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 from ..utils import int_or_none
   8
   9
  10 _translation_table = {
  11     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
  12     'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
  13     'y': 'l', 'z': 'i',
  14     '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
  15 }
  16
  17
  18 def _decode(s):
  19     return ''.join(_translation_table.get(c, c) for c in s)
  20
  21
  22 class CliphunterIE(InfoExtractor):
  23     IE_NAME = 'cliphunter'
  24
  25     _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
  26         (?P<id>[0-9]+)/
  27         (?P<seo>.+?)(?:$|[#\?])
  28     '''
  29     _TEST = {
  30         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  31         'md5': 'a2ba71eebf523859fe527a61018f723e',
  32         'info_dict': {
  33             'id': '1012420',
  34             'ext': 'mp4',
  35             'title': 'Fun Jynx Maze solo',
  36             'thumbnail': 're:^https?://.*\.jpg$',
  37             'age_limit': 18,
  38             'duration': 1317,
  39         }
  40     }
  41
  42     def _real_extract(self, url):
  43         mobj = re.match(self._VALID_URL, url)
  44         video_id = mobj.group('id')
  45
  46         webpage = self._download_webpage(url, video_id)
  47
  48         video_title = self._search_regex(
  49             r'mediaTitle = "([^"]+)"', webpage, 'title')
  50
  51         pl_fiji = self._search_regex(
  52             r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
  53         pl_c_qual = self._search_regex(
  54             r'pl_c_qual = "(.)"', webpage, 'video quality')
  55         video_url = _decode(pl_fiji)
  56         formats = [{
  57             'url': video_url,
  58             'format_id': 'default-%s' % pl_c_qual,
  59         }]
  60
  61         qualities_json = self._search_regex(
  62             r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
  63         qualities_data = json.loads(qualities_json)
  64
  65         for i, t in enumerate(
  66                 re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
  67             quality_id, crypted_url = t
  68             video_url = _decode(crypted_url)
  69             f = {
  70                 'format_id': quality_id,
  71                 'url': video_url,
  72                 'quality': i,
  73             }
  74             if quality_id in qualities_data:
  75                 qd = qualities_data[quality_id]
  76                 m = re.match(
  77                     r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
  78                         \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
  79                 if m:
  80                     f['width'] = int(m.group('width'))
  81                     f['height'] = int(m.group('height'))
  82                     f['tbr'] = int(m.group('tbr'))
  83             formats.append(f)
  84         self._sort_formats(formats)
  85
  86         thumbnail = self._search_regex(
  87             r"var\s+mov_thumb\s*=\s*'([^']+)';",
  88             webpage, 'thumbnail', fatal=False)
  89         duration = int_or_none(self._search_regex(
  90             r'pl_dur\s*=\s*([0-9]+)', webpage, 'duration', fatal=False))
  91
  92         return {
  93             'id': video_id,
  94             'title': video_title,
  95             'formats': formats,
  96             'duration': duration,
  97             'age_limit': self._rta_search(webpage),
  98             'thumbnail': thumbnail,
  99         }