Raphaël G. Git Repositories - youtubedl/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     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                             (?:[^/]+\.)?xvideos2?\.com/video|
  21                             (?:www\.)?xvideos\.es/video|
  22                             flashservice\.xvideos\.com/embedframe/|
  23                             static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
  24                         )
  25                         (?P<id>[0-9]+)
  26                     '''
  27     _TESTS = [{
  28         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  29         'md5': '14cea69fcb84db54293b1e971466c2e1',
  30         'info_dict': {
  31             'id': '4588838',
  32             'ext': 'mp4',
  33             'title': 'Biker Takes his Girl',
  34             'duration': 108,
  35             'age_limit': 18,
  36         }
  37     }, {
  38         'url': 'https://flashservice.xvideos.com/embedframe/4588838',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://xvideos.com/video4588838/biker_takes_his_girl',
  45         'only_matching': True
  46     }, {
  47         'url': 'https://xvideos.com/video4588838/biker_takes_his_girl',
  48         'only_matching': True
  49     }, {
  50         'url': 'https://xvideos.es/video4588838/biker_takes_his_girl',
  51         'only_matching': True
  52     }, {
  53         'url': 'https://www.xvideos.es/video4588838/biker_takes_his_girl',
  54         'only_matching': True
  55     }, {
  56         'url': 'http://xvideos.es/video4588838/biker_takes_his_girl',
  57         'only_matching': True
  58     }, {
  59         'url': 'http://www.xvideos.es/video4588838/biker_takes_his_girl',
  60         'only_matching': True
  61     }, {
  62         'url': 'http://fr.xvideos.com/video4588838/biker_takes_his_girl',
  63         'only_matching': True
  64     }, {
  65         'url': 'https://fr.xvideos.com/video4588838/biker_takes_his_girl',
  66         'only_matching': True
  67     }, {
  68         'url': 'http://it.xvideos.com/video4588838/biker_takes_his_girl',
  69         'only_matching': True
  70     }, {
  71         'url': 'https://it.xvideos.com/video4588838/biker_takes_his_girl',
  72         'only_matching': True
  73     }, {
  74         'url': 'http://de.xvideos.com/video4588838/biker_takes_his_girl',
  75         'only_matching': True
  76     }, {
  77         'url': 'https://de.xvideos.com/video4588838/biker_takes_his_girl',
  78         'only_matching': True
  79     }]
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83
  84         webpage = self._download_webpage(
  85             'https://www.xvideos.com/video%s/' % video_id, video_id)
  86
  87         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  88         if mobj:
  89             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  90
  91         title = self._html_search_regex(
  92             (r'<title>(?P<title>.+?)\s+-\s+XVID',
  93              r'setVideoTitle\s*\(\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
  94             webpage, 'title', default=None,
  95             group='title') or self._og_search_title(webpage)
  96
  97         thumbnails = []
  98         for preference, thumbnail in enumerate(('', '169')):
  99             thumbnail_url = self._search_regex(
 100                 r'setThumbUrl%s\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
 101                 webpage, 'thumbnail', default=None, group='thumbnail')
 102             if thumbnail_url:
 103                 thumbnails.append({
 104                     'url': thumbnail_url,
 105                     'preference': preference,
 106                 })
 107
 108         duration = int_or_none(self._og_search_property(
 109             'duration', webpage, default=None)) or parse_duration(
 110             self._search_regex(
 111                 r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
 112                 webpage, 'duration', fatal=False))
 113
 114         formats = []
 115
 116         video_url = compat_urllib_parse_unquote(self._search_regex(
 117             r'flv_url=(.+?)&', webpage, 'video URL', default=''))
 118         if video_url:
 119             formats.append({
 120                 'url': video_url,
 121                 'format_id': 'flv',
 122             })
 123
 124         for kind, _, format_url in re.findall(
 125                 r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
 126             format_id = kind.lower()
 127             if format_id == 'hls':
 128                 formats.extend(self._extract_m3u8_formats(
 129                     format_url, video_id, 'mp4',
 130                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 131             elif format_id in ('urllow', 'urlhigh'):
 132                 formats.append({
 133                     'url': format_url,
 134                     'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
 135                     'quality': -2 if format_id.endswith('low') else None,
 136                 })
 137
 138         self._sort_formats(formats)
 139
 140         return {
 141             'id': video_id,
 142             'formats': formats,
 143             'title': title,
 144             'duration': duration,
 145             'thumbnails': thumbnails,
 146             'age_limit': 18,
 147         }