[generic] Add support for Crooks and Liars embeds

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 013198b0df2b0685b5207572e278703143b5192e..0dc52ed23a38de7a5684b232197aff89537d2406 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -29,10 +29,12 @@ from ..utils import (
     xpath_text,
 )
 from .brightcove import BrightcoveIE
     xpath_text,
 )
 from .brightcove import BrightcoveIE

+from .nbc import NBCSportsVPlayerIE

 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE

+from .udn import UDNEmbedIE

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


@@ -527,6 +529,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
             },
             'add_ie': ['Viddler'],
         },

+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },

         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',


@@ -596,6 +609,29 @@ class GenericIE(InfoExtractor):
                 'view_count': int,
             },
         },
                 'view_count': int,
             },
         },

+        # Pladform embed
+        {
+            'url': 'http://muz-tv.ru/kinozal/view/7400/',
+            'info_dict': {
+                'id': '100183293',
+                'ext': 'mp4',
+                'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
+                'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 694,
+                'age_limit': 0,
+            },
+        },
+        # 5min embed
+        {
+            'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+            'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+            'info_dict': {
+                'id': '518726732',
+                'ext': 'mp4',
+                'title': 'Facebook Creates "On This Day" | Crunch Report',
+            },
+        },

         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',


@@ -605,6 +641,27 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20150228',
                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
             }
                 'upload_date': '20150228',
                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
             }

+        },
+        # NBC Sports vplayer embed
+        {
+            'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+            'info_dict': {
+                'id': 'ln7x1qSThw4k',
+                'ext': 'flv',
+                'title': "PFT Live: New leader in the 'new-look' defense",
+                'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+            },
+        },
+        # UDN embed
+        {
+            'url': 'http://www.udn.com/news/story/7314/822787',
+            'md5': 'de06b4c90b042c128395a88f0384817e',
+            'info_dict': {
+                'id': '300040',
+                'ext': 'mp4',
+                'title': '生物老師男變女 全校挺"做自己"',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }

         }
     ]
 
         }
     ]
 


@@ -993,6 +1050,19 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 

+        # Look for NYTimes player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+

         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or


@@ -1193,6 +1263,36 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
 
         if mobj is not None:
             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
 

+        # Look for Pladform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Pladform')
+
+        # Look for 5min embeds
+        mobj = re.search(
+            r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+        if mobj is not None:
+            return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+        # Look for Crooks and Liars embeds
+        mobj = re.search(
+            r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for NBC Sports VPlayer embeds
+        nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+        if nbc_sports_url:
+            return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+        # Look for UDN embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+        if mobj is not None:
+            return self.url_result(
+                compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+

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


@@ -1249,10 +1349,16 @@ class GenericIE(InfoExtractor):
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:

+            REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'

             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'

-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,

                 webpage)
                 webpage)

+            if not found:
+                # Look also in Refresh HTTP header
+                refresh_header = head_response.headers.get('Refresh')
+                if refresh_header:
+                    found = re.search(REDIRECT_REGEX, refresh_header)

             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)
             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)