From 78e762d23c48f85c61a8afcae29307912000a7dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mat=C4=9Bj=20Cepl?= Date: Thu, 1 Sep 2016 17:31:08 +0200 Subject: [PATCH] Add new extractor for TV Noe (Czech Christian TV). Fixes #10520 --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tvnoe.py | 44 ++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 youtube_dl/extractor/tvnoe.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8c6ee0503..e47adc26c 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -916,6 +916,7 @@ from .tvc import ( ) from .tvigle import TvigleIE from .tvland import TVLandIE +from .tvnoe import TVNoeIE from .tvp import ( TVPEmbedIE, TVPIE, diff --git a/youtube_dl/extractor/tvnoe.py b/youtube_dl/extractor/tvnoe.py new file mode 100644 index 000000000..d50261ddd --- /dev/null +++ b/youtube_dl/extractor/tvnoe.py @@ -0,0 +1,44 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .jwplatform import JWPlatformBaseIE +from ..utils import clean_html, get_element_by_class, js_to_json + + +class TVNoeIE(JWPlatformBaseIE): + _VALID_URL = r'https?://(www\.)?tvnoe\.cz/video/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.tvnoe.cz/video/10362', + 'md5': 'aee983f279aab96ec45ab6e2abb3c2ca', + 'info_dict': { + 'id': '10362', + 'ext': 'mp4', + 'series': 'Noční univerzita', + 'title': 'prof. Tomáš Halík, Th.D. - ' + + 'Návrat náboženství a střet civilizací', + 'description': 'md5:f337bae384e1a531a52c55ebc50fff41', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + iframe_url = self._search_regex(r']+src="([^"]+)"', + webpage, 'iframe src attribute') + + ifs_page = self._download_webpage(iframe_url, video_id) + jwplayer_data = self._parse_json(self._find_jwplayer_data(ifs_page), + video_id, transform_source=js_to_json) + info_dict = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=iframe_url) + + info_dict.update({ + 'id': video_id, + 'title': clean_html( + get_element_by_class('field-name-field-podnazev', webpage)), + 'description': clean_html(get_element_by_class('field-name-body', + webpage)), + 'series': clean_html(get_element_by_class('title', webpage)) + }) + return info_dict