mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-12-22 20:20:09 +09:00
added speedrun author and timer
optional (fatal=False) because the website's layout forced me into an unreliably regex.
This commit is contained in:
parent
14834bf977
commit
9addbadd33
@ -27,8 +27,13 @@ class TASVideosIE(InfoExtractor):
|
||||
r'<a [^>]+(?P<URL>archive\.org\/download[^<]+\.(?:mkv|mp4|avi))[^<]+<\/a>',
|
||||
webpage)
|
||||
title = self._search_regex(
|
||||
r'<span title="Movie[^"]+">(?P<TITLE>[^<]+)<\/span>', webpage,
|
||||
'title')
|
||||
r'<span title="Movie[^"]+">(?P<TITLE>[^<]+)<\/span>',
|
||||
webpage, 'title')
|
||||
time_and_author = self._html_search_regex(
|
||||
r'<th.*<\/span>(?P<time_and_author>.*)<\/th>', webpage,
|
||||
'title: speedrun timer and credit', fatal=False)
|
||||
if time_and_author is not None:
|
||||
title = title + time_and_author
|
||||
|
||||
formats = []
|
||||
for url in video_urls:
|
||||
@ -60,15 +65,20 @@ class TASVideosPlaylistIE(InfoExtractor):
|
||||
playlist_title = self._search_regex(
|
||||
r'<title>(?P<title>[^<]*)</title>', webpage, 'title')
|
||||
video_entries = get_elements_by_class('item', webpage)
|
||||
|
||||
|
||||
entries = []
|
||||
for entry in video_entries:
|
||||
video_urls = re.findall(
|
||||
r'<a [^>]+(?P<URL>archive\.org\/download[^<]+\.(?:mkv|mp4|avi))[^<]+<\/a>',
|
||||
entry)
|
||||
title = self._search_regex(
|
||||
r'<span title="Movie[^"]+">(?P<title>[^<]+)<\/span>', entry,
|
||||
'title')
|
||||
r'<span title="Movie[^"]+">(?P<title>[^<]+)<\/span>',
|
||||
entry, 'title')
|
||||
time_and_author = self._html_search_regex(
|
||||
r'<th.*<\/span>(?P<time_and_author>.*)<\/th>', entry,
|
||||
'time_and_author', fatal=False)
|
||||
if time_and_author is not None:
|
||||
title = title + time_and_author
|
||||
video_id = self._search_regex(
|
||||
r'id="movie_(?P<id>\d+)', entry, 'video id') + 'M'
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user