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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import url_basename
   8
   9
  10 class BehindKinkIE(InfoExtractor):
  11     _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
  12     _TEST = {
  13         'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
  14         'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
  15         'info_dict': {
  16             'id': '37127',
  17             'ext': 'mp4',
  18             'title': 'What are you passionate about – Marley Blaze',
  19             'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
  20             'upload_date': '20141205',
  21             'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
  22             'age_limit': 18,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         display_id = mobj.group('id')
  29
  30         webpage = self._download_webpage(url, display_id)
  31
  32         video_url = self._search_regex(
  33             r'<source src="([^"]+)"', webpage, 'video URL')
  34         video_id = url_basename(video_url).split('_')[0]
  35         upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
  36
  37         return {
  38             'id': video_id,
  39             'display_id': display_id,
  40             'url': video_url,
  41             'title': self._og_search_title(webpage),
  42             'thumbnail': self._og_search_thumbnail(webpage),
  43             'description': self._og_search_description(webpage),
  44             'upload_date': upload_date,
  45             'age_limit': 18,
  46         }