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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 translation_table = {
   9     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
  10     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
  11     'y': 'l', 'z': 'i',
  12     '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
  13 }
  14
  15
  16 class CliphunterIE(InfoExtractor):
  17     IE_NAME = 'cliphunter'
  18
  19     _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
  20         (?P<id>[0-9]+)/
  21         (?P<seo>.+?)(?:$|[#\?])
  22     '''
  23     _TEST = {
  24         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  25         'file': '1012420.flv',
  26         'md5': '15e7740f30428abf70f4223478dc1225',
  27         'info_dict': {
  28             'title': 'Fun Jynx Maze solo',
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         pl_fiji = self._search_regex(
  39             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
  40         pl_c_qual = self._search_regex(
  41             r'pl_c_qual = "(.)"', webpage, 'video quality')
  42         video_title = self._search_regex(
  43             r'mediaTitle = "([^"]+)"', webpage, 'title')
  44
  45         video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
  46
  47         formats = [{
  48             'url': video_url,
  49             'format_id': pl_c_qual,
  50         }]
  51
  52         return {
  53             'id': video_id,
  54             'title': video_title,
  55             'formats': formats,
  56         }