]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/charlierose.py
4bf2cf7b0ce7648ec2786952220b452c20201a52
[youtubedl] / youtube_dl / extractor / charlierose.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import remove_end
5
6
7 class CharlieRoseIE(InfoExtractor):
8 _VALID_URL = r'https?://(?:www\.)?charlierose\.com/video(?:s|/player)/(?P<id>\d+)'
9 _TESTS = [{
10 'url': 'https://charlierose.com/videos/27996',
11 'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
12 'info_dict': {
13 'id': '27996',
14 'ext': 'mp4',
15 'title': 'Remembering Zaha Hadid',
16 'thumbnail': 're:^https?://.*\.jpg\?\d+',
17 'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
18 'subtitles': {
19 'en': [{
20 'ext': 'vtt',
21 }],
22 },
23 },
24 }, {
25 'url': 'https://charlierose.com/videos/27996',
26 'only_matching': True,
27 }]
28
29 _PLAYER_BASE = 'https://charlierose.com/video/player/%s'
30
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33 webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
34
35 title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
36
37 info_dict = self._parse_html5_media_entries(
38 self._PLAYER_BASE % video_id, webpage, video_id,
39 m3u8_entry_protocol='m3u8_native')[0]
40
41 self._sort_formats(info_dict['formats'])
42 self._remove_duplicate_formats(info_dict['formats'])
43
44 info_dict.update({
45 'id': video_id,
46 'title': title,
47 'thumbnail': self._og_search_thumbnail(webpage),
48 'description': self._og_search_description(webpage),
49 })
50
51 return info_dict