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

   1 from __future__ import unicode_literals
   2
   3 import random
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class Laola1TvIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
  11     _TEST = {
  12         'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
  13         'info_dict': {
  14             'id': '250019',
  15             'ext': 'mp4',
  16             'title': 'Bitburger Open Grand Prix Gold - Court 1',
  17             'categories': ['Badminton'],
  18             'uploader': 'BWF - Badminton World Federation',
  19             'is_live': True,
  20         },
  21         'params': {
  22             'skip_download': True,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         lang = mobj.group('lang')
  30         portal = mobj.group('portal')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         iframe_url = self._search_regex(
  34             r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
  35             webpage, 'iframe URL')
  36
  37         iframe = self._download_webpage(
  38             iframe_url, video_id, note='Downloading iframe')
  39         flashvars_m = re.findall(
  40             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
  41         flashvars = dict((m[0], m[1]) for m in flashvars_m)
  42
  43         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  44                    'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
  45                        video_id, portal, lang))
  46         hd_doc = self._download_xml(xml_url, video_id)
  47
  48         title = hd_doc.find('.//video/title').text
  49         flash_url = hd_doc.find('.//video/url').text
  50         categories = hd_doc.find('.//video/meta_sports').text.split(',')
  51         uploader = hd_doc.find('.//video/meta_organistation').text
  52
  53         ident = random.randint(10000000, 99999999)
  54         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
  55             flash_url, ident, flashvars['timestamp'], flashvars['auth'])
  56
  57         token_doc = self._download_xml(
  58             token_url, video_id, note='Downloading token')
  59         token_attrib = token_doc.find('.//token').attrib
  60         if token_attrib.get('auth') == 'blocked':
  61             raise ExtractorError('Token error: ' % token_attrib.get('comment'))
  62
  63         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
  64             token_attrib['url'], token_attrib['auth'])
  65
  66         return {
  67             'id': video_id,
  68             'is_live': True,
  69             'title': title,
  70             'url': video_url,
  71             'uploader': uploader,
  72             'categories': categories,
  73             'ext': 'mp4',
  74         }
  75