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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 _translation_table = {
  10     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
  11     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
  12     'y': 'l', 'z': 'i',
  13     '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
  14 }
  15
  16
  17 def _decode(s):
  18     return ''.join(_translation_table.get(c, c) for c in s)
  19
  20
  21 class CliphunterIE(InfoExtractor):
  22     IE_NAME = 'cliphunter'
  23
  24     _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
  25         (?P<id>[0-9]+)/
  26         (?P<seo>.+?)(?:$|[#\?])
  27     '''
  28     _TEST = {
  29         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  30         'md5': 'a2ba71eebf523859fe527a61018f723e',
  31         'info_dict': {
  32             'id': '1012420',
  33             'ext': 'mp4',
  34             'title': 'Fun Jynx Maze solo',
  35             'thumbnail': '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         pl_fiji = self._search_regex(
  48             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
  49         pl_c_qual = self._search_regex(
  50             r'pl_c_qual = "(.)"', webpage, 'video quality')
  51         video_url = _decode(pl_fiji)
  52         formats = [{
  53             'url': video_url,
  54             'format_id': 'default-%s' % pl_c_qual,
  55         }]
  56
  57         qualities_json = self._search_regex(
  58             r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
  59         qualities_data = json.loads(qualities_json)
  60
  61         for i, t in enumerate(
  62                 re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
  63             quality_id, crypted_url = t
  64             video_url = _decode(crypted_url)
  65             f = {
  66                 'format_id': quality_id,
  67                 'url': video_url,
  68                 'quality': i,
  69             }
  70             if quality_id in qualities_data:
  71                 qd = qualities_data[quality_id]
  72                 m = re.match(
  73                     r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
  74                         \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
  75                 if m:
  76                     f['width'] = int(m.group('width'))
  77                     f['height'] = int(m.group('height'))
  78                     f['tbr'] = int(m.group('tbr'))
  79             formats.append(f)
  80         self._sort_formats(formats)
  81
  82         thumbnail = self._search_regex(
  83             r"var\s+mov_thumb\s*=\s*'([^']+)';",
  84             webpage, 'thumbnail', fatal=False)
  85
  86         return {
  87             'id': video_id,
  88             'title': video_title,
  89             'formats': formats,
  90             'age_limit': self._rta_search(webpage),
  91             'thumbnail': thumbnail,
  92         }