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 ..compat import (
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     remove_end,
  15 )
  16
  17
  18 class IPrimaIE(InfoExtractor):
  19     _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
  20
  21     _TESTS = [{
  22         'url': 'http://play.iprima.cz/particka/particka-92',
  23         'info_dict': {
  24             'id': '39152',
  25             'ext': 'flv',
  26             'title': 'Partička (92)',
  27             'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
  28             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
  29         },
  30         'params': {
  31             'skip_download': True,  # requires rtmpdump
  32         },
  33     }, {
  34         'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
  35         'info_dict': {
  36             'id': '9718337',
  37             'ext': 'flv',
  38             'title': 'Tchibo Partička - Jarní móda',
  39             'thumbnail': 're:^http:.*\.jpg$',
  40         },
  41         'params': {
  42             'skip_download': True,  # requires rtmpdump
  43         },
  44     }, {
  45         'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         video_id = mobj.group('id')
  52
  53         webpage = self._download_webpage(url, video_id)
  54
  55         if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
  56             raise ExtractorError(
  57                 '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
  58
  59         player_url = (
  60             'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
  61             (floor(random() * 1073741824), floor(random() * 1073741824))
  62         )
  63
  64         req = compat_urllib_request.Request(player_url)
  65         req.add_header('Referer', url)
  66         playerpage = self._download_webpage(req, video_id)
  67
  68         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
  69
  70         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
  71         if zoneGEO != '0':
  72             base_url = base_url.replace('token', 'token_' + zoneGEO)
  73
  74         formats = []
  75         for format_id in ['lq', 'hq', 'hd']:
  76             filename = self._html_search_regex(
  77                 r'"%s_id":(.+?),' % format_id, webpage, 'filename')
  78
  79             if filename == 'null':
  80                 continue
  81
  82             real_id = self._search_regex(
  83                 r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
  84                 filename, 'real video id')
  85
  86             if format_id == 'lq':
  87                 quality = 0
  88             elif format_id == 'hq':
  89                 quality = 1
  90             elif format_id == 'hd':
  91                 quality = 2
  92                 filename = 'hq/' + filename
  93
  94             formats.append({
  95                 'format_id': format_id,
  96                 'url': base_url,
  97                 'quality': quality,
  98                 'play_path': 'mp4:' + filename.replace('"', '')[:-4],
  99                 'rtmp_live': True,
 100                 'ext': 'flv',
 101             })
 102
 103         self._sort_formats(formats)
 104
 105         return {
 106             'id': real_id,
 107             'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
 108             'thumbnail': self._og_search_thumbnail(webpage),
 109             'formats': formats,
 110             'description': self._search_regex(
 111                 r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
 112                 webpage, 'description', default=None),
 113         }