Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornoxo.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     str_to_int,
   8 )
   9
  10
  11 class PornoXOIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
  13     _TEST = {
  14         'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
  15         'md5': '582f28ecbaa9e6e24cb90f50f524ce87',
  16         'info_dict': {
  17             'id': '7564',
  18             'ext': 'flv',
  19             'title': 'Striptease From Sexy Secretary!',
  20             'display_id': 'striptease-from-sexy-secretary',
  21             'description': 'md5:0ee35252b685b3883f4a1d38332f9980',
  22             'categories': list,  # NSFW
  23             'thumbnail': r're:https?://.*\.jpg$',
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id, display_id = mobj.groups()
  31
  32         webpage = self._download_webpage(url, video_id)
  33         video_data = self._extract_jwplayer_data(webpage, video_id, require_title=False)
  34
  35         title = self._html_search_regex(
  36             r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
  37
  38         view_count = str_to_int(self._html_search_regex(
  39             r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
  40
  41         categories_str = self._html_search_regex(
  42             r'<meta name="description" content=".*featuring\s*([^"]+)"',
  43             webpage, 'categories', fatal=False)
  44         categories = (
  45             None if categories_str is None
  46             else categories_str.split(','))
  47
  48         video_data.update({
  49             'id': video_id,
  50             'title': title,
  51             'display_id': display_id,
  52             'description': self._html_search_meta('description', webpage),
  53             'categories': categories,
  54             'view_count': view_count,
  55             'age_limit': 18,
  56         })
  57
  58         return video_data