mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-19 05:40:51 +02:00
Merge branch 'master' of github.com:rg3/youtube-dl
This commit is contained in:
commit
f009fcac0d
@ -1,3 +1,9 @@
|
||||
version <unreleased>
|
||||
|
||||
Extractors
|
||||
* [newgrounds] Fix uploader extraction (#10584)
|
||||
|
||||
|
||||
version 2016.09.08
|
||||
|
||||
Extractors
|
||||
|
@ -1,15 +1,12 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class NewgroundsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.newgrounds.com/audio/listen/549479',
|
||||
'url': 'https://www.newgrounds.com/audio/listen/549479',
|
||||
'md5': 'fe6033d297591288fa1c1f780386f07a',
|
||||
'info_dict': {
|
||||
'id': '549479',
|
||||
@ -18,7 +15,7 @@ class NewgroundsIE(InfoExtractor):
|
||||
'uploader': 'Burn7',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.newgrounds.com/portal/view/673111',
|
||||
'url': 'https://www.newgrounds.com/portal/view/673111',
|
||||
'md5': '3394735822aab2478c31b1004fe5e5bc',
|
||||
'info_dict': {
|
||||
'id': '673111',
|
||||
@ -29,24 +26,20 @@ class NewgroundsIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
music_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, music_id)
|
||||
media_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, media_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<title>([^>]+)</title>', webpage, 'title')
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
[r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
|
||||
webpage, 'uploader')
|
||||
r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
|
||||
|
||||
music_url_json_string = self._html_search_regex(
|
||||
r'({"url":"[^"]+"),', webpage, 'music url') + '}'
|
||||
music_url_json = json.loads(music_url_json_string)
|
||||
music_url = music_url_json['url']
|
||||
music_url = self._parse_json(self._search_regex(
|
||||
r'"url":("[^"]+"),', webpage, ''), media_id)
|
||||
|
||||
return {
|
||||
'id': music_id,
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'url': music_url,
|
||||
'uploader': uploader,
|
||||
|
Loading…
Reference in New Issue
Block a user