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/cjsw.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

68 lines
2.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from .common import InfoExtractor
from ..utils import (
determine_ext,
unescapeHTML,
)
class CJSWIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
_TESTS = [{
'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
'md5': 'cee14d40f1e9433632c56e3d14977120',
'info_dict': {
'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
'ext': 'mp3',
'title': 'Freshly Squeezed Episode June 20, 2017',
'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
'series': 'Freshly Squeezed',
'episode_id': '20170620',
},
}, {
# no description
'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
program, episode_id = mobj.group('program', 'id')
audio_id = '%s/%s' % (program, episode_id)
webpage = self._download_webpage(url, episode_id)
title = unescapeHTML(self._search_regex(
(r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
webpage, 'title', group='title'))
audio_url = self._search_regex(
r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'audio url', group='url')
audio_id = self._search_regex(
r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
audio_url, 'audio id', default=audio_id)
formats = [{
'url': audio_url,
'ext': determine_ext(audio_url, 'mp3'),
'vcodec': 'none',
}]
description = self._html_search_regex(
r'<p>(?P<description>.+?)</p>', webpage, 'description',
default=None)
series = self._search_regex(
r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
'series', default=program, group='name')
return {
'id': audio_id,
'title': title,
'description': description,
'formats': formats,
'series': series,
'episode_id': episode_id,
}