youtube_dl/extractor/goshgay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_parse_qs,
   7 )
   8 from ..utils import (
   9     parse_duration,
  10 )
  11
  12
  13 class GoshgayIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
  15     _TEST = {
  16         'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
  17         'md5': '4b6db9a0a333142eb9f15913142b0ed1',
  18         'info_dict': {
  19             'id': '299069',
  20             'ext': 'flv',
  21             'title': 'DIESEL SFW XXX Video',
  22             'thumbnail': 're:^http://.*\.jpg$',
  23             'duration': 80,
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         title = self._html_search_regex(
  33             r'<h2>(.*?)<', webpage, 'title')
  34         duration = parse_duration(self._html_search_regex(
  35             r'<span class="duration">\s*-?\s*(.*?)</span>',
  36             webpage, 'duration', fatal=False))
  37
  38         flashvars = compat_parse_qs(self._html_search_regex(
  39             r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
  40             webpage, 'flashvars'))
  41         thumbnail = flashvars.get('url_bigthumb', [None])[0]
  42         video_url = flashvars['flv_url'][0]
  43
  44         return {
  45             'id': video_id,
  46             'url': video_url,
  47             'title': title,
  48             'thumbnail': thumbnail,
  49             'duration': duration,
  50             'age_limit': 18,
  51         }