yt_dlp/extractor/parliamentliveuk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import uuid
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     unified_timestamp,
  10     try_get,
  11 )
  12
  13
  14 class ParliamentLiveUKIE(InfoExtractor):
  15     IE_NAME = 'parliamentlive.tv'
  16     IE_DESC = 'UK parliament videos'
  17     _VALID_URL = r'(?i)https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  18
  19     _TESTS = [{
  20         'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
  21         'info_dict': {
  22             'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
  23             'ext': 'mp4',
  24             'title': 'Home Affairs Committee',
  25             'timestamp': 1395153872,
  26             'upload_date': '20140318',
  27         },
  28         'params': {
  29             'format': 'bestvideo',
  30         },
  31     }, {
  32         'url': 'http://parliamentlive.tv/event/index/3f24936f-130f-40bf-9a5d-b3d6479da6a4',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         video_info = self._download_json(f'https://www.parliamentlive.tv/Event/GetShareVideo/{video_id}', video_id)
  39         _DEVICE_ID = str(uuid.uuid4())
  40         auth = 'Bearer ' + self._download_json(
  41             'https://exposure.api.redbee.live/v2/customer/UKParliament/businessunit/ParliamentLive/auth/anonymous',
  42             video_id, headers={
  43                 'Origin': 'https://videoplayback.parliamentlive.tv',
  44                 'Accept': 'application/json, text/plain, */*',
  45                 'Content-Type': 'application/json;charset=utf-8'
  46             }, data=json.dumps({
  47                 'deviceId': _DEVICE_ID,
  48                 'device': {
  49                     'deviceId': _DEVICE_ID,
  50                     'width': 653,
  51                     'height': 368,
  52                     'type': 'WEB',
  53                     'name': ' Mozilla Firefox 91'
  54                 }
  55             }).encode('utf-8'))['sessionToken']
  56
  57         video_urls = self._download_json(
  58             f'https://exposure.api.redbee.live/v2/customer/UKParliament/businessunit/ParliamentLive/entitlement/{video_id}/play',
  59             video_id, headers={'Authorization': auth, 'Accept': 'application/json, text/plain, */*'})['formats']
  60
  61         formats = []
  62         for format in video_urls:
  63             if not format.get('mediaLocator'):
  64                 continue
  65             if format.get('format') == 'DASH':
  66                 formats.extend(self._extract_mpd_formats(
  67                     format['mediaLocator'], video_id, mpd_id='dash', fatal=False))
  68             elif format.get('format') == 'SMOOTHSTREAMING':
  69                 formats.extend(self._extract_ism_formats(
  70                     format['mediaLocator'], video_id, ism_id='ism', fatal=False))
  71             elif format.get('format') == 'HLS':
  72                 formats.extend(self._extract_m3u8_formats(
  73                     format['mediaLocator'], video_id, m3u8_id='hls', fatal=False))
  74
  75         self._sort_formats(formats)
  76
  77         return {
  78             'id': video_id,
  79             'formats': formats,
  80             'title': video_info['event']['title'],
  81             'timestamp': unified_timestamp(try_get(video_info, lambda x: x['event']['publishedStartTime'])),
  82             'thumbnail': video_info.get('thumbnailUrl'),
  83         }