]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/libsyn.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
16 class LibsynIE(InfoExtractor
):
17 _VALID_URL
= r
'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
20 'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
21 'md5': '2a55e75496c790cdeb058e7e6c087746',
25 'title': "Champion Minded - Developing a Growth Mindset",
26 # description fetched using another request:
27 # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
28 # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
29 'upload_date': '20180320',
30 'thumbnail': 're:^https?://.*',
33 '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/',
34 'md5': '6c5cb21acd622d754d3b1a92b582ce42',
38 'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
39 'upload_date': '20150818',
40 'thumbnail': 're:^https?://.*',
44 def _real_extract(self
, url
):
45 url
, video_id
= re
.match(self
._VALID
_URL
, url
).groups()
46 webpage
= self
._download
_webpage
(url
, video_id
)
48 data
= self
._parse
_json
(self
._search
_regex
(
49 r
'var\s+playlistItem\s*=\s*({.+?});',
50 webpage
, 'JSON data block'), video_id
)
52 episode_title
= data
.get('item_title') or get_element_by_class('episode-title', webpage
)
55 [r
'data-title="([^"]+)"', r
'<title>(.+?)</title>'],
56 webpage
, 'episode title')
57 episode_title
= episode_title
.strip()
59 podcast_title
= strip_or_none(clean_html(self
._search
_regex
(
60 r
'<h3>([^<]+)</h3>', webpage
, 'podcast title',
61 default
=None) or get_element_by_class('podcast-title', webpage
)))
63 title
= '%s - %s' % (podcast_title
, episode_title
) if podcast_title
else episode_title
66 for k
, format_id
in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
72 'format_id': format_id
,
75 description
= self
._html
_search
_regex
(
76 r
'<p\s+id="info_text_body">(.+?)</p>', webpage
,
77 'description', default
=None)
79 # Strip non-breaking and normal spaces
80 description
= description
.replace('\u00A0', ' ').strip()
81 release_date
= unified_strdate(self
._search
_regex
(
82 r
'<div class="release_date">Released: ([^<]+)<',
83 webpage
, 'release date', default
=None) or data
.get('release_date'))
88 'description': description
,
89 'thumbnail': data
.get('thumbnail_url'),
90 'upload_date': release_date
,
91 'duration': parse_duration(data
.get('duration')),