pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-02 16:37:59 +09:00
Code Issues Projects Releases Wiki Activity

[channelnewsasia] fix tests, more relaxed regex

Browse Source
This commit is contained in:
fourjr 2020-11-22 18:03:12 +08:00
parent 357a506c20
commit 59e9536b98
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
youtube_dl/extractor/channelnewsasia.py
View File

@ -9,7 +9,7 @@ class ChannelNewsAsiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?channelnewsasia\.com/(?:(?:-|\w|\d)+)/(?:(?:-|\w|\d)+)/(?P<id>(?:-|\w|\d)+)' _VALID_URL = r'https?://(?:www\.)?channelnewsasia\.com/(?:(?:-|\w|\d)+)/(?:(?:-|\w|\d)+)/(?P<id>(?:-|\w|\d)+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://www.channelnewsasia.com/news/video-on-demand/wizards-of-tech', 'url': 'https://www.channelnewsasia.com/news/video-on-demand/wizards-of-tech/wizards-of-tech-body-13515106',
'md5': 'ed9ed143052f0da3ee8a8fa59ba16870', 'md5': 'ed9ed143052f0da3ee8a8fa59ba16870',
'info_dict': { 'info_dict': {
'id': 'w0ZWRzajE6qDPXDb7DSeaOCJ3bJ3GDqC', 'id': 'w0ZWRzajE6qDPXDb7DSeaOCJ3bJ3GDqC',
@ -34,11 +34,15 @@ class ChannelNewsAsiaIE(InfoExtractor):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
url_obj = (
re.search(r'<div.*video-asset-id="(?P<id>(?:\d|\w|-)+)".*</div>', webpage, flags=re.DOTALL)
or re.search(r'<div.*data-video-id="(?P<id>(?:\d|\w|-)+)".*</div>', webpage, flags=re.DOTALL))
ooyala_id = url_obj.group('id') ooyala_id = (
self._search_regex(
r'id="ooyala-\d+-((?:\d|\w|-)+)--\d+', webpage, 'ooyala id',
default=None, fatal=False)
or self._search_regex(
r'video-asset-id="((?:\d|\w|-)+)', webpage, 'ooyala id',
default=None, fatal=False))
return self.url_result( return self.url_result(
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id 'ooyala:' + ooyala_id, 'Ooyala', ooyala_id
) )