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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import random
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     xpath_text,
  11 )
  12
  13
  14 class Laola1TvIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
  16     _TEST = {
  17         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
  18         'info_dict': {
  19             'id': '227883',
  20             'ext': 'mp4',
  21             'title': 'Straubing Tigers - Kölner Haie',
  22             'categories': ['Eishockey'],
  23             'is_live': False,
  24         },
  25         'params': {
  26             'skip_download': True,
  27         }
  28     }
  29
  30     _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35         lang = mobj.group('lang')
  36         portal = mobj.group('portal')
  37
  38         webpage = self._download_webpage(url, video_id)
  39         iframe_url = self._search_regex(
  40             r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
  41             webpage, 'iframe URL')
  42
  43         iframe = self._download_webpage(
  44             iframe_url, video_id, note='Downloading iframe')
  45         flashvars_m = re.findall(
  46             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
  47         flashvars = dict((m[0], m[1]) for m in flashvars_m)
  48
  49         partner_id = self._search_regex(
  50             r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id')
  51
  52         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  53                    'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % (
  54                        video_id, partner_id, portal, lang))
  55         hd_doc = self._download_xml(xml_url, video_id)
  56
  57         title = xpath_text(hd_doc, './/video/title', fatal=True)
  58         flash_url = xpath_text(hd_doc, './/video/url', fatal=True)
  59         uploader = xpath_text(hd_doc, './/video/meta_organistation')
  60
  61         is_live = xpath_text(hd_doc, './/video/islive') == 'true'
  62         if is_live:
  63             raise ExtractorError(
  64                 'Live streams are not supported by the f4m downloader.')
  65
  66         categories = xpath_text(hd_doc, './/video/meta_sports')
  67         if categories:
  68             categories = categories.split(',')
  69
  70         ident = random.randint(10000000, 99999999)
  71         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
  72             flash_url, ident, flashvars['timestamp'], flashvars['auth'])
  73
  74         token_doc = self._download_xml(
  75             token_url, video_id, note='Downloading token')
  76         token_attrib = token_doc.find('.//token').attrib
  77         if token_attrib.get('auth') in ('blocked', 'restricted'):
  78             raise ExtractorError(
  79                 'Token error: %s' % token_attrib.get('comment'), expected=True)
  80
  81         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
  82             token_attrib['url'], token_attrib['auth'])
  83
  84         return {
  85             'id': video_id,
  86             'is_live': is_live,
  87             'title': title,
  88             'url': video_url,
  89             'uploader': uploader,
  90             'categories': categories,
  91             'ext': 'mp4',
  92         }