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'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
  18     _TEST = {
  19         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  20         'md5': '14cea69fcb84db54293b1e971466c2e1',
  21         'info_dict': {
  22             'id': '4588838',
  23             'ext': 'mp4',
  24             'title': 'Biker Takes his Girl',
  25             'duration': 108,
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  35         if mobj:
  36             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  37
  38         video_title = self._html_search_regex(
  39             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  40         video_thumbnail = self._search_regex(
  41             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  42         video_duration = int_or_none(self._og_search_property(
  43             'duration', webpage, default=None)) or parse_duration(
  44             self._search_regex(
  45                 r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
  46                 webpage, 'duration', fatal=False))
  47
  48         formats = []
  49
  50         video_url = compat_urllib_parse_unquote(self._search_regex(
  51             r'flv_url=(.+?)&', webpage, 'video URL', default=''))
  52         if video_url:
  53             formats.append({
  54                 'url': video_url,
  55                 'format_id': 'flv',
  56             })
  57
  58         for kind, _, format_url in re.findall(
  59                 r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
  60             format_id = kind.lower()
  61             if format_id == 'hls':
  62                 formats.extend(self._extract_m3u8_formats(
  63                     format_url, video_id, 'mp4',
  64                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  65             elif format_id in ('urllow', 'urlhigh'):
  66                 formats.append({
  67                     'url': format_url,
  68                     'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
  69                     'quality': -2 if format_id.endswith('low') else None,
  70                 })
  71
  72         self._sort_formats(formats)
  73
  74         return {
  75             'id': video_id,
  76             'formats': formats,
  77             'title': video_title,
  78             'duration': video_duration,
  79             'thumbnail': video_thumbnail,
  80             'age_limit': 18,
  81         }