_ Git - youtube-dl/blob - 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,  # requires rtmpdump
  26         },
  27     }, {
  28         'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
  29         'info_dict': {
  30             'id': '9718337',
  31             'ext': 'flv',
  32             'title': 'Tchibo Partička - Jarní móda',
  33             'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
  34             'thumbnail': 're:^http:.*\.jpg$',
  35         },
  36         'params': {
  37             'skip_download': True,  # requires rtmpdump
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('id')
  44
  45         webpage = self._download_webpage(url, video_id)
  46
  47         player_url = (
  48             'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
  49             (floor(random()*1073741824), floor(random()*1073741824))
  50
  51         req = compat_urllib_request.Request(player_url)
  52         req.add_header('Referer', url)
  53         playerpage = self._download_webpage(req, video_id)
  54
  55         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
  56
  57         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
  58         if zoneGEO != '0':
  59             base_url = base_url.replace('token', 'token_' + zoneGEO)
  60
  61         formats = []
  62         for format_id in ['lq', 'hq', 'hd']:
  63             filename = self._html_search_regex(
  64                 r'"%s_id":(.+?),' % format_id, webpage, 'filename')
  65
  66             if filename == 'null':
  67                 continue
  68
  69             real_id = self._search_regex(
  70                 r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
  71                 filename, 'real video id')
  72
  73             if format_id == 'lq':
  74                 quality = 0
  75             elif format_id == 'hq':
  76                 quality = 1
  77             elif format_id == 'hd':
  78                 quality = 2
  79                 filename = 'hq/' + filename
  80
  81             formats.append({
  82                 'format_id': format_id,
  83                 'url': base_url,
  84                 'quality': quality,
  85                 'play_path': 'mp4:' + filename.replace('"', '')[:-4],
  86                 'rtmp_live': True,
  87                 'ext': 'flv',
  88             })
  89
  90         self._sort_formats(formats)
  91
  92         return {
  93             'id': real_id,
  94             'title': self._og_search_title(webpage),
  95             'thumbnail': self._og_search_thumbnail(webpage),
  96             'formats': formats,
  97             'description': self._og_search_description(webpage),
  98         }