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     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     parse_duration,
  13 )
  14
  15
  16 class XVideosIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     https?://
  19                         (?:
  20                             (?:www\.)?xvideos\.com/video|
  21                             flashservice\.xvideos\.com/embedframe/|
  22                             static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
  23                         )
  24                         (?P<id>[0-9]+)
  25                     '''
  26     _TESTS = [{
  27         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  28         'md5': '14cea69fcb84db54293b1e971466c2e1',
  29         'info_dict': {
  30             'id': '4588838',
  31             'ext': 'mp4',
  32             'title': 'Biker Takes his Girl',
  33             'duration': 108,
  34             'age_limit': 18,
  35         }
  36     }, {
  37         'url': 'https://flashservice.xvideos.com/embedframe/4588838',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         webpage = self._download_webpage(
  48             'https://www.xvideos.com/video%s/' % video_id, video_id)
  49
  50         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  51         if mobj:
  52             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  53
  54         title = self._html_search_regex(
  55             (r'<title>(?P<title>.+?)\s+-\s+XVID',
  56              r'setVideoTitle\s*\(\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
  57             webpage, 'title', default=None,
  58             group='title') or self._og_search_title(webpage)
  59
  60         thumbnails = []
  61         for preference, thumbnail in enumerate(('', '169')):
  62             thumbnail_url = self._search_regex(
  63                 r'setThumbUrl%s\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
  64                 webpage, 'thumbnail', default=None, group='thumbnail')
  65             if thumbnail_url:
  66                 thumbnails.append({
  67                     'url': thumbnail_url,
  68                     'preference': preference,
  69                 })
  70
  71         duration = int_or_none(self._og_search_property(
  72             'duration', webpage, default=None)) or parse_duration(
  73             self._search_regex(
  74                 r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
  75                 webpage, 'duration', fatal=False))
  76
  77         formats = []
  78
  79         video_url = compat_urllib_parse_unquote(self._search_regex(
  80             r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  81         if video_url:
  82             formats.append({
  83                 'url': video_url,
  84                 'format_id': 'flv',
  85             })
  86
  87         for kind, _, format_url in re.findall(
  88                 r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
  89             format_id = kind.lower()
  90             if format_id == 'hls':
  91                 formats.extend(self._extract_m3u8_formats(
  92                     format_url, video_id, 'mp4',
  93                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  94             elif format_id in ('urllow', 'urlhigh'):
  95                 formats.append({
  96                     'url': format_url,
  97                     'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
  98                     'quality': -2 if format_id.endswith('low') else None,
  99                 })
 100
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'formats': formats,
 106             'title': title,
 107             'duration': duration,
 108             'thumbnails': thumbnails,
 109             'age_limit': 18,
 110         }