_ 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 )
  12
  13
  14 class XVideosIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
  16     _TEST = {
  17         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  18         'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
  19         'info_dict': {
  20             'id': '4588838',
  21             'ext': 'flv',
  22             'title': 'Biker Takes his Girl',
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  32         if mobj:
  33             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  34
  35         video_title = self._html_search_regex(
  36             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  37         video_thumbnail = self._search_regex(
  38             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  39
  40         formats = []
  41
  42         video_url = compat_urllib_parse_unquote(self._search_regex(
  43             r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  44         if video_url:
  45             formats.append({'url': video_url})
  46
  47         player_args = self._search_regex(
  48             r'(?s)new\s+HTML5Player\((.+?)\)', webpage, ' html5 player', default=None)
  49         if player_args:
  50             for arg in player_args.split(','):
  51                 format_url = self._search_regex(
  52                     r'(["\'])(?P<url>https?://.+?)\1', arg, 'url',
  53                     default=None, group='url')
  54                 if not format_url:
  55                     continue
  56                 ext = determine_ext(format_url)
  57                 if ext == 'mp4':
  58                     formats.append({'url': format_url})
  59                 elif ext == 'm3u8':
  60                     formats.extend(self._extract_m3u8_formats(
  61                         format_url, video_id, 'mp4',
  62                         entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  63
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': video_id,
  68             'formats': formats,
  69             'title': video_title,
  70             'thumbnail': video_thumbnail,
  71             'age_limit': 18,
  72         }