1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 14:47:44 +01:00
yt-dlp/yt_dlp/extractor/libsyn.py

89 lines
3.5 KiB
Python
Raw Normal View History

2015-03-16 20:05:02 +01:00
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
parse_duration,
strip_or_none,
unified_strdate,
)
2015-03-22 03:11:10 +01:00
2015-03-16 20:05:02 +01:00
class LibsynIE(InfoExtractor):
2015-08-18 13:02:41 +02:00
_VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
2015-03-22 03:11:10 +01:00
2015-08-18 13:02:41 +02:00
_TESTS = [{
'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
'md5': '2a55e75496c790cdeb058e7e6c087746',
'info_dict': {
'id': '6385796',
2015-03-22 03:11:10 +01:00
'ext': 'mp3',
'title': "Champion Minded - Developing a Growth Mindset",
# description fetched using another request:
# http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
# 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
'upload_date': '20180320',
2015-08-18 13:02:41 +02:00
'thumbnail': 're:^https?://.*',
},
2015-08-18 13:02:41 +02:00
}, {
'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/',
'md5': '6c5cb21acd622d754d3b1a92b582ce42',
'info_dict': {
'id': '3727166',
'ext': 'mp3',
'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
'upload_date': '20150818',
'thumbnail': 're:^https?://.*',
}
}]
2015-03-16 20:05:02 +01:00
def _real_extract(self, url):
url, video_id = self._match_valid_url(url).groups()
2015-03-22 03:11:10 +01:00
webpage = self._download_webpage(url, video_id)
data = self._parse_json(self._search_regex(
r'var\s+playlistItem\s*=\s*({.+?});',
webpage, 'JSON data block'), video_id)
episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
if not episode_title:
self._search_regex(
[r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
webpage, 'episode title')
episode_title = episode_title.strip()
podcast_title = strip_or_none(clean_html(self._search_regex(
r'<h3>([^<]+)</h3>', webpage, 'podcast title',
default=None) or get_element_by_class('podcast-title', webpage)))
2015-03-22 03:11:10 +01:00
title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
2015-03-22 03:11:10 +01:00
formats = []
for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
f_url = data.get(k)
if not f_url:
continue
formats.append({
'url': f_url,
'format_id': format_id,
})
2015-03-22 03:11:10 +01:00
description = self._html_search_regex(
r'<p\s+id="info_text_body">(.+?)</p>', webpage,
2015-08-18 13:02:41 +02:00
'description', default=None)
if description:
# Strip non-breaking and normal spaces
description = description.replace('\u00A0', ' ').strip()
2015-03-22 03:11:10 +01:00
release_date = unified_strdate(self._search_regex(
r'<div class="release_date">Released: ([^<]+)<',
webpage, 'release date', default=None) or data.get('release_date'))
2015-03-16 20:05:02 +01:00
return {
2015-03-22 03:11:10 +01:00
'id': video_id,
'title': title,
'description': description,
'thumbnail': data.get('thumbnail_url'),
2015-03-22 03:11:10 +01:00
'upload_date': release_date,
'duration': parse_duration(data.get('duration')),
2015-03-16 20:05:02 +01:00
'formats': formats,
}