)
from ..utils import (
ExtractorError,
+ get_element_by_id,
)
class SlideshareIE(InfoExtractor):
- _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
+ _VALID_URL = r'https?://(?:www\.)?slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
_TEST = {
'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
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)
'ext': ext,
'url': video_url,
'thumbnail': info['slideshow']['pin_image_url'],
- 'description': description,
+ 'description': description.strip() if description else None,
}