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 from ..utils import ExtractorError
   8
   9
  10 class Laola1TvIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
  12     _TEST = {
  13         'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
  14         'info_dict': {
  15             'id': '250019',
  16             'ext': 'mp4',
  17             'title': 'Bitburger Open Grand Prix Gold - Court 1',
  18             'categories': ['Badminton'],
  19             'uploader': 'BWF - Badminton World Federation',
  20             'is_live': True,
  21         },
  22         'params': {
  23             'skip_download': True,
  24         }
  25     }
  26
  27     _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         lang = mobj.group('lang')
  33         portal = mobj.group('portal')
  34
  35         webpage = self._download_webpage(url, video_id)
  36         iframe_url = self._search_regex(
  37             r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
  38             webpage, 'iframe URL')
  39
  40         iframe = self._download_webpage(
  41             iframe_url, video_id, note='Downloading iframe')
  42         flashvars_m = re.findall(
  43             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
  44         flashvars = dict((m[0], m[1]) for m in flashvars_m)
  45
  46         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  47                    'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
  48                        video_id, portal, lang))
  49         hd_doc = self._download_xml(xml_url, video_id)
  50
  51         title = hd_doc.find('.//video/title').text
  52         flash_url = hd_doc.find('.//video/url').text
  53         categories = hd_doc.find('.//video/meta_sports').text.split(',')
  54         uploader = hd_doc.find('.//video/meta_organistation').text
  55
  56         ident = random.randint(10000000, 99999999)
  57         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
  58             flash_url, ident, flashvars['timestamp'], flashvars['auth'])
  59
  60         token_doc = self._download_xml(
  61             token_url, video_id, note='Downloading token')
  62         token_attrib = token_doc.find('.//token').attrib
  63         if token_attrib.get('auth') == 'blocked':
  64             raise ExtractorError('Token error: ' % token_attrib.get('comment'))
  65
  66         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
  67             token_attrib['url'], token_attrib['auth'])
  68
  69         return {
  70             'id': video_id,
  71             'is_live': True,
  72             'title': title,
  73             'url': video_url,
  74             'uploader': uploader,
  75             'categories': categories,
  76             'ext': 'mp4',
  77         }