yt_dlp/extractor/goshgay.py

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