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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     sanitized_Request,
  14     unified_strdate,
  15     urlencode_postdata,
  16     xpath_element,
  17     xpath_text,
  18 )
  19
  20
  21 class Laola1TvIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/[^/]+/(?P<slug>[^/?#&]+)'
  23     _TESTS = [{
  24         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
  25         'info_dict': {
  26             'id': '227883',
  27             'display_id': 'straubing-tigers-koelner-haie',
  28             'ext': 'flv',
  29             'title': 'Straubing Tigers - Kölner Haie',
  30             'upload_date': '20140912',
  31             'is_live': False,
  32             'categories': ['Eishockey'],
  33         },
  34         'params': {
  35             'skip_download': True,
  36         }
  37     }, {
  38         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
  39         'info_dict': {
  40             'id': '464602',
  41             'display_id': 'straubing-tigers-koelner-haie',
  42             'ext': 'flv',
  43             'title': 'Straubing Tigers - Kölner Haie',
  44             'upload_date': '20160129',
  45             'is_live': False,
  46             'categories': ['Eishockey'],
  47         },
  48         'params': {
  49             'skip_download': True,
  50         }
  51     }]
  52
  53     def _real_extract(self, url):
  54         mobj = re.match(self._VALID_URL, url)
  55         display_id = mobj.group('slug')
  56         lang = mobj.group('lang')
  57         portal = mobj.group('portal')
  58
  59         webpage = self._download_webpage(url, display_id)
  60
  61         iframe_url = self._search_regex(
  62             r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
  63             webpage, 'iframe url')
  64
  65         video_id = self._search_regex(
  66             r'videoid=(\d+)', iframe_url, 'video id')
  67
  68         iframe = self._download_webpage(compat_urlparse.urljoin(
  69             url, iframe_url), display_id, 'Downloading iframe')
  70
  71         partner_id = self._search_regex(
  72             r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
  73             iframe, 'partner id', group='partner_id')
  74
  75         hd_doc = self._download_xml(
  76             'http://www.laola1.tv/server/hd_video.php?%s'
  77             % compat_urllib_parse.urlencode({
  78                 'play': video_id,
  79                 'partner': partner_id,
  80                 'portal': portal,
  81                 'lang': lang,
  82                 'v5ident': '',
  83             }), display_id)
  84
  85         _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
  86         title = _v('title', fatal=True)
  87
  88         req = sanitized_Request(
  89             'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
  90             compat_urllib_parse.urlencode({
  91                 'videoId': video_id,
  92                 'target': '2',
  93                 'label': 'laola1tv',
  94                 'area': _v('area'),
  95             }),
  96             urlencode_postdata(
  97                 dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
  98
  99         token_url = self._download_json(req, display_id)['data']['stream-access'][0]
 100         token_doc = self._download_xml(token_url, display_id, 'Downloading token')
 101
 102         token_attrib = xpath_element(token_doc, './/token').attrib
 103         token_auth = token_attrib['auth']
 104
 105         if token_auth in ('blocked', 'restricted', 'error'):
 106             raise ExtractorError(
 107                 'Token error: %s' % token_attrib['comment'], expected=True)
 108
 109         formats = self._extract_f4m_formats(
 110             '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
 111             video_id, f4m_id='hds')
 112
 113         categories_str = _v('meta_sports')
 114         categories = categories_str.split(',') if categories_str else []
 115
 116         return {
 117             'id': video_id,
 118             'display_id': display_id,
 119             'title': title,
 120             'upload_date': unified_strdate(_v('time_date')),
 121             'uploader': _v('meta_organisation'),
 122             'categories': categories,
 123             'is_live': _v('islive') == 'true',
 124             'formats': formats,
 125         }