From 3b9b32f404ab09d9dc801dd8ec57d79711be5cb3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 18 Aug 2015 13:02:41 +0200 Subject: [PATCH] [libsyn] Strip options from player URL --- youtube_dl/extractor/libsyn.py | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py index 9ab1416f5..d375695f5 100644 --- a/youtube_dl/extractor/libsyn.py +++ b/youtube_dl/extractor/libsyn.py @@ -8,9 +8,9 @@ class LibsynIE(InfoExtractor): - _VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P[0-9]+)' + _VALID_URL = r'(?Phttps?://html5-player\.libsyn\.com/embed/episode/id/(?P[0-9]+))' - _TEST = { + _TESTS = [{ 'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/', 'md5': '443360ee1b58007bc3dcf09b41d093bb', 'info_dict': { @@ -19,12 +19,24 @@ class LibsynIE(InfoExtractor): 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", 'description': 'md5:601cb790edd05908957dae8aaa866465', 'upload_date': '20150220', + 'thumbnail': 're:^https?://.*', }, - } + }, { + 'url': 'https://html5-player.libsyn.com/embed/episode/id/3727166/height/75/width/200/theme/standard/direction/no/autoplay/no/autonext/no/thumbnail/no/preload/no/no_addthis/no/', + 'md5': '6c5cb21acd622d754d3b1a92b582ce42', + 'info_dict': { + 'id': '3727166', + 'ext': 'mp3', + 'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career', + 'upload_date': '20150818', + 'thumbnail': 're:^https?://.*', + } + }] def _real_extract(self, url): - video_id = self._match_id(url) - + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + url = m.group('mainurl') webpage = self._download_webpage(url, video_id) formats = [{ @@ -32,20 +44,18 @@ def _real_extract(self, url): } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))] podcast_title = self._search_regex( - r'

([^<]+)

', webpage, 'title') + r'

([^<]+)

', webpage, 'podcast title', default=None) episode_title = self._search_regex( - r'

([^<]+)

', webpage, 'title', default=None) + r'(?:
|

)([^<]+)(.+?)

', webpage, - 'description', fatal=False) - + 'description', default=None) 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))