commit 77082c7b9ef2ea95161e4e288c110b5f7f34fda0
parent 252a1f75d205b2c95c6a04c7aa64f08c756e4954
Author: Remita Amine <remitamine@gmail.com>
Date: Tue, 5 Jul 2016 12:01:04 +0100
[slideshare] fix description extraction
Diffstat:
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py
@@ -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,
}