]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/techtalks.py
a55f236cbbca0ac5ef70db2b22eb3c94a778b2c1
[youtubedl] / youtube_dl / extractor / techtalks.py
1 import re
2
3 from .common import InfoExtractor
4 from ..utils import (
5 get_element_by_attribute,
6 clean_html,
7 )
8
9
10 class TechTalksIE(InfoExtractor):
11 _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/'
12
13 _TEST = {
14 u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
15 u'playlist': [
16 {
17 u'file': u'57758.flv',
18 u'info_dict': {
19 u'title': u'Learning Topic Models --- Going beyond SVD',
20 },
21 },
22 {
23 u'file': u'57758-slides.flv',
24 u'info_dict': {
25 u'title': u'Learning Topic Models --- Going beyond SVD',
26 },
27 },
28 ],
29 u'params': {
30 # rtmp download
31 u'skip_download': True,
32 },
33 }
34
35 def _real_extract(self, url):
36 mobj = re.match(self._VALID_URL, url)
37 talk_id = mobj.group('id')
38 webpage = self._download_webpage(url, talk_id)
39 rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage,
40 u'rtmp url')
41 play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
42 webpage, u'presenter play path')
43 title = clean_html(get_element_by_attribute('class', 'title', webpage))
44 video_info = {
45 'id': talk_id,
46 'title': title,
47 'url': rtmp_url,
48 'play_path': play_path,
49 'ext': 'flv',
50 }
51 m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage)
52 if m_slides is None:
53 return video_info
54 else:
55 return [
56 video_info,
57 # The slides video
58 {
59 'id': talk_id + '-slides',
60 'title': title,
61 'url': rtmp_url,
62 'play_path': m_slides.group(1),
63 'ext': 'flv',
64 },
65 ]