yt_dlp/extractor/mediaklikk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from ..utils import (
   5     unified_strdate
   6 )
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse_unquote,
  10     compat_str
  11 )
  12
  13
  14 class MediaKlikkIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)^https?:\/\/(?:www\.)?
  16                         (?:mediaklikk|m4sport|hirado|petofilive)\.hu\/.*?videok?\/
  17                         (?:(?P<year>[0-9]{4})/(?P<month>[0-9]{1,2})/(?P<day>[0-9]{1,2})/)?
  18                         (?P<id>[^/#?_]+)'''
  19
  20     _TESTS = [{
  21         # mediaklikk. date in html.
  22         'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/',
  23         'info_dict': {
  24             'id': '4754129',
  25             'title': 'Hazajáró, DÉLNYUGAT-BÁCSKA – A Duna mentén Palánkától Doroszlóig',
  26             'ext': 'mp4',
  27             'upload_date': '20210901',
  28             'thumbnail': 'http://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg'
  29         }
  30     }, {
  31         # m4sport
  32         'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/',
  33         'info_dict': {
  34             'id': '4754999',
  35             'title': 'Gyémánt Liga, Párizs',
  36             'ext': 'mp4',
  37             'upload_date': '20210830',
  38             'thumbnail': 'http://m4sport.hu/wp-content/uploads/sites/4/2021/08/vlcsnap-2021-08-30-18h21m20s10-1024x576.jpg'
  39         }
  40     }, {
  41         # m4sport with *video/ url and no date
  42         'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/',
  43         'info_dict': {
  44             'id': '4492099',
  45             'title': 'Real Madrid - Chelsea 1-1',
  46             'ext': 'mp4',
  47             'thumbnail': 'http://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png'
  48         }
  49     }, {
  50         # hirado
  51         'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/',
  52         'info_dict': {
  53             'id': '4760120',
  54             'title': 'Feltételeket szabott a főváros',
  55             'ext': 'mp4',
  56             'thumbnail': 'http://hirado.hu/wp-content/uploads/sites/4/2021/09/vlcsnap-2021-09-01-20h20m37s165.jpg'
  57         }
  58     }, {
  59         # petofilive
  60         'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/',
  61         'info_dict': {
  62             'id': '4571948',
  63             'title': 'Tha Shudras az Akusztikban',
  64             'ext': 'mp4',
  65             'upload_date': '20210607',
  66             'thumbnail': 'http://petofilive.hu/wp-content/uploads/sites/4/2021/06/vlcsnap-2021-06-07-22h14m23s915-1024x576.jpg'
  67         }
  68     }]
  69
  70     def _real_extract(self, url):
  71         mobj = self._match_valid_url(url)
  72         display_id = mobj.group('id')
  73         webpage = self._download_webpage(url, display_id)
  74
  75         player_data_str = self._html_search_regex(
  76             r'mtva_player_manager\.player\(document.getElementById\(.*\),\s?(\{.*\}).*\);', webpage, 'player data')
  77         player_data = self._parse_json(player_data_str, display_id, compat_urllib_parse_unquote)
  78         video_id = compat_str(player_data['contentId'])
  79         title = player_data.get('title') or self._og_search_title(webpage, fatal=False) or \
  80             self._html_search_regex(r'<h\d+\b[^>]+\bclass="article_title">([^<]+)<', webpage, 'title')
  81
  82         upload_date = unified_strdate(
  83             '%s-%s-%s' % (mobj.group('year'), mobj.group('month'), mobj.group('day')))
  84         if not upload_date:
  85             upload_date = unified_strdate(self._html_search_regex(
  86                 r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
  87
  88         player_data['video'] = player_data.pop('token')
  89         player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data)
  90         playlist_url = self._proto_relative_url(compat_urllib_parse_unquote(
  91             self._html_search_regex(r'\"file\":\s*\"(\\?/\\?/.*playlist\.m3u8)\"', player_page, 'playlist_url')).replace('\\/', '/'))
  92
  93         formats = self._extract_wowza_formats(
  94             playlist_url, video_id, skip_protocols=['f4m', 'smil', 'dash'])
  95         self._sort_formats(formats)
  96
  97         return {
  98             'id': video_id,
  99             'title': title,
 100             'display_id': display_id,
 101             'formats': formats,
 102             'upload_date': upload_date,
 103             'thumbnail': player_data.get('bgImage') or self._og_search_thumbnail(webpage)
 104         }