From 02d9b82a233abcb778f3f8601b229f996fd7df94 Mon Sep 17 00:00:00 2001 From: Jakub Wilk Date: Wed, 11 Jan 2017 18:49:40 +0100 Subject: [PATCH] [tvn24] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tvn24.py | 47 ++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 youtube_dl/extractor/tvn24.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index be3688d5a6..55b4782d38 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1009,6 +1009,7 @@ ) from .tvigle import TvigleIE from .tvland import TVLandIE +from .tvn24 import TVN24IE from .tvnoe import TVNoeIE from .tvp import ( TVPEmbedIE, diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py new file mode 100644 index 0000000000..225ee4a6a7 --- /dev/null +++ b/youtube_dl/extractor/tvn24.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TVN24IE(InfoExtractor): + _VALID_URL = r'http://(?:tvn24bis|(?:www|fakty)\.tvn24)\.pl/.+/(?P[^/]+)\.html' + _TEST = { + 'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html', + 'md5': 'fbdec753d7bc29d96036808275f2130c', + 'info_dict': { + 'id': '1584444', + 'ext': 'mp4', + 'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"', + 'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".', + 'thumbnail': 're:http://.*[.]jpeg', + } + } + + def _real_extract(self, url): + page_id = self._match_id(url) + webpage = self._download_webpage(url, page_id) + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._html_search_regex(r'\bdata-poster="(.+?)"', webpage, 'data-poster') + share_params = self._html_search_regex(r'\bdata-share-params="(.+?)"', webpage, 'data-share-params') + share_params = self._parse_json(share_params, page_id) + video_id = share_params['id'] + quality_data = self._html_search_regex(r'\bdata-quality="(.+?)"', webpage, 'data-quality') + quality_data = self._parse_json(quality_data, page_id) + formats = [] + for format_id, url in quality_data.items(): + formats.append({ + 'format_id': format_id, + 'height': int(format_id.rstrip('p')), + 'url': url, + 'ext': 'mp4', + }) + self._sort_formats(formats) + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + }