1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import unified_strdate
class LibsynIE(InfoExtractor):
_VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
'md5': '443360ee1b58007bc3dcf09b41d093bb',
'info_dict': {
'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):
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'<h2>([^<]+)</h2>', webpage, 'title')
episode_title = self._search_regex(
r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
description = self._html_search_regex(
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 {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': release_date,
'formats': formats,
}
|
