]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/slideshare.py
Merge tag 'upstream/2015.01.16'
[youtubedl] / youtube_dl / extractor / slideshare.py
index 9c62825cc7f7cab2a4023a74e36307b48c280bd6..9f79ff5c1b66d2bf37369a6009a914043493b407 100644 (file)
@@ -4,8 +4,10 @@ import re
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urlparse,
+)
+from ..utils import (
     ExtractorError,
 )
 
     ExtractorError,
 )
 
@@ -28,7 +30,7 @@ class SlideshareIE(InfoExtractor):
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
-            r'var slideshare_object =  ({.*?}); var user_info =',
+            r'var\s+slideshare_object\s*=\s*({.*?});\s*var\s+user_info\s*=',
             webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
         if info['slideshow']['type'] != 'video':
             webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
         if info['slideshow']['type'] != 'video':
@@ -39,7 +41,8 @@ class SlideshareIE(InfoExtractor):
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
         description = self._html_search_regex(
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
         description = self._html_search_regex(
-            r'<p class="description.*?"[^>]*>(.*?)</p>', webpage, 'description')
+            r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
+            'description', fatal=False)
 
         return {
             '_type': 'video',
 
         return {
             '_type': 'video',