youtube_dl/extractor/iprima.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from random import random
   6 from math import floor
   7
   8 from .common import InfoExtractor
   9 from ..utils import compat_urllib_request
  10
  11
  12 class IPrimaIE(InfoExtractor):
  13     _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
  14
  15     _TESTS = [{
  16         'url': 'http://play.iprima.cz/particka/particka-92',
  17         'info_dict': {
  18             'id': '39152',
  19             'ext': 'flv',
  20             'title': 'Partička (92)',
  21             'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
  22             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
  23         },
  24         'params': {
  25             'skip_download': True,
  26         },
  27     },
  28     ]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33
  34         webpage = self._download_webpage(url, video_id)
  35
  36         player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
  37                          floor(random()*1073741824),
  38                          floor(random()*1073741824))
  39
  40         req = compat_urllib_request.Request(player_url)
  41         req.add_header('Referer', url)
  42         playerpage = self._download_webpage(req, video_id)
  43
  44         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
  45
  46         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
  47         if zoneGEO != '0':
  48             base_url = base_url.replace('token', 'token_' + zoneGEO)
  49
  50         formats = []
  51         for format_id in ['lq', 'hq', 'hd']:
  52             filename = self._html_search_regex(
  53                 r'"%s_id":(.+?),' % format_id, webpage, 'filename')
  54
  55             if filename == 'null':
  56                 continue
  57
  58             real_id = self._search_regex(
  59                 r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
  60
  61             if format_id == 'lq':
  62                 quality = 0
  63             elif format_id == 'hq':
  64                 quality = 1
  65             elif format_id == 'hd':
  66                 quality = 2
  67                 filename = 'hq/' + filename
  68
  69             formats.append({
  70                 'format_id': format_id,
  71                 'url': base_url,
  72                 'quality': quality,
  73                 'play_path': 'mp4:' + filename.replace('"', '')[:-4],
  74                 'rtmp_live': True,
  75                 'ext': 'flv',
  76             })
  77
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': real_id,
  82             'title': self._og_search_title(webpage),
  83             'thumbnail': self._og_search_thumbnail(webpage),
  84             'formats': formats,
  85             'description': self._og_search_description(webpage),
  86         }