From de02d1f4e94a50eaad0f268fffec6880e9d61d2f Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Mon, 8 Aug 2016 04:58:02 +0700 Subject: [PATCH] [rozhlas] Fix regexes and improve extraction (Closes #10253) --- youtube_dl/extractor/rozhlas.py | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/rozhlas.py b/youtube_dl/extractor/rozhlas.py index ef99b5b1f..f8eda8dea 100644 --- a/youtube_dl/extractor/rozhlas.py +++ b/youtube_dl/extractor/rozhlas.py @@ -2,11 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + int_or_none, + remove_start, +) class RozhlasIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?prehravac\.rozhlas\.cz/audio/(?P[0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://prehravac.rozhlas.cz/audio/3421320', 'md5': '504c902dbc9e9a1fd50326eccf02a7e2', 'info_dict': { @@ -15,20 +19,32 @@ class RozhlasIE(InfoExtractor): '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' } - } + }, { + 'url': 'http://prehravac.rozhlas.cz/audio/3421320/embed', + 'skip_download': True, + }] def _real_extract(self, url): audio_id = self._match_id(url) - webpage = self._download_webpage(url, audio_id) - title = self._html_search_regex(r'

(.+?)

', webpage, 'title') - description = self._html_search_regex(r'

', webpage, 'description', fatal=False) + webpage = self._download_webpage( + 'http://prehravac.rozhlas.cz/audio/%s' % audio_id, audio_id) - url = 'http://media.rozhlas.cz/_audio/' + audio_id + '.mp3' + title = self._html_search_regex( + r'

(.+?)

\s*]*>.*?

\s*]+id=["\']player-track', + webpage, 'title', default=None) or remove_start( + self._og_search_title(webpage), 'Radio Wave - ') + description = self._html_search_regex( + r']+title=(["\'])(?P(?:(?!\1).)+)\1[^>]*>.*?

\s*]+id=["\']player-track', + webpage, 'description', fatal=False, group='url') + duration = int_or_none(self._search_regex( + r'data-duration=["\'](\d+)', webpage, 'duration', default=None)) return { 'id': audio_id, - 'url': url, + 'url': 'http://media.rozhlas.cz/_audio/%s.mp3' % audio_id, 'title': title, 'description': description, + 'duration': duration, + 'vcodec': 'none', } -- 2.22.2