]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/libsyn.py
9ab1416f55e29d69681d0ccf3678957482a3e80c
[youtubedl] / youtube_dl / extractor / libsyn.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import unified_strdate
8
9
10 class LibsynIE(InfoExtractor):
11 _VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
12
13 _TEST = {
14 'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
15 'md5': '443360ee1b58007bc3dcf09b41d093bb',
16 'info_dict': {
17 'id': '3377616',
18 'ext': 'mp3',
19 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
20 'description': 'md5:601cb790edd05908957dae8aaa866465',
21 'upload_date': '20150220',
22 },
23 }
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27
28 webpage = self._download_webpage(url, video_id)
29
30 formats = [{
31 'url': media_url,
32 } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
33
34 podcast_title = self._search_regex(
35 r'<h2>([^<]+)</h2>', webpage, 'title')
36 episode_title = self._search_regex(
37 r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
38
39 title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
40
41 description = self._html_search_regex(
42 r'<div id="info_text_body">(.+?)</div>', webpage,
43 'description', fatal=False)
44
45 thumbnail = self._search_regex(
46 r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
47 webpage, 'thumbnail', fatal=False)
48
49 release_date = unified_strdate(self._search_regex(
50 r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
51
52 return {
53 'id': video_id,
54 'title': title,
55 'description': description,
56 'thumbnail': thumbnail,
57 'upload_date': release_date,
58 'formats': formats,
59 }