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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     url_or_none,
   7 )
   8
   9
  10 class CliphunterIE(InfoExtractor):
  11     IE_NAME = 'cliphunter'
  12
  13     _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
  14         (?P<id>[0-9]+)/
  15         (?P<seo>.+?)(?:$|[#\?])
  16     '''
  17     _TESTS = [{
  18         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  19         'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
  20         'info_dict': {
  21             'id': '1012420',
  22             'ext': 'flv',
  23             'title': 'Fun Jynx Maze solo',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'age_limit': 18,
  26         },
  27         'skip': 'Video gone',
  28     }, {
  29         'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
  30         'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
  31         'info_dict': {
  32             'id': '2019449',
  33             'ext': 'mp4',
  34             'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
  35             'thumbnail': r're:^https?://.*\.jpg$',
  36             'age_limit': 18,
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage(url, video_id)
  43
  44         video_title = self._search_regex(
  45             r'mediaTitle = "([^"]+)"', webpage, 'title')
  46
  47         gexo_files = self._parse_json(
  48             self._search_regex(
  49                 r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
  50             video_id)
  51
  52         formats = []
  53         for format_id, f in gexo_files.items():
  54             video_url = url_or_none(f.get('url'))
  55             if not video_url:
  56                 continue
  57             fmt = f.get('fmt')
  58             height = f.get('h')
  59             format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
  60             formats.append({
  61                 'url': video_url,
  62                 'format_id': format_id,
  63                 'width': int_or_none(f.get('w')),
  64                 'height': int_or_none(height),
  65                 'tbr': int_or_none(f.get('br')),
  66             })
  67         self._sort_formats(formats)
  68
  69         thumbnail = self._search_regex(
  70             r"var\s+mov_thumb\s*=\s*'([^']+)';",
  71             webpage, 'thumbnail', fatal=False)
  72
  73         return {
  74             'id': video_id,
  75             'title': video_title,
  76             'formats': formats,
  77             'age_limit': self._rta_search(webpage),
  78             'thumbnail': thumbnail,
  79         }