crooksandliars.py 2.0 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556
  1. from .common import InfoExtractor
  2. from ..utils import (
  3. int_or_none,
  4. qualities,
  5. )
  6. class CrooksAndLiarsIE(InfoExtractor):
  7. _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
  8. _EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
  9. _TESTS = [{
  10. 'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
  11. 'info_dict': {
  12. 'id': '8RUoRhRi',
  13. 'ext': 'mp4',
  14. 'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
  15. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  16. 'thumbnail': r're:^https?://.*\.jpg',
  17. 'timestamp': 1428207000,
  18. 'upload_date': '20150405',
  19. 'uploader': 'Heather',
  20. 'duration': 236,
  21. },
  22. }, {
  23. 'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
  24. 'only_matching': True,
  25. }]
  26. def _real_extract(self, url):
  27. video_id = self._match_id(url)
  28. webpage = self._download_webpage(
  29. f'http://embed.crooksandliars.com/embed/{video_id}', video_id)
  30. manifest = self._search_json(r'var\s+manifest\s*=', webpage, 'manifest JSON', video_id)
  31. quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
  32. formats = [{
  33. 'url': item['url'],
  34. 'format_id': item['type'],
  35. 'quality': quality(item['type']),
  36. } for item in manifest['flavors'] if item['mime'].startswith('video/')]
  37. return {
  38. 'url': url,
  39. 'id': video_id,
  40. 'title': manifest['title'],
  41. 'description': manifest.get('description'),
  42. 'thumbnail': self._proto_relative_url(manifest.get('poster')),
  43. 'timestamp': int_or_none(manifest.get('created')),
  44. 'uploader': manifest.get('author'),
  45. 'duration': int_or_none(manifest.get('duration')),
  46. 'formats': formats,
  47. }