From 77082c7b9ef2ea95161e4e288c110b5f7f34fda0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 5 Jul 2016 12:01:04 +0100 Subject: [PATCH] [slideshare] fix description extraction --- youtube_dl/extractor/slideshare.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py index 0b717a1e4..4967c1b77 100644 --- a/youtube_dl/extractor/slideshare.py +++ b/youtube_dl/extractor/slideshare.py @@ -9,6 +9,7 @@ ) from ..utils import ( ExtractorError, + get_element_by_id, ) @@ -40,7 +41,7 @@ def _real_extract(self, url): 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)]+itemprop="description"[^>]*>(.+?)

', webpage, 'description', fatal=False) @@ -51,5 +52,5 @@ def _real_extract(self, url): 'ext': ext, 'url': video_url, 'thumbnail': info['slideshow']['pin_image_url'], - 'description': description, + 'description': description.strip() if description else None, }