[libsyn] Improve and simplify

This commit is contained in:
Sergey M․ 2015-03-22 08:11:10 +06:00
parent ef249a2cd7
commit 49aeedb8cb

View File

@ -1,50 +1,59 @@
# encoding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import unified_strdate
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'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
_TESTS = [{
'url': "http://html5-player.libsyn.com/embed/episode/id/3377616/", _TEST = {
'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
'md5': '443360ee1b58007bc3dcf09b41d093bb',
'info_dict': { 'info_dict': {
'id': "3377616", 'id': '3377616',
'ext': "mp3", 'ext': 'mp3',
'title': "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': "<p>Bassem Youssef joins executive producer Steve Bodow and senior producer Sara Taksler for a conversation about how&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">The Daily Show</em>&nbsp;inspired Bassem to create&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Al-Bernameg</em>, his massively popular (and now banned) Egyptian news satire program. Sara discusses her soon-to-be-released documentary,&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Tickling Giants</em>, which chronicles how Bassem and his staff risked their safety every day to tell jokes.</p>", 'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220',
}, },
}] }
def _real_extract(self, url): def _real_extract(self, url):
if url.startswith('//'): video_id = self._match_id(url)
url = 'https:' + url
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
podcast_title = self._search_regex(r'<h2>(.*?)</h2>', webpage, 'show title') webpage = self._download_webpage(url, video_id)
podcast_episode_title = self._search_regex(r'<h3>(.*?)</h3>', webpage, 'episode title')
podcast_date = unified_strdate(self._search_regex(r'<div class="release_date">Released: (.*?)</div>', webpage, 'release date'))
podcast_description = self._search_regex(r'<div id="info_text_body">(.*?)</div>', webpage, 'description')
url0 = self._search_regex(r'var mediaURLLibsyn = "(?P<url0>https?://.*)";', webpage, 'first media URL') formats = [{
url1 = self._search_regex(r'var mediaURL = "(?P<url1>https?://.*)";', webpage, 'second media URL') 'url': media_url,
} for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
if url0 != url1: podcast_title = self._search_regex(
formats = [{ r'<h2>([^<]+)</h2>', webpage, 'title')
'url': url0 episode_title = self._search_regex(
}, { r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
'url': url1
}] title = '%s - %s' %(podcast_title, episode_title) if podcast_title else episode_title
else:
formats = [{ description = self._html_search_regex(
'url': url0 r'<div id="info_text_body">(.+?)</div>', webpage,
}] 'description', fatal=False)
thumbnail = self._search_regex(
r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
release_date = unified_strdate(self._search_regex(
r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
return { return {
'id': display_id, 'id': video_id,
'title': podcast_episode_title, 'title': title,
'description': podcast_description, 'description': description,
'upload_date': podcast_date, 'thumbnail': thumbnail,
'upload_date': release_date,
'formats': formats, 'formats': formats,
} }