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 int_or_none
   5
   6
   7 _translation_table = {
   8     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
   9     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
  10     'y': 'l', 'z': 'i',
  11     '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
  12 }
  13
  14
  15 def _decode(s):
  16     return ''.join(_translation_table.get(c, c) for c in s)
  17
  18
  19 class CliphunterIE(InfoExtractor):
  20     IE_NAME = 'cliphunter'
  21
  22     _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
  23         (?P<id>[0-9]+)/
  24         (?P<seo>.+?)(?:$|[#\?])
  25     '''
  26     _TESTS = [{
  27         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  28         'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
  29         'info_dict': {
  30             'id': '1012420',
  31             'ext': 'flv',
  32             'title': 'Fun Jynx Maze solo',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'age_limit': 18,
  35         },
  36         'skip': 'Video gone',
  37     }, {
  38         'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
  39         'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
  40         'info_dict': {
  41             'id': '2019449',
  42             'ext': 'mp4',
  43             'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
  44             'thumbnail': r're:^https?://.*\.jpg$',
  45             'age_limit': 18,
  46         },
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51         webpage = self._download_webpage(url, video_id)
  52
  53         video_title = self._search_regex(
  54             r'mediaTitle = "([^"]+)"', webpage, 'title')
  55
  56         gexo_files = self._parse_json(
  57             self._search_regex(
  58                 r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
  59             video_id)
  60
  61         formats = []
  62         for format_id, f in gexo_files.items():
  63             video_url = f.get('url')
  64             if not video_url:
  65                 continue
  66             fmt = f.get('fmt')
  67             height = f.get('h')
  68             format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
  69             formats.append({
  70                 'url': _decode(video_url),
  71                 'format_id': format_id,
  72                 'width': int_or_none(f.get('w')),
  73                 'height': int_or_none(height),
  74                 'tbr': int_or_none(f.get('br')),
  75             })
  76         self._sort_formats(formats)
  77
  78         thumbnail = self._search_regex(
  79             r"var\s+mov_thumb\s*=\s*'([^']+)';",
  80             webpage, 'thumbnail', fatal=False)
  81
  82         return {
  83             'id': video_id,
  84             'title': video_title,
  85             'formats': formats,
  86             'age_limit': self._rta_search(webpage),
  87             'thumbnail': thumbnail,
  88         }