Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornflip.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     compat_str,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     try_get,
  12     unified_timestamp,
  13 )
  14
  15
  16 class PornFlipIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z]{11})'
  18     _TESTS = [{
  19         'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
  20         'md5': '98c46639849145ae1fd77af532a9278c',
  21         'info_dict': {
  22             'id': 'wz7DfNhMmep',
  23             'ext': 'mp4',
  24             'title': '2 Amateurs swallow make his dream cumshots true',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'duration': 112,
  27             'timestamp': 1481655502,
  28             'upload_date': '20161213',
  29             'uploader_id': '106786',
  30             'uploader': 'figifoto',
  31             'view_count': int,
  32             'age_limit': 18,
  33         }
  34     }, {
  35         'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(
  43             'https://www.pornflip.com/v/%s' % video_id, video_id)
  44
  45         flashvars = compat_parse_qs(self._search_regex(
  46             r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
  47             webpage, 'flashvars', group='flashvars'))
  48
  49         title = flashvars['video_vars[title]'][0]
  50
  51         def flashvar(kind):
  52             return try_get(
  53                 flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
  54
  55         formats = []
  56         for key, value in flashvars.items():
  57             if not (value and isinstance(value, list)):
  58                 continue
  59             format_url = value[0]
  60             if key == 'video_vars[hds_manifest]':
  61                 formats.extend(self._extract_mpd_formats(
  62                     format_url, video_id, mpd_id='dash', fatal=False))
  63                 continue
  64             height = self._search_regex(
  65                 r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
  66             if not height:
  67                 continue
  68             formats.append({
  69                 'url': format_url,
  70                 'format_id': 'http-%s' % height,
  71                 'height': int_or_none(height),
  72             })
  73         self._sort_formats(formats)
  74
  75         uploader = self._html_search_regex(
  76             (r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
  77              r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
  78             webpage, 'uploader', fatal=False, group='uploader')
  79
  80         return {
  81             'id': video_id,
  82             'formats': formats,
  83             'title': title,
  84             'thumbnail': flashvar('big_thumb'),
  85             'duration': int_or_none(flashvar('duration')),
  86             'timestamp': unified_timestamp(self._html_search_meta(
  87                 'uploadDate', webpage, 'timestamp')),
  88             'uploader_id': flashvar('author_id'),
  89             'uploader': uploader,
  90             'view_count': int_or_none(flashvar('views')),
  91             'age_limit': 18,
  92         }