Merge branch 'brightcove_in_page_embed' of https://github.com/remitamine/youtube...

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 8881a8a237bfe809f5fe924afcc70109166f66af..34d930a2db82fe340d55efe681bd43ff00b32aa1 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -9,6 +9,7 @@ import sys
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..compat import (
+    compat_etree_fromstring,
     compat_urllib_parse_unquote,
     compat_urllib_request,
     compat_urlparse,
@@ -21,7 +22,6 @@ from ..utils import (
     HEADRequest,
     is_html,
     orderedSet,
-    parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
@@ -30,7 +30,10 @@ from ..utils import (
     url_basename,
     xpath_text,
 )
-from .brightcove import BrightcoveIE
+from .brightcove import (
+    BrightcoveIE,
+    BrightcoveInPageEmbedIE,
+)
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
@@ -50,6 +53,7 @@ from .dailymotion import DailymotionCloudIE
 from .onionstudios import OnionStudiosIE
 from .snagfilms import SnagFilmsEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
+from .mtv import MTVServicesEmbeddedIE
 
 
 class GenericIE(InfoExtractor):
@@ -140,6 +144,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Automatics, robotics and biocybernetics',
                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
+                'upload_date': '20130627',
                 'formats': 'mincount:16',
                 'subtitles': 'mincount:1',
             },
@@ -1029,6 +1034,17 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'cinemasnob',
             },
+        },
+        # BrightcoveInPageEmbed embed
+        {
+            'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
+            'info_dict': {
+                'id': '4238694884001',
+                'ext': 'flv',
+                'title': 'Tabletop: Dread, Last Thoughts',
+                'description': 'Tabletop: Dread, Last Thoughts',
+                'duration': 51690,
+            },
         }
     ]
 
@@ -1236,7 +1252,7 @@ class GenericIE(InfoExtractor):
 
         # Is it an RSS feed, a SMIL file or a XSPF playlist?
         try:
-            doc = parse_xml(webpage)
+            doc = compat_etree_fromstring(webpage.encode('utf-8'))
             if doc.tag == 'rss':
                 return self._extract_rss(url, video_id, doc)
             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
@@ -1305,6 +1321,11 @@ class GenericIE(InfoExtractor):
                 'entries': entries,
             }
 
+        # Look for Brightcove In Page Embed:
+        brightcove_in_page_embed_url = BrightcoveInPageEmbedIE._extract_url(webpage)
+        if brightcove_in_page_embed_url:
+            return self.url_result(brightcove_in_page_embed_url, 'BrightcoveInPageEmbed')
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
@@ -1611,12 +1632,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(url, ie='Vulture')
 
         # Look for embedded mtvservices player
-        mobj = re.search(
-            r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
-            webpage)
-        if mobj is not None:
-            url = unescapeHTML(mobj.group('url'))
-            return self.url_result(url, ie='MTVServicesEmbedded')
+        mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
+        if mtvservices_url:
+            return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
 
         # Look for embedded yahoo player
         mobj = re.search(
@@ -1655,7 +1673,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'MLB')
 
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
+            r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
             webpage)
         if mobj is not None:
             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
@@ -1673,8 +1691,8 @@ class GenericIE(InfoExtractor):
             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) 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))
+        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
+                re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')