_ Git - youtube-dl/blob - youtube_dl/extractor/laola1tv.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urlparse,
   9     ExtractorError,
  10     sanitized_Request,
  11     xpath_element,
  12     xpath_text,
  13     unified_strdate,
  14     urlencode_postdata,
  15 )
  16
  17
  18 class Laola1TvIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<slug>[\w-]+)'
  20     _TESTS = [{
  21         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
  22         'info_dict': {
  23             'categories': ['Eishockey'],
  24             'ext': 'flv',
  25             'id': '227883',
  26             'is_live': False,
  27             'title': 'Straubing Tigers - Kölner Haie',
  28             'upload_date': '20140912',
  29         },
  30         'params': {
  31             'skip_download': True,
  32         }
  33     }, {
  34         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
  35         'info_dict': {
  36             'categories': ['Eishockey'],
  37             'ext': 'flv',
  38             'id': '464602',
  39             'is_live': False,
  40             'title': 'Straubing Tigers - Kölner Haie',
  41             'upload_date': '20160129',
  42         },
  43         'params': {
  44             'skip_download': True,
  45         }
  46     }]
  47
  48     def _real_extract(self, url):
  49         mobj = re.match(self._VALID_URL, url)
  50         lang = mobj.group('lang')
  51         portal = mobj.group('portal')
  52
  53         webpage = self._download_webpage(url, mobj.group('slug'))
  54         iframe_url = self._search_regex(
  55             r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
  56             webpage, 'iframe URL')
  57
  58         video_id = self._search_regex(
  59             r'videoid=(\d+)', iframe_url, 'video ID')
  60
  61         iframe = self._download_webpage(compat_urlparse.urljoin(
  62             url, iframe_url), video_id, note='Downloading iframe')
  63
  64         partner_id = self._search_regex(
  65             r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner ID')
  66
  67         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  68                    'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % (
  69                        video_id, partner_id, portal, lang))
  70         hd_doc = self._download_xml(xml_url, video_id)
  71
  72         _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
  73         title = _v('title', fatal=True)
  74
  75         categories = _v('meta_sports')
  76         if categories:
  77             categories = categories.split(',')
  78
  79         time_date = _v('time_date')
  80         time_start = _v('time_start')
  81         upload_date = None
  82         if time_date and time_start:
  83             upload_date = unified_strdate(time_date + ' ' + time_start)
  84
  85         json_url = ('https://club.laola1.tv/sp/laola1/api/v3/user/session' +
  86                     '/premium/player/stream-access?videoId=%s&target=2' +
  87                     '&label=laola1tv&area=%s') % (video_id, _v('area'))
  88         req = sanitized_Request(json_url, urlencode_postdata(
  89             dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
  90
  91         token_url = self._download_json(req, video_id)['data']['stream-access'][0]
  92         token_doc = self._download_xml(
  93             token_url, video_id, note='Downloading token')
  94
  95         token_attrib = xpath_element(token_doc, './/token').attrib
  96         token_auth = token_attrib['auth']
  97
  98         if token_auth in ('blocked', 'restricted'):
  99             raise ExtractorError(
 100                 'Token error: %s' % token_attrib['comment'], expected=True)
 101
 102         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth)
 103
 104         return {
 105             'categories': categories,
 106             'formats': self._extract_f4m_formats(
 107                 video_url, video_id, f4m_id='hds'),
 108             'id': video_id,
 109             'is_live': _v('islive') == 'true',
 110             'title': title,
 111             'upload_date': upload_date,
 112             'uploader': _v('meta_organisation'),
 113         }