1 from __future__ import unicode_literals
6 from .common import InfoExtractor
13 class SlideshareIE(InfoExtractor):
14 _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
17 'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
21 'title': 'Managing Scale and Complexity',
22 'description': 'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix.',
26 def _real_extract(self, url):
27 mobj = re.match(self._VALID_URL, url)
28 page_title = mobj.group('title')
29 webpage = self._download_webpage(url, page_title)
30 slideshare_obj = self._search_regex(
31 r'var slideshare_object = ({.*?}); var user_info =',
32 webpage, 'slideshare object')
33 info = json.loads(slideshare_obj)
34 if info['slideshow']['type'] != 'video':
35 raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
38 bucket = info['jsplayer']['video_bucket']
39 ext = info['jsplayer']['video_extension']
40 video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
41 description = self._html_search_regex(
42 r'<p\s+(?:style="[^"]*"\s+)?class=".*?description.*?"[^>]*>(.*?)</p>', webpage,
43 'description', fatal=False)
47 'id': info['slideshow']['id'],
48 'title': info['slideshow']['title'],
51 'thumbnail': info['slideshow']['pin_image_url'],
52 'description': description,