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.

72 lines
2.3 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. ExtractorError,
  8. determine_ext,
  9. )
  10. class XVideosIE(InfoExtractor):
  11. _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
  12. _TEST = {
  13. 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  14. 'md5': '14cea69fcb84db54293b1e971466c2e1',
  15. 'info_dict': {
  16. 'id': '4588838',
  17. 'ext': 'mp4',
  18. 'title': 'Biker Takes his Girl',
  19. 'age_limit': 18,
  20. }
  21. }
  22. def _real_extract(self, url):
  23. video_id = self._match_id(url)
  24. webpage = self._download_webpage(url, video_id)
  25. mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  26. if mobj:
  27. raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  28. video_title = self._html_search_regex(
  29. r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  30. video_thumbnail = self._search_regex(
  31. r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  32. formats = []
  33. video_url = compat_urllib_parse_unquote(self._search_regex(
  34. r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  35. if video_url:
  36. formats.append({
  37. 'url': video_url,
  38. 'format_id': 'flv',
  39. })
  40. for kind, _, format_url in re.findall(
  41. r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
  42. format_id = kind.lower()
  43. if format_id == 'hls':
  44. formats.extend(self._extract_m3u8_formats(
  45. format_url, video_id, 'mp4',
  46. entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  47. elif format_id in ('urllow', 'urlhigh'):
  48. formats.append({
  49. 'url': format_url,
  50. 'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
  51. 'quality': -2 if format_id.endswith('low') else None,
  52. })
  53. self._sort_formats(formats)
  54. return {
  55. 'id': video_id,
  56. 'formats': formats,
  57. 'title': video_title,
  58. 'thumbnail': video_thumbnail,
  59. 'age_limit': 18,
  60. }