]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/slideshare.py
9c62825cc7f7cab2a4023a74e36307b48c280bd6
[youtubedl] / youtube_dl / extractor / slideshare.py
1 from __future__ import unicode_literals
2
3 import re
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8 compat_urlparse,
9 ExtractorError,
10 )
11
12
13 class SlideshareIE(InfoExtractor):
14 _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
15
16 _TEST = {
17 'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
18 'info_dict': {
19 'id': '25665706',
20 'ext': 'mp4',
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.',
23 },
24 }
25
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)
36
37 doc = info['doc']
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 class="description.*?"[^>]*>(.*?)</p>', webpage, 'description')
43
44 return {
45 '_type': 'video',
46 'id': info['slideshow']['id'],
47 'title': info['slideshow']['title'],
48 'ext': ext,
49 'url': video_url,
50 'thumbnail': info['slideshow']['pin_image_url'],
51 'description': description,
52 }