]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/slideshare.py
Update changelog.
[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 ..compat import (
8 compat_urlparse,
9 )
10 from ..utils import (
11 ExtractorError,
12 )
13
14
15 class SlideshareIE(InfoExtractor):
16 _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
17
18 _TEST = {
19 'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
20 'info_dict': {
21 'id': '25665706',
22 'ext': 'mp4',
23 'title': 'Managing Scale and Complexity',
24 '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.',
25 },
26 }
27
28 def _real_extract(self, url):
29 mobj = re.match(self._VALID_URL, url)
30 page_title = mobj.group('title')
31 webpage = self._download_webpage(url, page_title)
32 slideshare_obj = self._search_regex(
33 r'\$\.extend\(slideshare_object,\s*(\{.*?\})\);',
34 webpage, 'slideshare object')
35 info = json.loads(slideshare_obj)
36 if info['slideshow']['type'] != 'video':
37 raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
38
39 doc = info['doc']
40 bucket = info['jsplayer']['video_bucket']
41 ext = info['jsplayer']['video_extension']
42 video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
43 description = self._html_search_regex(
44 r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
45 'description', fatal=False)
46
47 return {
48 '_type': 'video',
49 'id': info['slideshow']['id'],
50 'title': info['slideshow']['title'],
51 'ext': ext,
52 'url': video_url,
53 'thumbnail': info['slideshow']['pin_image_url'],
54 'description': description,
55 }