youtube_dl/extractor/alphaporno.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_iso8601,
   6     parse_duration,
   7     parse_filesize,
   8     int_or_none,
   9 )
  10
  11
  12 class AlphaPornoIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
  14     _TEST = {
  15         'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
  16         'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
  17         'info_dict': {
  18             'id': '258807',
  19             'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
  20             'ext': 'mp4',
  21             'title': 'Sensual striptease porn with Samantha Alexandra',
  22             'thumbnail': 're:https?://.*\.jpg$',
  23             'timestamp': 1418694611,
  24             'upload_date': '20141216',
  25             'duration': 387,
  26             'filesize_approx': 54120000,
  27             'tbr': 1145,
  28             'categories': list,
  29             'age_limit': 18,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(url, display_id)
  37
  38         video_id = self._search_regex(
  39             r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
  40
  41         video_url = self._search_regex(
  42             r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
  43         ext = self._html_search_meta(
  44             'encodingFormat', webpage, 'ext', default='.mp4')[1:]
  45
  46         title = self._search_regex(
  47             [r'<meta content="([^"]+)" itemprop="description">',
  48              r'class="title" itemprop="name">([^<]+)<'],
  49             webpage, 'title')
  50         thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
  51         timestamp = parse_iso8601(self._html_search_meta(
  52             'uploadDate', webpage, 'upload date'))
  53         duration = parse_duration(self._html_search_meta(
  54             'duration', webpage, 'duration'))
  55         filesize_approx = parse_filesize(self._html_search_meta(
  56             'contentSize', webpage, 'file size'))
  57         bitrate = int_or_none(self._html_search_meta(
  58             'bitrate', webpage, 'bitrate'))
  59         categories = self._html_search_meta(
  60             'keywords', webpage, 'categories', default='').split(',')
  61
  62         age_limit = self._rta_search(webpage)
  63
  64         return {
  65             'id': video_id,
  66             'display_id': display_id,
  67             'url': video_url,
  68             'ext': ext,
  69             'title': title,
  70             'thumbnail': thumbnail,
  71             'timestamp': timestamp,
  72             'duration': duration,
  73             'filesize_approx': filesize_approx,
  74             'tbr': bitrate,
  75             'categories': categories,
  76             'age_limit': age_limit,
  77         }