From 5f627b4448f3276089978177a550624bbd5e945f Mon Sep 17 00:00:00 2001 From: Petr Kutalek Date: Wed, 17 Dec 2014 15:52:54 +0100 Subject: [PATCH] [dvtv] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/dvtv.py | 63 ++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) create mode 100644 youtube_dl/extractor/dvtv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c30cbc926..79f6f6f13 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -88,6 +88,7 @@ from .dotsub import DotsubIE from .dreisat import DreiSatIE from .drtuber import DrTuberIE from .drtv import DRTVIE +from .dvtv import DVTVIE from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE diff --git a/youtube_dl/extractor/dvtv.py b/youtube_dl/extractor/dvtv.py new file mode 100644 index 000000000..a52bb3469 --- /dev/null +++ b/youtube_dl/extractor/dvtv.py @@ -0,0 +1,63 @@ +# coding: utf-8 + +from __future__ import unicode_literals + +import re +import json +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + js_to_json, + unescapeHTML +) + + +class DVTVIE(InfoExtractor): + IE_NAME = 'dvtv' + IE_DESC = 'http://video.aktualne.cz/dvtv/' + + _VALID_URL = r'http://video\.aktualne\.cz/dvtv/(?P[a-z0-9-]+/r~[0-9a-f]{32})/?' + + _TESTS = [{ + 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', + 'md5': '75800f964fa0f82939a2914563301f72', + 'info_dict': { + 'id': 'e5efe9ca855511e4833a0025900fea04', + 'ext': 'webm', + 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně' + } + }, { + 'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/', + 'md5': 'd50455195a67a94c57f931360cc68a1b', + 'info_dict': { + 'id': '82ed4322849211e4a10c0025900fea04', + 'ext': 'webm', + 'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala' + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + code = self._search_regex(r'embedData[0-9a-f]{32}\[\'asset\'\] = (\{.+?\});', webpage, 'video JSON', flags=re.DOTALL) + payload = self._parse_json(code, video_id, transform_source=js_to_json) + formats = [] + for source in payload['sources']: + formats.append({ + 'url': source['file'], + 'ext': source['type'][6:], + 'format': '%s %s' % (source['type'][6:], source['label']), + 'format_id': '%s-%s' % (source['type'][6:], source['label']), + 'resolution': source['label'], + 'fps': 25, + 'preference': -1 if source['type'][6:] == 'mp4' and source['label'] == '720p' else -2 + }) + + return { + 'id': video_id[-32:], + 'display_id': video_id[:-35], + 'title': unescapeHTML(payload['title']), + 'thumbnail': 'http:%s' % payload['image'], + 'formats': formats + } -- 2.22.2