]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/libsyn.py
2 from __future__
import unicode_literals
5 from .common
import InfoExtractor
15 class LibsynIE(InfoExtractor
):
16 _VALID_URL
= r
'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
19 'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
20 'md5': '2a55e75496c790cdeb058e7e6c087746',
24 'title': "Champion Minded - Developing a Growth Mindset",
25 # description fetched using another request:
26 # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
27 # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
28 'upload_date': '20180320',
29 'thumbnail': 're:^https?://.*',
32 '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/',
33 'md5': '6c5cb21acd622d754d3b1a92b582ce42',
37 'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
38 'upload_date': '20150818',
39 'thumbnail': 're:^https?://.*',
43 def _real_extract(self
, url
):
44 url
, video_id
= self
._match
_valid
_url
(url
).groups()
45 webpage
= self
._download
_webpage
(url
, video_id
)
47 data
= self
._parse
_json
(self
._search
_regex
(
48 r
'var\s+playlistItem\s*=\s*({.+?});',
49 webpage
, 'JSON data block'), video_id
)
51 episode_title
= data
.get('item_title') or get_element_by_class('episode-title', webpage
)
54 [r
'data-title="([^"]+)"', r
'<title>(.+?)</title>'],
55 webpage
, 'episode title')
56 episode_title
= episode_title
.strip()
58 podcast_title
= strip_or_none(clean_html(self
._search
_regex
(
59 r
'<h3>([^<]+)</h3>', webpage
, 'podcast title',
60 default
=None) or get_element_by_class('podcast-title', webpage
)))
62 title
= '%s - %s' % (podcast_title
, episode_title
) if podcast_title
else episode_title
65 for k
, format_id
in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
71 'format_id': format_id
,
74 description
= self
._html
_search
_regex
(
75 r
'<p\s+id="info_text_body">(.+?)</p>', webpage
,
76 'description', default
=None)
78 # Strip non-breaking and normal spaces
79 description
= description
.replace('\u00A0', ' ').strip()
80 release_date
= unified_strdate(self
._search
_regex
(
81 r
'<div class="release_date">Released: ([^<]+)<',
82 webpage
, 'release date', default
=None) or data
.get('release_date'))
87 'description': description
,
88 'thumbnail': data
.get('thumbnail_url'),
89 'upload_date': release_date
,
90 'duration': parse_duration(data
.get('duration')),