]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/crooksandliars.py
debian/control: Update list of extractors in long description.
[youtubedl] / youtube_dl / extractor / crooksandliars.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5 int_or_none,
6 qualities,
7 )
8
9
10 class CrooksAndLiarsIE(InfoExtractor):
11 _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
12 _TESTS = [{
13 'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
14 'info_dict': {
15 'id': '8RUoRhRi',
16 'ext': 'mp4',
17 'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
18 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
19 'thumbnail': r're:^https?://.*\.jpg',
20 'timestamp': 1428207000,
21 'upload_date': '20150405',
22 'uploader': 'Heather',
23 'duration': 236,
24 }
25 }, {
26 'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
27 'only_matching': True,
28 }]
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 webpage = self._download_webpage(
34 'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
35
36 manifest = self._parse_json(
37 self._search_regex(
38 r'var\s+manifest\s*=\s*({.+?})\n', webpage, 'manifest JSON'),
39 video_id)
40
41 quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
42
43 formats = [{
44 'url': item['url'],
45 'format_id': item['type'],
46 'quality': quality(item['type']),
47 } for item in manifest['flavors'] if item['mime'].startswith('video/')]
48 self._sort_formats(formats)
49
50 return {
51 'url': url,
52 'id': video_id,
53 'title': manifest['title'],
54 'description': manifest.get('description'),
55 'thumbnail': self._proto_relative_url(manifest.get('poster')),
56 'timestamp': int_or_none(manifest.get('created')),
57 'uploader': manifest.get('author'),
58 'duration': int_or_none(manifest.get('duration')),
59 'formats': formats,
60 }