yt_dlp/extractor/laola1tv.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     unified_strdate,
   8     urlencode_postdata,
   9     xpath_element,
  10     xpath_text,
  11     update_url_query,
  12     js_to_json,
  13 )
  14
  15
  16 class Laola1TvEmbedIE(InfoExtractor):
  17     IE_NAME = 'laola1tv:embed'
  18     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
  19     _TESTS = [{
  20         # flashvars.premium = "false";
  21         'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
  22         'info_dict': {
  23             'id': '708065',
  24             'ext': 'mp4',
  25             'title': 'MA Long CHN - FAN Zhendong CHN',
  26             'uploader': 'ITTF - International Table Tennis Federation',
  27             'upload_date': '20161211',
  28         },
  29     }]
  30
  31     def _extract_token_url(self, stream_access_url, video_id, data):
  32         return self._download_json(
  33             self._proto_relative_url(stream_access_url, 'https:'), video_id,
  34             headers={
  35                 'Content-Type': 'application/json',
  36             }, data=json.dumps(data).encode())['data']['stream-access'][0]
  37
  38     def _extract_formats(self, token_url, video_id):
  39         token_doc = self._download_xml(
  40             token_url, video_id, 'Downloading token',
  41             headers=self.geo_verification_headers())
  42
  43         token_attrib = xpath_element(token_doc, './/token').attrib
  44
  45         if token_attrib['status'] != '0':
  46             raise ExtractorError(
  47                 'Token error: %s' % token_attrib['comment'], expected=True)
  48
  49         formats = self._extract_akamai_formats(
  50             '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
  51             video_id)
  52         return formats
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56         webpage = self._download_webpage(url, video_id)
  57         flash_vars = self._search_regex(
  58             r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars')
  59
  60         def get_flashvar(x, *args, **kwargs):
  61             flash_var = self._search_regex(
  62                 r'%s\s*:\s*"([^"]+)"' % x,
  63                 flash_vars, x, default=None)
  64             if not flash_var:
  65                 flash_var = self._search_regex([
  66                     r'flashvars\.%s\s*=\s*"([^"]+)"' % x,
  67                     r'%s\s*=\s*"([^"]+)"' % x],
  68                     webpage, x, *args, **kwargs)
  69             return flash_var
  70
  71         hd_doc = self._download_xml(
  72             'http://www.laola1.tv/server/hd_video.php', video_id, query={
  73                 'play': get_flashvar('streamid'),
  74                 'partner': get_flashvar('partnerid'),
  75                 'portal': get_flashvar('portalid'),
  76                 'lang': get_flashvar('sprache'),
  77                 'v5ident': '',
  78             })
  79
  80         _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
  81         title = _v('title', fatal=True)
  82
  83         token_url = None
  84         premium = get_flashvar('premium', default=None)
  85         if premium:
  86             token_url = update_url_query(
  87                 _v('url', fatal=True), {
  88                     'timestamp': get_flashvar('timestamp'),
  89                     'auth': get_flashvar('auth'),
  90                 })
  91         else:
  92             data_abo = urlencode_postdata(
  93                 dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
  94             stream_access_url = update_url_query(
  95                 'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', {
  96                     'videoId': _v('id'),
  97                     'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
  98                     'label': _v('label'),
  99                     'area': _v('area'),
 100                 })
 101             token_url = self._extract_token_url(stream_access_url, video_id, data_abo)
 102
 103         formats = self._extract_formats(token_url, video_id)
 104
 105         categories_str = _v('meta_sports')
 106         categories = categories_str.split(',') if categories_str else []
 107         is_live = _v('islive') == 'true'
 108
 109         return {
 110             'id': video_id,
 111             'title': title,
 112             'upload_date': unified_strdate(_v('time_date')),
 113             'uploader': _v('meta_organisation'),
 114             'categories': categories,
 115             'is_live': is_live,
 116             'formats': formats,
 117         }
 118
 119
 120 class Laola1TvBaseIE(Laola1TvEmbedIE):  # XXX: Do not subclass from concrete IE
 121     def _extract_video(self, url):
 122         display_id = self._match_id(url)
 123         webpage = self._download_webpage(url, display_id)
 124
 125         if 'Dieser Livestream ist bereits beendet.' in webpage:
 126             raise ExtractorError('This live stream has already finished.', expected=True)
 127
 128         conf = self._parse_json(self._search_regex(
 129             r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
 130             display_id,
 131             transform_source=lambda s: js_to_json(re.sub(r'shareurl:.+,', '', s)))
 132         video_id = conf['videoid']
 133
 134         config = self._download_json(conf['configUrl'], video_id, query={
 135             'videoid': video_id,
 136             'partnerid': conf['partnerid'],
 137             'language': conf.get('language', ''),
 138             'portal': conf.get('portalid', ''),
 139         })
 140         error = config.get('error')
 141         if error:
 142             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 143
 144         video_data = config['video']
 145         title = video_data['title']
 146         is_live = video_data.get('isLivestream') and video_data.get('isLive')
 147         meta = video_data.get('metaInformation')
 148         sports = meta.get('sports')
 149         categories = sports.split(',') if sports else []
 150
 151         token_url = self._extract_token_url(
 152             video_data['streamAccess'], video_id,
 153             video_data['abo']['required'])
 154
 155         formats = self._extract_formats(token_url, video_id)
 156
 157         return {
 158             'id': video_id,
 159             'display_id': display_id,
 160             'title': title,
 161             'description': video_data.get('description'),
 162             'thumbnail': video_data.get('image'),
 163             'categories': categories,
 164             'formats': formats,
 165             'is_live': is_live,
 166         }
 167
 168
 169 class Laola1TvIE(Laola1TvBaseIE):
 170     IE_NAME = 'laola1tv'
 171     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
 172
 173     _TESTS = [{
 174         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
 175         'info_dict': {
 176             'id': '227883',
 177             'display_id': 'straubing-tigers-koelner-haie',
 178             'ext': 'flv',
 179             'title': 'Straubing Tigers - Kölner Haie',
 180             'upload_date': '20140912',
 181             'is_live': False,
 182             'categories': ['Eishockey'],
 183         },
 184         'params': {
 185             'skip_download': True,
 186         },
 187     }, {
 188         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
 189         'info_dict': {
 190             'id': '464602',
 191             'display_id': 'straubing-tigers-koelner-haie',
 192             'ext': 'flv',
 193             'title': 'Straubing Tigers - Kölner Haie',
 194             'upload_date': '20160129',
 195             'is_live': False,
 196             'categories': ['Eishockey'],
 197         },
 198         'params': {
 199             'skip_download': True,
 200         },
 201     }, {
 202         'url': 'http://www.laola1.tv/de-de/livestream/2016-03-22-belogorie-belgorod-trentino-diatec-lde',
 203         'info_dict': {
 204             'id': '487850',
 205             'display_id': '2016-03-22-belogorie-belgorod-trentino-diatec-lde',
 206             'ext': 'flv',
 207             'title': 'Belogorie BELGOROD - TRENTINO Diatec',
 208             'upload_date': '20160322',
 209             'uploader': 'CEV - Europäischer Volleyball Verband',
 210             'is_live': True,
 211             'categories': ['Volleyball'],
 212         },
 213         'params': {
 214             'skip_download': True,
 215         },
 216         'skip': 'This live stream has already finished.',
 217     }]
 218
 219     def _real_extract(self, url):
 220         return self._extract_video(url)
 221
 222
 223 class EHFTVIE(Laola1TvBaseIE):
 224     IE_NAME = 'ehftv'
 225     _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(?:-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)'
 226
 227     _TESTS = [{
 228         'url': 'https://www.ehftv.com/int/video/paris-saint-germain-handball-pge-vive-kielce/1166761',
 229         'info_dict': {
 230             'id': '1166761',
 231             'display_id': 'paris-saint-germain-handball-pge-vive-kielce',
 232             'ext': 'mp4',
 233             'title': 'Paris Saint-Germain Handball - PGE Vive Kielce',
 234             'is_live': False,
 235             'categories': ['Handball'],
 236         },
 237         'params': {
 238             'skip_download': True,
 239         },
 240     }]
 241
 242     def _real_extract(self, url):
 243         return self._extract_video(url)
 244
 245
 246 class ITTFIE(InfoExtractor):
 247     _VALID_URL = r'https?://tv\.ittf\.com/video/[^/]+/(?P<id>\d+)'
 248     _TEST = {
 249         'url': 'https://tv.ittf.com/video/peng-wang-wei-matsudaira-kenta/951802',
 250         'only_matching': True,
 251     }
 252
 253     def _real_extract(self, url):
 254         return self.url_result(
 255             update_url_query('https://www.laola1.tv/titanplayer.php', {
 256                 'videoid': self._match_id(url),
 257                 'type': 'V',
 258                 'lang': 'en',
 259                 'portal': 'int',
 260                 'customer': 1024,
 261             }), Laola1TvEmbedIE.ie_key())