yt_dlp/extractor/puls4.py

   1 from .prosiebensat1 import ProSiebenSat1BaseIE
   2 from ..compat import compat_str
   3 from ..utils import parse_duration, unified_strdate
   4
   5
   6 class Puls4IE(ProSiebenSat1BaseIE):
   7     _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
   8     _TESTS = [{
   9         'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
  10         'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
  11         'info_dict': {
  12             'id': '118118',
  13             'ext': 'flv',
  14             'title': 'Tobias Homberger von myclubs im #2min2miotalk',
  15             'description': 'md5:f9def7c5e8745d6026d8885487d91955',
  16             'upload_date': '20160830',
  17             'uploader': 'PULS_4',
  18         },
  19     }, {
  20         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
  21         'only_matching': True,
  22     }, {
  23         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
  24         'only_matching': True,
  25     }]
  26     _TOKEN = 'puls4'
  27     _SALT = '01!kaNgaiNgah1Ie4AeSha'
  28     _CLIENT_NAME = ''
  29
  30     def _real_extract(self, url):
  31         path = self._match_id(url)
  32         content_path = self._download_json(
  33             'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
  34         media = self._download_json(
  35             'http://www.puls4.com' + content_path,
  36             content_path)['mediaCurrent']
  37         player_content = media['playerContent']
  38         info = self._extract_video_info(url, player_content['id'])
  39         info.update({
  40             'id': compat_str(media['objectId']),
  41             'title': player_content['title'],
  42             'description': media.get('description'),
  43             'thumbnail': media.get('previewLink'),
  44             'upload_date': unified_strdate(media.get('date')),
  45             'duration': parse_duration(player_content.get('duration')),
  46             'episode': player_content.get('episodePartName'),
  47             'show': media.get('channel'),
  48             'season_id': player_content.get('seasonId'),
  49             'uploader': player_content.get('sourceCompany'),
  50         })
  51         return info