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>[^/?#&]+)'
  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         'url': 'https://www.pornflip.com/v/EkRD6-vS2-s',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://www.pornflip.com/embed/EkRD6-vS2-s',
  42         'only_matching': True,
  43     }, {
  44         'url': 'https://www.pornflip.com/v/NG9q6Pb_iK8',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50
  51         webpage = self._download_webpage(
  52             'https://www.pornflip.com/v/%s' % video_id, video_id)
  53
  54         flashvars = compat_parse_qs(self._search_regex(
  55             r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
  56             webpage, 'flashvars', group='flashvars'))
  57
  58         title = flashvars['video_vars[title]'][0]
  59
  60         def flashvar(kind):
  61             return try_get(
  62                 flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
  63
  64         formats = []
  65         for key, value in flashvars.items():
  66             if not (value and isinstance(value, list)):
  67                 continue
  68             format_url = value[0]
  69             if key == 'video_vars[hds_manifest]':
  70                 formats.extend(self._extract_mpd_formats(
  71                     format_url, video_id, mpd_id='dash', fatal=False))
  72                 continue
  73             height = self._search_regex(
  74                 r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
  75             if not height:
  76                 continue
  77             formats.append({
  78                 'url': format_url,
  79                 'format_id': 'http-%s' % height,
  80                 'height': int_or_none(height),
  81             })
  82         self._sort_formats(formats)
  83
  84         uploader = self._html_search_regex(
  85             (r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
  86              r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
  87             webpage, 'uploader', fatal=False, group='uploader')
  88
  89         return {
  90             'id': video_id,
  91             'formats': formats,
  92             'title': title,
  93             'thumbnail': flashvar('big_thumb'),
  94             'duration': int_or_none(flashvar('duration')),
  95             'timestamp': unified_timestamp(self._html_search_meta(
  96                 'uploadDate', webpage, 'timestamp')),
  97             'uploader_id': flashvar('author_id'),
  98             'uploader': uploader,
  99             'view_count': int_or_none(flashvar('views')),
 100             'age_limit': 18,
 101         }