Raphaël G. Git Repositories - youtubedl/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     _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31         lang = mobj.group('lang')
  32         portal = mobj.group('portal')
  33
  34         webpage = self._download_webpage(url, video_id)
  35         iframe_url = self._search_regex(
  36             r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
  37             webpage, 'iframe URL')
  38
  39         iframe = self._download_webpage(
  40             iframe_url, video_id, note='Downloading iframe')
  41         flashvars_m = re.findall(
  42             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
  43         flashvars = dict((m[0], m[1]) for m in flashvars_m)
  44
  45         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  46                    'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
  47                        video_id, portal, lang))
  48         hd_doc = self._download_xml(xml_url, video_id)
  49
  50         title = hd_doc.find('.//video/title').text
  51         flash_url = hd_doc.find('.//video/url').text
  52         categories = hd_doc.find('.//video/meta_sports').text.split(',')
  53         uploader = hd_doc.find('.//video/meta_organistation').text
  54
  55         ident = random.randint(10000000, 99999999)
  56         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
  57             flash_url, ident, flashvars['timestamp'], flashvars['auth'])
  58
  59         token_doc = self._download_xml(
  60             token_url, video_id, note='Downloading token')
  61         token_attrib = token_doc.find('.//token').attrib
  62         if token_attrib.get('auth') == 'blocked':
  63             raise ExtractorError('Token error: ' % token_attrib.get('comment'))
  64
  65         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
  66             token_attrib['url'], token_attrib['auth'])
  67
  68         return {
  69             'id': video_id,
  70             'is_live': True,
  71             'title': title,
  72             'url': video_url,
  73             'uploader': uploader,
  74             'categories': categories,
  75             'ext': 'mp4',
  76         }
  77