youtube_dl/extractor/puls4.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .prosiebensat1 import ProSiebenSat1BaseIE
   5 from ..utils import (
   6     unified_strdate,
   7     parse_duration,
   8     compat_str,
   9 )
  10
  11
  12 class Puls4IE(ProSiebenSat1BaseIE):
  13     _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
  14     _TESTS = [{
  15         'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
  16         'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
  17         'info_dict': {
  18             'id': '118118',
  19             'ext': 'flv',
  20             'title': 'Tobias Homberger von myclubs im #2min2miotalk',
  21             'description': 'md5:f9def7c5e8745d6026d8885487d91955',
  22             'upload_date': '20160830',
  23             'uploader': 'PULS_4',
  24         },
  25     }, {
  26         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
  27         'only_matching': True,
  28     }, {
  29         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
  30         'only_matching': True,
  31     }]
  32     _TOKEN = 'puls4'
  33     _SALT = '01!kaNgaiNgah1Ie4AeSha'
  34     _CLIENT_NAME = ''
  35
  36     def _real_extract(self, url):
  37         path = self._match_id(url)
  38         content_path = self._download_json(
  39             'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
  40         media = self._download_json(
  41             'http://www.puls4.com' + content_path,
  42             content_path)['mediaCurrent']
  43         player_content = media['playerContent']
  44         info = self._extract_video_info(url, player_content['id'])
  45         info.update({
  46             'id': compat_str(media['objectId']),
  47             'title': player_content['title'],
  48             'description': media.get('description'),
  49             'thumbnail': media.get('previewLink'),
  50             'upload_date': unified_strdate(media.get('date')),
  51             'duration': parse_duration(player_content.get('duration')),
  52             'episode': player_content.get('episodePartName'),
  53             'show': media.get('channel'),
  54             'season_id': player_content.get('seasonId'),
  55             'uploader': player_content.get('sourceCompany'),
  56         })
  57         return info