[slideshare] fix description extraction
authorRemita Amine <remitamine@gmail.com>
Tue, 5 Jul 2016 11:01:04 +0000 (12:01 +0100)
committerRemita Amine <remitamine@gmail.com>
Tue, 5 Jul 2016 11:01:04 +0000 (12:01 +0100)
youtube_dl/extractor/slideshare.py

index 0b717a1e42b8dd2c3d8a88d602f001876cf99e03..4967c1b7752e4ebfd0c1aac9b0d079c2dc843363 100644 (file)
@@ -9,6 +9,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    get_element_by_id,
 )
 
 
@@ -40,7 +41,7 @@ class SlideshareIE(InfoExtractor):
         bucket = info['jsplayer']['video_bucket']
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
-        description = self._html_search_regex(
+        description = get_element_by_id('slideshow-description-paragraph', webpage) or self._html_search_regex(
             r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
             'description', fatal=False)
 
@@ -51,5 +52,5 @@ class SlideshareIE(InfoExtractor):
             'ext': ext,
             'url': video_url,
             'thumbnail': info['slideshow']['pin_image_url'],
-            'description': description,
+            'description': description.strip() if description else None,
         }