[rozhlas] Add new extractor

This commit is contained in:
Petr Zvoníček 2016-08-07 17:35:54 +02:00 committed by Sergey M․
parent d21a661bb4
commit e1f93a0a76
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 35 additions and 0 deletions

View file

@ -696,6 +696,7 @@ from .rockstargames import RockstarGamesIE
from .roosterteeth import RoosterTeethIE from .roosterteeth import RoosterTeethIE
from .rottentomatoes import RottenTomatoesIE from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE from .roxwel import RoxwelIE
from .rozhlas import RozhlasIE
from .rtbf import RTBFIE from .rtbf import RTBFIE
from .rte import RteIE, RteRadioIE from .rte import RteIE, RteRadioIE
from .rtlnl import RtlNlIE from .rtlnl import RtlNlIE

View file

@ -0,0 +1,34 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class RozhlasIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?prehravac\.rozhlas\.cz/audio/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://prehravac.rozhlas.cz/audio/3421320',
'md5': '504c902dbc9e9a1fd50326eccf02a7e2',
'info_dict': {
'id': '3421320',
'ext': 'mp3',
'title': 'Echo Pavla Klusáka (30.06.2015 21:00)',
'description': 'Osmdesátiny Terryho Rileyho jsou skvělou příležitostí proletět se elektronickými i akustickými díly zakladatatele minimalismu, který je aktivní už přes padesát let'
}
}
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
title = self._html_search_regex(r'<h3>(.+?)</h3>', webpage, 'title')
description = self._html_search_regex(r'<p title="(.+?)">', webpage, 'description', fatal=False)
url = 'http://media.rozhlas.cz/_audio/' + audio_id + '.mp3'
return {
'id': audio_id,
'url': url,
'title': title,
'description': description,
}