_ Git - youtube-dl/blob - youtube_dl/extractor/xvideos.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_parse_unquote
   7 from ..utils import (
   8     clean_html,
   9     ExtractorError,
  10     determine_ext,
  11     parse_duration,
  12 )
  13
  14
  15 class XVideosIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
  17     _TEST = {
  18         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  19         'md5': '14cea69fcb84db54293b1e971466c2e1',
  20         'info_dict': {
  21             'id': '4588838',
  22             'ext': 'mp4',
  23             'title': 'Biker Takes his Girl',
  24             'duration': 120,
  25             'age_limit': 18,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  34         if mobj:
  35             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  36
  37         video_title = self._html_search_regex(
  38             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  39         video_thumbnail = self._search_regex(
  40             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  41         video_duration = parse_duration(self._search_regex(
  42             r'<span class="duration">.*?(\d[^<]+)', webpage, 'duration', fatal=False))
  43
  44         formats = []
  45
  46         video_url = compat_urllib_parse_unquote(self._search_regex(
  47             r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  48         if video_url:
  49             formats.append({
  50                 'url': video_url,
  51                 'format_id': 'flv',
  52             })
  53
  54         for kind, _, format_url in re.findall(
  55                 r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
  56             format_id = kind.lower()
  57             if format_id == 'hls':
  58                 formats.extend(self._extract_m3u8_formats(
  59                     format_url, video_id, 'mp4',
  60                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  61             elif format_id in ('urllow', 'urlhigh'):
  62                 formats.append({
  63                     'url': format_url,
  64                     'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
  65                     'quality': -2 if format_id.endswith('low') else None,
  66                 })
  67
  68         self._sort_formats(formats)
  69
  70         return {
  71             'id': video_id,
  72             'formats': formats,
  73             'title': video_title,
  74             'duration': video_duration,
  75             'thumbnail': video_thumbnail,
  76             'age_limit': 18,
  77         }