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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     ExtractorError,
  10     unified_timestamp,
  11 )
  12
  13
  14 class TennisTVIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?tennistv\.com/videos/(?P<id>[-a-z0-9]+)'
  16     _TEST = {
  17         'url': 'https://www.tennistv.com/videos/indian-wells-2018-verdasco-fritz',
  18         'info_dict': {
  19             'id': 'indian-wells-2018-verdasco-fritz',
  20             'ext': 'mp4',
  21             'title': 'Fernando Verdasco v Taylor Fritz',
  22             'description': 're:^After his stunning victory.{174}$',
  23             'thumbnail': 'https://atp-prod.akamaized.net/api/images/v1/images/112831/landscape/1242/0',
  24             'timestamp': 1521017381,
  25             'upload_date': '20180314',
  26         },
  27         'params': {
  28             'skip_download': True,
  29         },
  30         'skip': 'Requires email and password of a subscribed account',
  31     }
  32     _NETRC_MACHINE = 'tennistv'
  33
  34     def _login(self):
  35         username, password = self._get_login_info()
  36         if not username or not password:
  37             raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  38
  39         login_form = {
  40             'Email': username,
  41             'Password': password,
  42         }
  43         login_json = json.dumps(login_form).encode('utf-8')
  44         headers = {
  45             'content-type': 'application/json',
  46             'Referer': 'https://www.tennistv.com/login',
  47             'Origin': 'https://www.tennistv.com',
  48         }
  49
  50         login_result = self._download_json(
  51             'https://www.tennistv.com/api/users/v1/login', None,
  52             note='Logging in',
  53             errnote='Login failed (wrong password?)',
  54             headers=headers,
  55             data=login_json)
  56
  57         if login_result['error']['errorCode']:
  58             raise ExtractorError('Login failed, %s said: %r' % (self.IE_NAME, login_result['error']['errorMessage']))
  59
  60         if login_result['entitlement'] != 'SUBSCRIBED':
  61             self.report_warning('%s may not be subscribed to %s.' % (username, self.IE_NAME))
  62
  63         self._session_token = login_result['sessionToken']
  64
  65     def _real_initialize(self):
  66         self._login()
  67
  68     def _real_extract(self, url):
  69         video_id = self._match_id(url)
  70         webpage = self._download_webpage(url, video_id)
  71
  72         internal_id = self._search_regex(r'video=([0-9]+)', webpage, 'internal video id')
  73
  74         headers = {
  75             'Origin': 'https://www.tennistv.com',
  76             'authorization': 'ATP %s' % self._session_token,
  77             'content-type': 'application/json',
  78             'Referer': url,
  79         }
  80         check_data = {
  81             'videoID': internal_id,
  82             'VideoUrlType': 'HLSV3',
  83         }
  84         check_json = json.dumps(check_data).encode('utf-8')
  85         check_result = self._download_json(
  86             'https://www.tennistv.com/api/users/v1/entitlementchecknondiva',
  87             video_id, note='Checking video authorization', headers=headers, data=check_json)
  88         formats = self._extract_m3u8_formats(check_result['contentUrl'], video_id, ext='mp4')
  89
  90         vdata_url = 'https://www.tennistv.com/api/channels/v1/de/none/video/%s' % video_id
  91         vdata = self._download_json(vdata_url, video_id)
  92
  93         timestamp = unified_timestamp(vdata['timestamp'])
  94         thumbnail = vdata['video']['thumbnailUrl']
  95         description = vdata['displayText']['description']
  96         title = vdata['video']['title']
  97
  98         series = vdata['tour']
  99         venue = vdata['displayText']['venue']
 100         round_str = vdata['seo']['round']
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'description': description,
 106             'formats': formats,
 107             'thumbnail': thumbnail,
 108             'timestamp': timestamp,
 109             'series': series,
 110             'season': venue,
 111             'episode': round_str,
 112         }