result(vimeo_url)

 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)


@@ -1301,11 +1387,32 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 

+        # Look for embedded TVC player
+        tvc_url = TVCIE._extract_url(webpage)
+        if tvc_url:
+            return self.url_result(tvc_url, 'TVC')
+

         # Look for embedded SportBox player
         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
         # Look for embedded SportBox player
         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
         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:
+            return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+        # Look for embedded Tvigle player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Tvigle')
+

         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)


@@ -1330,6 +1437,11 @@ class GenericIE(InfoExtractor):
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 
         if smotri_url:
             return self.url_result(smotri_url, 'Smotri')
 

+        # Look for embedded Myvi.ru player
+        myvi_url = MyviIE._extract_url(webpage)
+        if myvi_url:
+            return self.url_result(myvi_url)
+

         # Look for embeded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
         # Look for embeded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',


@@ -1409,8 +1521,8 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds

-        mobj = re.search(
-            r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
+                re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))

         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 


@@ -1467,6 +1579,30 @@ class GenericIE(InfoExtractor):
         if senate_isvp_url:
             return self.url_result(senate_isvp_url, 'SenateISVP')
 
         if senate_isvp_url:
             return self.url_result(senate_isvp_url, 'SenateISVP')
 

+        # Look for Dailymotion Cloud videos
+        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+        if dmcloud_url:
+            return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+        # Look for OnionStudios embeds
+        onionstudios_url = OnionStudiosIE._extract_url(webpage)
+        if onionstudios_url:
+            return self.url_result(onionstudios_url)
+
+        # Look for SnagFilms embeds
+        snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
+        if snagfilms_url:
+            return self.url_result(snagfilms_url)
+
+        # Look for AdobeTVVideo embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))),
+                'AdobeTVVideo')
+

         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True