Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/laola1tv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     unified_strdate,
  10     urlencode_postdata,
  11     xpath_element,
  12     xpath_text,
  13     update_url_query,
  14     js_to_json,
  15 )
  16
  17
  18 class Laola1TvEmbedIE(InfoExtractor):
  19     IE_NAME = 'laola1tv:embed'
  20     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
  21     _TESTS = [{
  22         # flashvars.premium = "false";
  23         'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
  24         'info_dict': {
  25             'id': '708065',
  26             'ext': 'mp4',
  27             'title': 'MA Long CHN - FAN Zhendong CHN',
  28             'uploader': 'ITTF - International Table Tennis Federation',
  29             'upload_date': '20161211',
  30         },
  31     }]
  32
  33     def _extract_token_url(self, stream_access_url, video_id, data):
  34         return self._download_json(
  35             stream_access_url, video_id, headers={
  36                 'Content-Type': 'application/json',
  37             }, data=json.dumps(data).encode())['data']['stream-access'][0]
  38
  39     def _extract_formats(self, token_url, video_id):
  40         token_doc = self._download_xml(
  41             token_url, video_id, 'Downloading token',
  42             headers=self.geo_verification_headers())
  43
  44         token_attrib = xpath_element(token_doc, './/token').attrib
  45
  46         if token_attrib['status'] != '0':
  47             raise ExtractorError(
  48                 'Token error: %s' % token_attrib['comment'], expected=True)
  49
  50         formats = self._extract_akamai_formats(
  51             '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
  52             video_id)
  53         self._sort_formats(formats)
  54         return formats
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         webpage = self._download_webpage(url, video_id)
  59         flash_vars = self._search_regex(
  60             r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars')
  61
  62         def get_flashvar(x, *args, **kwargs):
  63             flash_var = self._search_regex(
  64                 r'%s\s*:\s*"([^"]+)"' % x,
  65                 flash_vars, x, default=None)
  66             if not flash_var:
  67                 flash_var = self._search_regex([
  68                     r'flashvars\.%s\s*=\s*"([^"]+)"' % x,
  69                     r'%s\s*=\s*"([^"]+)"' % x],
  70                     webpage, x, *args, **kwargs)
  71             return flash_var
  72
  73         hd_doc = self._download_xml(
  74             'http://www.laola1.tv/server/hd_video.php', video_id, query={
  75                 'play': get_flashvar('streamid'),
  76                 'partner': get_flashvar('partnerid'),
  77                 'portal': get_flashvar('portalid'),
  78                 'lang': get_flashvar('sprache'),
  79                 'v5ident': '',
  80             })
  81
  82         _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
  83         title = _v('title', fatal=True)
  84
  85         token_url = None
  86         premium = get_flashvar('premium', default=None)
  87         if premium:
  88             token_url = update_url_query(
  89                 _v('url', fatal=True), {
  90                     'timestamp': get_flashvar('timestamp'),
  91                     'auth': get_flashvar('auth'),
  92                 })
  93         else:
  94             data_abo = urlencode_postdata(
  95                 dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
  96             stream_access_url = update_url_query(
  97                 'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', {
  98                     'videoId': _v('id'),
  99                     'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
 100                     'label': _v('label'),
 101                     'area': _v('area'),
 102                 })
 103             token_url = self._extract_token_url(stream_access_url, video_id, data_abo)
 104
 105         formats = self._extract_formats(token_url, video_id)
 106
 107         categories_str = _v('meta_sports')
 108         categories = categories_str.split(',') if categories_str else []
 109         is_live = _v('islive') == 'true'
 110
 111         return {
 112             'id': video_id,
 113             'title': self._live_title(title) if is_live else title,
 114             'upload_date': unified_strdate(_v('time_date')),
 115             'uploader': _v('meta_organisation'),
 116             'categories': categories,
 117             'is_live': is_live,
 118             'formats': formats,
 119         }
 120
 121
 122 class Laola1TvIE(Laola1TvEmbedIE):
 123     IE_NAME = 'laola1tv'
 124     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
 125     _TESTS = [{
 126         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
 127         'info_dict': {
 128             'id': '227883',
 129             'display_id': 'straubing-tigers-koelner-haie',
 130             'ext': 'flv',
 131             'title': 'Straubing Tigers - Kölner Haie',
 132             'upload_date': '20140912',
 133             'is_live': False,
 134             'categories': ['Eishockey'],
 135         },
 136         'params': {
 137             'skip_download': True,
 138         },
 139     }, {
 140         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
 141         'info_dict': {
 142             'id': '464602',
 143             'display_id': 'straubing-tigers-koelner-haie',
 144             'ext': 'flv',
 145             'title': 'Straubing Tigers - Kölner Haie',
 146             'upload_date': '20160129',
 147             'is_live': False,
 148             'categories': ['Eishockey'],
 149         },
 150         'params': {
 151             'skip_download': True,
 152         },
 153     }, {
 154         'url': 'http://www.laola1.tv/de-de/livestream/2016-03-22-belogorie-belgorod-trentino-diatec-lde',
 155         'info_dict': {
 156             'id': '487850',
 157             'display_id': '2016-03-22-belogorie-belgorod-trentino-diatec-lde',
 158             'ext': 'flv',
 159             'title': 'Belogorie BELGOROD - TRENTINO Diatec',
 160             'upload_date': '20160322',
 161             'uploader': 'CEV - Europäischer Volleyball Verband',
 162             'is_live': True,
 163             'categories': ['Volleyball'],
 164         },
 165         'params': {
 166             'skip_download': True,
 167         },
 168         'skip': 'This live stream has already finished.',
 169     }]
 170
 171     def _real_extract(self, url):
 172         display_id = self._match_id(url)
 173
 174         webpage = self._download_webpage(url, display_id)
 175
 176         if 'Dieser Livestream ist bereits beendet.' in webpage:
 177             raise ExtractorError('This live stream has already finished.', expected=True)
 178
 179         conf = self._parse_json(self._search_regex(
 180             r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
 181             display_id, js_to_json)
 182
 183         video_id = conf['videoid']
 184
 185         config = self._download_json(conf['configUrl'], video_id, query={
 186             'videoid': video_id,
 187             'partnerid': conf['partnerid'],
 188             'language': conf.get('language', ''),
 189             'portal': conf.get('portalid', ''),
 190         })
 191         error = config.get('error')
 192         if error:
 193             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 194
 195         video_data = config['video']
 196         title = video_data['title']
 197         is_live = video_data.get('isLivestream') and video_data.get('isLive')
 198         meta = video_data.get('metaInformation')
 199         sports = meta.get('sports')
 200         categories = sports.split(',') if sports else []
 201
 202         token_url = self._extract_token_url(
 203             video_data['streamAccess'], video_id,
 204             video_data['abo']['required'])
 205
 206         formats = self._extract_formats(token_url, video_id)
 207
 208         return {
 209             'id': video_id,
 210             'display_id': display_id,
 211             'title': self._live_title(title) if is_live else title,
 212             'description': video_data.get('description'),
 213             'thumbnail': video_data.get('image'),
 214             'categories': categories,
 215             'formats': formats,
 216             'is_live': is_live,
 217         }