pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-03-23 00:07:27 +09:00
Code Issues Projects Releases Wiki Activity

No default for content_id, better content parsing

Browse Source
This commit is contained in:
Martin Vician 2022-03-25 16:18:21 +00:00
parent fb13bb6598
commit d4ac3ac47f
No known key found for this signature in database
GPG Key ID: CA35047BCEF7ACC4
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
youtube_dl/extractor/mujrozhlas.py
View File

@ -9,7 +9,7 @@ from ..utils import (
class MujRozhlasIE(InfoExtractor): class MujRozhlasIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mujrozhlas\.cz/(?P<id>[a-zA-Z0-9\-\/]+)' _VALID_URL = r'https?://(?:www\.)?mujrozhlas\.cz/(?P<id>[a-zA-Z0-9/-]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.mujrozhlas.cz/meteor/meteor-o-nejvetsim-matematikovi-nekonecnem-vesmiru-skakajicim-pavoukovi-hrani-surikat', 'url': 'https://www.mujrozhlas.cz/meteor/meteor-o-nejvetsim-matematikovi-nekonecnem-vesmiru-skakajicim-pavoukovi-hrani-surikat',
'info_dict': { 'info_dict': {
@ -33,14 +33,16 @@ class MujRozhlasIE(InfoExtractor):
webpage = self._download_webpage(url, audio_id) webpage = self._download_webpage(url, audio_id)
content_id = self._html_search_regex(r'\"contentId\":\"(.+?)\"', webpage, 'content_id', default=None) content_id = self._html_search_regex(r'\"contentId\":\"(.+?)\"', webpage, 'content_id')
content_url = 'https://api.mujrozhlas.cz/episodes/' + content_id content_url = 'https://api.mujrozhlas.cz/episodes/' + content_id
content = self._download_json(content_url, content_id) content = self._download_json(content_url, content_id)
audio_url = content['data']['attributes']['audioLinks'][0]['url'] attrs = content['data']['attributes']
duration = content['data']['attributes']['audioLinks'][0]['duration'] title = attrs['title']
title = content['data']['attributes']['title'] audio_info = content['data']['attributes']['audioLinks'][0]
description = clean_html(content['data']['attributes']['description']) duration = audio_info.get('duration')
description = clean_html(attrs.get('description'))
audio_url = audio_info.get('url')
return { return {
'id': audio_id, 'id': audio_id,