]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/techtalks.py
Tidy the changelog.
[youtubedl] / youtube_dl / extractor / techtalks.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 get_element_by_attribute,
8 clean_html,
9 )
10
11
12 class TechTalksIE(InfoExtractor):
13 _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/'
14
15 _TEST = {
16 'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
17 'info_dict': {
18 'id': '57758',
19 'title': 'Learning Topic Models --- Going beyond SVD',
20 },
21 'playlist': [
22 {
23 'info_dict': {
24 'id': '57758',
25 'ext': 'flv',
26 'title': 'Learning Topic Models --- Going beyond SVD',
27 },
28 },
29 {
30 'info_dict': {
31 'id': '57758-slides',
32 'ext': 'flv',
33 'title': 'Learning Topic Models --- Going beyond SVD',
34 },
35 },
36 ],
37 'params': {
38 # rtmp download
39 'skip_download': True,
40 },
41 }
42
43 def _real_extract(self, url):
44 mobj = re.match(self._VALID_URL, url)
45 talk_id = mobj.group('id')
46 webpage = self._download_webpage(url, talk_id)
47 rtmp_url = self._search_regex(
48 r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url')
49 play_path = self._search_regex(
50 r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
51 webpage, 'presenter play path')
52 title = clean_html(get_element_by_attribute('class', 'title', webpage))
53 video_info = {
54 'id': talk_id,
55 'title': title,
56 'url': rtmp_url,
57 'play_path': play_path,
58 'ext': 'flv',
59 }
60 m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage)
61 if m_slides is None:
62 return video_info
63 else:
64 return {
65 '_type': 'playlist',
66 'id': talk_id,
67 'title': title,
68 'entries': [
69 video_info,
70 # The slides video
71 {
72 'id': talk_id + '-slides',
73 'title': title,
74 'url': rtmp_url,
75 'play_path': m_slides.group(1),
76 'ext': 'flv',
77 },
78 ],
79 }