From: pulpe Date: Fri, 13 Jun 2014 06:51:35 +0000 (+0200) Subject: [WrzutaIE] Add extractor for wrzuta.pl (fixes #3072) X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=0c361c41b895147372ecd18d31dfa1c0d3f7b6a4;p=youtube-dl [WrzutaIE] Add extractor for wrzuta.pl (fixes #3072) --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 45cc479e2..270925677 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -344,6 +344,7 @@ from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE +from .wrzuta import WrzutaIE from .xbef import XBefIE from .xhamster import XHamsterIE from .xnxx import XNXXIE diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py new file mode 100644 index 000000000..cfa76a6d2 --- /dev/null +++ b/youtube_dl/extractor/wrzuta.py @@ -0,0 +1,80 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + qualities, +) + + +class WrzutaIE(InfoExtractor): + IE_NAME = 'wrzuta.pl' + + _VALID_URL = r'https?://(?P[0-9a-zA-Z]+)\.wrzuta\.pl/(?Pfilm|audio)/(?P[0-9a-zA-Z]+)' + + _TESTS = [{ + 'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game', + 'md5': '9e67e05bed7c03b82488d87233a9efe7', + 'info_dict': { + 'id': 'aq4hIZWrkBu', + 'ext': 'mp4', + 'title': 'Nike Football: The Last Game', + 'duration': 307, + 'uploader_id': 'laboratoriumdextera', + 'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd', + }, + }, { + 'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad', + 'md5': '1e546a18e1c22ac6e9adce17b8961ff5', + 'info_dict': { + 'id': '9oXJqdcndqv', + 'ext': 'ogg', + 'title': 'David Guetta & Showtek ft. Vassy - Bad', + 'duration': 270, + 'uploader_id': 'w729', + 'description': 'md5:4628f01c666bbaaecefa83476cfa794a', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + typ = mobj.group('typ') + uploader = mobj.group('uploader') + + webpage = self._download_webpage(url, video_id) + + quality = qualities(['SD', 'MQ', 'HQ', 'HD']) + + audio_table = {'flv': 'mp3', 'webm': 'ogg'} + + embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id) + + formats = [] + for media in embedpage['url']: + if typ == 'audio': + ext = audio_table[media['type'].split('@')[0]] + else: + ext = media['type'].split('@')[0] + + formats.append({ + 'format_id': '%s_%s' % (ext, media['quality'].lower()), + 'url': media['url'], + 'ext': ext, + 'quality': quality(media['quality']), + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + 'duration': int_or_none(embedpage['duration']), + 'uploader_id': uploader, + 'description': self._og_search_description(webpage), + }