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             'description': 'Striptease From Sexy Secretary!',
  21             'categories': list,  # NSFW
  22             'thumbnail': 're:https?://.*\.jpg$',
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_url = self._html_search_regex(
  34             r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url')
  35
  36         title = self._html_search_regex(
  37             r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
  38
  39         description = self._html_search_regex(
  40             r'<meta name="description" content="([^"]+)\s*featuring',
  41             webpage, 'description', fatal=False)
  42
  43         thumbnail = self._html_search_regex(
  44             r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
  45
  46         view_count = str_to_int(self._html_search_regex(
  47             r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
  48
  49         categories_str = self._html_search_regex(
  50             r'<meta name="description" content=".*featuring\s*([^"]+)"',
  51             webpage, 'categories', fatal=False)
  52         categories = (
  53             None if categories_str is None
  54             else categories_str.split(','))
  55
  56         return {
  57             'id': video_id,
  58             'url': video_url,
  59             'title': title,
  60             'description': description,
  61             'thumbnail': thumbnail,
  62             'categories': categories,
  63             'view_count': view_count,
  64             'age_limit': 18,
  65         }