You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

110 lines
3.8 KiB

Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
  1. from __future__ import unicode_literals
  2. import re
  3. from .common import InfoExtractor
  4. from ..compat import compat_urllib_parse_unquote
  5. from ..utils import (
  6. clean_html,
  7. determine_ext,
  8. ExtractorError,
  9. int_or_none,
  10. parse_duration,
  11. )
  12. class XVideosIE(InfoExtractor):
  13. _VALID_URL = r'''(?x)
  14. https?://
  15. (?:
  16. (?:www\.)?xvideos\.com/video|
  17. flashservice\.xvideos\.com/embedframe/|
  18. static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
  19. )
  20. (?P<id>[0-9]+)
  21. '''
  22. _TESTS = [{
  23. 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  24. 'md5': '14cea69fcb84db54293b1e971466c2e1',
  25. 'info_dict': {
  26. 'id': '4588838',
  27. 'ext': 'mp4',
  28. 'title': 'Biker Takes his Girl',
  29. 'duration': 108,
  30. 'age_limit': 18,
  31. }
  32. }, {
  33. 'url': 'https://flashservice.xvideos.com/embedframe/4588838',
  34. 'only_matching': True,
  35. }, {
  36. 'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
  37. 'only_matching': True,
  38. }]
  39. def _real_extract(self, url):
  40. video_id = self._match_id(url)
  41. webpage = self._download_webpage(
  42. 'https://www.xvideos.com/video%s/' % video_id, video_id)
  43. mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  44. if mobj:
  45. raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  46. title = self._html_search_regex(
  47. (r'<title>(?P<title>.+?)\s+-\s+XVID',
  48. r'setVideoTitle\s*\(\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
  49. webpage, 'title', default=None,
  50. group='title') or self._og_search_title(webpage)
  51. thumbnails = []
  52. for preference, thumbnail in enumerate(('', '169')):
  53. thumbnail_url = self._search_regex(
  54. r'setThumbUrl%s\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
  55. webpage, 'thumbnail', default=None, group='thumbnail')
  56. if thumbnail_url:
  57. thumbnails.append({
  58. 'url': thumbnail_url,
  59. 'preference': preference,
  60. })
  61. duration = int_or_none(self._og_search_property(
  62. 'duration', webpage, default=None)) or parse_duration(
  63. self._search_regex(
  64. r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
  65. webpage, 'duration', fatal=False))
  66. formats = []
  67. video_url = compat_urllib_parse_unquote(self._search_regex(
  68. r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  69. if video_url:
  70. formats.append({
  71. 'url': video_url,
  72. 'format_id': 'flv',
  73. })
  74. for kind, _, format_url in re.findall(
  75. r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
  76. format_id = kind.lower()
  77. if format_id == 'hls':
  78. formats.extend(self._extract_m3u8_formats(
  79. format_url, video_id, 'mp4',
  80. entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  81. elif format_id in ('urllow', 'urlhigh'):
  82. formats.append({
  83. 'url': format_url,
  84. 'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
  85. 'quality': -2 if format_id.endswith('low') else None,
  86. })
  87. self._sort_formats(formats)
  88. return {
  89. 'id': video_id,
  90. 'formats': formats,
  91. 'title': title,
  92. 'duration': duration,
  93. 'thumbnails': thumbnails,
  94. 'age_limit': 18,
  95. }