[libsyn] Strip options from player URL

This commit is contained in:
Philipp Hagemeister 2015-08-18 13:02:41 +02:00
parent 9c724a9802
commit 3b9b32f404
1 changed files with 20 additions and 10 deletions

View File

@ -8,9 +8,9 @@ from ..utils import unified_strdate
class LibsynIE(InfoExtractor): class LibsynIE(InfoExtractor):
_VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)' _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
_TEST = { _TESTS = [{
'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/', 'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
'md5': '443360ee1b58007bc3dcf09b41d093bb', 'md5': '443360ee1b58007bc3dcf09b41d093bb',
'info_dict': { '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", 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
'description': 'md5:601cb790edd05908957dae8aaa866465', 'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220', '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): 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) webpage = self._download_webpage(url, video_id)
formats = [{ formats = [{
@ -32,20 +44,18 @@ class LibsynIE(InfoExtractor):
} for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))] } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
podcast_title = self._search_regex( podcast_title = self._search_regex(
r'<h2>([^<]+)</h2>', webpage, 'title') r'<h2>([^<]+)</h2>', webpage, 'podcast title', default=None)
episode_title = self._search_regex( episode_title = self._search_regex(
r'<h3>([^<]+)</h3>', webpage, 'title', default=None) r'(?:<div class="episode-title">|<h3>)([^<]+)</', webpage, 'episode title')
title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
description = self._html_search_regex( description = self._html_search_regex(
r'<div id="info_text_body">(.+?)</div>', webpage, r'<div id="info_text_body">(.+?)</div>', webpage,
'description', fatal=False) 'description', default=None)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"', r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
release_date = unified_strdate(self._search_regex( release_date = unified_strdate(self._search_regex(
r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False)) r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))