From 49aeedb8cb4dcf317c970a58c590d42e37904720 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sun, 22 Mar 2015 08:11:10 +0600 Subject: [PATCH] [libsyn] Improve and simplify --- youtube_dl/extractor/libsyn.py | 87 +++++++++++++++++++--------------- 1 file changed, 48 insertions(+), 39 deletions(-) diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py index 88379f276..6bf741db8 100644 --- a/youtube_dl/extractor/libsyn.py +++ b/youtube_dl/extractor/libsyn.py @@ -1,50 +1,59 @@ -# encoding: utf-8 +# coding: utf-8 +from __future__ import unicode_literals + +import re + from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate + class LibsynIE(InfoExtractor): - _VALID_URL = r'(?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/(?P[0-9]+)(?:/.*)?' - _TESTS = [{ - 'url': "http://html5-player.libsyn.com/embed/episode/id/3377616/", + _VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P[0-9]+)' + + _TEST = { + 'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/', + 'md5': '443360ee1b58007bc3dcf09b41d093bb', 'info_dict': { - 'id': "3377616", - 'ext': "mp3", - 'title': "Episode 12: Bassem Youssef: Egypt's Jon Stewart", - 'description': "

Bassem Youssef joins executive producer Steve Bodow and senior producer Sara Taksler for a conversation about how The Daily Show inspired Bassem to create Al-Bernameg, his massively popular (and now banned) Egyptian news satire program. Sara discusses her soon-to-be-released documentary, Tickling Giants, which chronicles how Bassem and his staff risked their safety every day to tell jokes.

", + 'id': '3377616', + 'ext': 'mp3', + 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", + 'description': 'md5:601cb790edd05908957dae8aaa866465', + 'upload_date': '20150220', }, - }] + } def _real_extract(self, url): - if url.startswith('//'): - url = 'https:' + url - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - podcast_title = self._search_regex(r'

(.*?)

', webpage, 'show title') - podcast_episode_title = self._search_regex(r'

(.*?)

', webpage, 'episode title') - podcast_date = unified_strdate(self._search_regex(r'
Released: (.*?)
', webpage, 'release date')) - podcast_description = self._search_regex(r'
(.*?)
', webpage, 'description') - - url0 = self._search_regex(r'var mediaURLLibsyn = "(?Phttps?://.*)";', webpage, 'first media URL') - url1 = self._search_regex(r'var mediaURL = "(?Phttps?://.*)";', webpage, 'second media URL') - - if url0 != url1: - formats = [{ - 'url': url0 - }, { - 'url': url1 - }] - else: - formats = [{ - 'url': url0 - }] + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + formats = [{ + 'url': media_url, + } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))] + + podcast_title = self._search_regex( + r'

([^<]+)

', webpage, 'title') + episode_title = self._search_regex( + r'

([^<]+)

', webpage, 'title', default=None) + + title = '%s - %s' %(podcast_title, episode_title) if podcast_title else episode_title + + description = self._html_search_regex( + r'
(.+?)
', webpage, + 'description', fatal=False) + + thumbnail = self._search_regex( + r']+class="info-show-icon"[^>]+src="([^"]+)"', + webpage, 'thumbnail', fatal=False) + + release_date = unified_strdate(self._search_regex( + r'
Released: ([^<]+)<', webpage, 'release date', fatal=False)) return { - 'id': display_id, - 'title': podcast_episode_title, - 'description': podcast_description, - 'upload_date': podcast_date, + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': release_date, 'formats': formats, } -- 2.22.2