Merge pull request #5961 from dstftw/force-generic-extractor

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 6be9e632923b157667b18db7a607561cc24bd59b..7769ffc5c5f425ce04dc92147c77803291f0fdd5 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -42,6 +42,10 @@ 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
 
 
 class GenericIE(InfoExtractor):
@@ -332,6 +336,15 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # 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/',
@@ -811,6 +824,29 @@ 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',
             },
+        },
+        # 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$',
+            }
+        },
+        # 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,
+            },
         }
     ]
 
@@ -978,7 +1014,9 @@ class GenericIE(InfoExtractor):
             }
 
         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)
@@ -1088,18 +1126,9 @@ class GenericIE(InfoExtractor):
         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)
@@ -1312,15 +1341,31 @@ class GenericIE(InfoExtractor):
             return self.url_result(rutv_url, 'RUTV')
 
         # Look for embedded TVC player
-        rutv_url = TVCIE._extract_url(webpage)
-        if rutv_url:
-            return self.url_result(rutv_url, 'TVC')
+        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 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)
@@ -1482,6 +1527,20 @@ class GenericIE(InfoExtractor):
         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 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