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