Raphaël G. Git Repositories - youtubedl/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     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         lang = mobj.group('lang')
  34         portal = mobj.group('portal')
  35
  36         webpage = self._download_webpage(url, video_id)
  37         iframe_url = self._search_regex(
  38             r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
  39             webpage, 'iframe URL')
  40
  41         iframe = self._download_webpage(
  42             iframe_url, video_id, note='Downloading iframe')
  43         flashvars_m = re.findall(
  44             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
  45         flashvars = dict((m[0], m[1]) for m in flashvars_m)
  46
  47         partner_id = self._search_regex(
  48             r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id')
  49
  50         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
  51                    'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % (
  52                        video_id, partner_id, portal, lang))
  53         hd_doc = self._download_xml(xml_url, video_id)
  54
  55         title = xpath_text(hd_doc, './/video/title', fatal=True)
  56         flash_url = xpath_text(hd_doc, './/video/url', fatal=True)
  57         uploader = xpath_text(hd_doc, './/video/meta_organistation')
  58         is_live = xpath_text(hd_doc, './/video/islive') == 'true'
  59
  60         categories = xpath_text(hd_doc, './/video/meta_sports')
  61         if categories:
  62             categories = categories.split(',')
  63
  64         ident = random.randint(10000000, 99999999)
  65         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
  66             flash_url, ident, flashvars['timestamp'], flashvars['auth'])
  67
  68         token_doc = self._download_xml(
  69             token_url, video_id, note='Downloading token')
  70         token_attrib = token_doc.find('.//token').attrib
  71         if token_attrib.get('auth') in ('blocked', 'restricted'):
  72             raise ExtractorError(
  73                 'Token error: %s' % token_attrib.get('comment'), expected=True)
  74
  75         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
  76             token_attrib['url'], token_attrib['auth'])
  77
  78         return {
  79             'id': video_id,
  80             'is_live': is_live,
  81             'title': title,
  82             'url': video_url,
  83             'uploader': uploader,
  84             'categories': categories,
  85             'ext': 'mp4',
  86         }