Raphaël G. Git Repositories - youtubedl/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 (
  10     compat_urllib_request,
  11     ExtractorError,
  12 )
  13
  14
  15 class IPrimaIE(InfoExtractor):
  16     _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
  17
  18     _TESTS = [{
  19         'url': 'http://play.iprima.cz/particka/particka-92',
  20         'info_dict': {
  21             'id': '39152',
  22             'ext': 'flv',
  23             'title': 'Partička (92)',
  24             'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
  25             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
  26         },
  27         'params': {
  28             'skip_download': True,  # requires rtmpdump
  29         },
  30     }, {
  31         'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
  32         'info_dict': {
  33             'id': '9718337',
  34             'ext': 'flv',
  35             'title': 'Tchibo Partička - Jarní móda',
  36             'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
  37             'thumbnail': 're:^http:.*\.jpg$',
  38         },
  39         'params': {
  40             'skip_download': True,  # requires rtmpdump
  41         },
  42         'skip': 'Do not have permission to access this page',
  43     }]
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_id = mobj.group('id')
  48
  49         webpage = self._download_webpage(url, video_id)
  50
  51         if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
  52             raise ExtractorError(
  53                 '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
  54
  55         player_url = (
  56             'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
  57             (floor(random()*1073741824), floor(random()*1073741824))
  58         )
  59
  60         req = compat_urllib_request.Request(player_url)
  61         req.add_header('Referer', url)
  62         playerpage = self._download_webpage(req, video_id)
  63
  64         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
  65
  66         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
  67         if zoneGEO != '0':
  68             base_url = base_url.replace('token', 'token_' + zoneGEO)
  69
  70         formats = []
  71         for format_id in ['lq', 'hq', 'hd']:
  72             filename = self._html_search_regex(
  73                 r'"%s_id":(.+?),' % format_id, webpage, 'filename')
  74
  75             if filename == 'null':
  76                 continue
  77
  78             real_id = self._search_regex(
  79                 r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
  80                 filename, 'real video id')
  81
  82             if format_id == 'lq':
  83                 quality = 0
  84             elif format_id == 'hq':
  85                 quality = 1
  86             elif format_id == 'hd':
  87                 quality = 2
  88                 filename = 'hq/' + filename
  89
  90             formats.append({
  91                 'format_id': format_id,
  92                 'url': base_url,
  93                 'quality': quality,
  94                 'play_path': 'mp4:' + filename.replace('"', '')[:-4],
  95                 'rtmp_live': True,
  96                 'ext': 'flv',
  97             })
  98
  99         self._sort_formats(formats)
 100
 101         return {
 102             'id': real_id,
 103             'title': self._og_search_title(webpage),
 104             'thumbnail': self._og_search_thumbnail(webpage),
 105             'formats': formats,
 106             'description': self._og_search_description(webpage),
 107         }