yt_dlp/extractor/goshgay.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_parse_qs,
   4 )
   5 from ..utils import (
   6     parse_duration,
   7 )
   8
   9
  10 class GoshgayIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
  12     _TEST = {
  13         'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
  14         'md5': '4b6db9a0a333142eb9f15913142b0ed1',
  15         'info_dict': {
  16             'id': '299069',
  17             'ext': 'flv',
  18             'title': 'DIESEL SFW XXX Video',
  19             'thumbnail': r're:^http://.*\.jpg$',
  20             'duration': 80,
  21             'age_limit': 18,
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27         webpage = self._download_webpage(url, video_id)
  28
  29         title = self._html_search_regex(
  30             r'<h2>(.*?)<', webpage, 'title')
  31         duration = parse_duration(self._html_search_regex(
  32             r'<span class="duration">\s*-?\s*(.*?)</span>',
  33             webpage, 'duration', fatal=False))
  34
  35         flashvars = compat_parse_qs(self._html_search_regex(
  36             r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
  37             webpage, 'flashvars'))
  38         thumbnail = flashvars.get('url_bigthumb', [None])[0]
  39         video_url = flashvars['flv_url'][0]
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'title': title,
  45             'thumbnail': thumbnail,
  46             'duration': duration,
  47             'age_limit': 18,
  48         }