From df58ecbeba72e03b241c28e7c4760ef9b215c402 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 21 Jan 2018 17:40:00 +0700 Subject: [PATCH] [rtvs] Add extractor (closes #9242, closes #15187) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/rtvs.py | 47 ++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 youtube_dl/extractor/rtvs.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f5bac6fd9..541f73e3c 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -900,6 +900,7 @@ from .rtp import RTPIE from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtvnh import RTVNHIE +from .rtvs import RTVSIE from .rudo import RudoIE from .ruhd import RUHDIE from .ruleporn import RulePornIE diff --git a/youtube_dl/extractor/rtvs.py b/youtube_dl/extractor/rtvs.py new file mode 100644 index 000000000..6573b260d --- /dev/null +++ b/youtube_dl/extractor/rtvs.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class RTVSIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P\d+)' + _TESTS = [{ + # radio archive + 'url': 'http://www.rtvs.sk/radio/archiv/11224/414872', + 'md5': '134d5d6debdeddf8a5d761cbc9edacb8', + 'info_dict': { + 'id': '414872', + 'ext': 'mp3', + 'title': 'Ostrov pokladov 1 časť.mp3' + }, + 'params': { + 'skip_download': True, + } + }, { + # tv archive + 'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118', + 'md5': '85e2c55cf988403b70cac24f5c086dc6', + 'info_dict': { + 'id': '63118', + 'ext': 'mp4', + 'title': 'Amaro Džives - Náš deň', + 'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.' + }, + 'params': { + 'skip_download': True, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + playlist_url = self._search_regex( + r'playlist["\']?\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'playlist url', group='url') + + data = self._download_json( + playlist_url, video_id, 'Downloading playlist')[0] + return self._parse_jwplayer_data(data, video_id=video_id)