From 5a3e2d571d8d9676eb337af7c6a7683981ee77e5 Mon Sep 17 00:00:00 2001 From: mrx23dot Date: Sat, 2 May 2020 14:18:23 +0100 Subject: [PATCH] [mediaklikk] initial --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/mediaklikk.py | 57 ++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 youtube_dl/extractor/mediaklikk.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 995af9988..0c9fcec0a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -607,6 +607,7 @@ from .markiza import ( from .massengeschmacktv import MassengeschmackTVIE from .matchtv import MatchTVIE from .mdr import MDRIE +from .mediaklikk import MediaKlikkIE from .mediaset import MediasetIE from .mediasite import MediasiteIE from .medici import MediciIE diff --git a/youtube_dl/extractor/mediaklikk.py b/youtube_dl/extractor/mediaklikk.py new file mode 100644 index 000000000..b049c7259 --- /dev/null +++ b/youtube_dl/extractor/mediaklikk.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_unquote, + compat_str +) + + +class MediaKlikkIE(InfoExtractor): + # (?P...) used for referencing match as 'id' + _VALID_URL = r'https?://(?:www\.)?mediaklikk\.hu/video/(?P:[^/]+)/?' + _TEST = { + 'url': 'https://mediaklikk.hu/video/kiberma-2020-04-30-i-adas/', + 'info_dict': { + 'id': '2512015', + 'ext': 'mp4', + 'title': 'KiberMa, 2020.04.30-i adás | MédiaKlikk', + # no thumbnail extractable + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + display_id = video_id + webpage = self._download_webpage(url, video_id) + + pattern = r"mtva_player_manager\.player\(document.getElementById\(.*\),\s?(\{.*\}).*\);" + info_json = self._html_search_regex(pattern, webpage, 'info_json') + info_meta = self._parse_json(compat_urllib_parse_unquote(info_json),None) + + info_ret = { + '_type': 'video', + 'title': info_meta.get('title') or self._og_search_title(webpage), + 'ext': 'mp4', + 'display_id': display_id, + 'id': video_id + } + + if 'series' in info_meta: + info_ret['series'] = info_meta['series'] + info_meta['video'] = info_meta['token'] + del info_meta['token'] + playerpage = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', + video_id, + query=info_meta) + pattern = r"\"file\": \"(\\/\\/.*playlist\.m3u8)\"," + playlist_url = 'https:' + compat_urllib_parse_unquote( + self._html_search_regex(pattern, playerpage, 'playlist_url'))\ + .replace('\\/', '/') + formats = self._extract_wowza_formats( + playlist_url, video_id, skip_protocols=['f4m', 'smil', 'dash']) + self._sort_formats(formats) + info_ret['formats'] = formats + + return info_ret