[newgrounds] Fix uploader extraction

Closes #10584

Also change test URLs to HTTPS, as proposed by
@stepshal in #10593.

Closes #10593
This commit is contained in:
Yen Chi Hsuan 2016-09-10 20:09:09 +08:00
parent c6129feb7f
commit 6c3affcb18
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 14 additions and 15 deletions

View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
* [newgrounds] Fix uploader extraction (#10584)
version 2016.09.08 version 2016.09.08
Extractors Extractors

View file

@ -1,15 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor from .common import InfoExtractor
class NewgroundsIE(InfoExtractor): class NewgroundsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.newgrounds.com/audio/listen/549479', 'url': 'https://www.newgrounds.com/audio/listen/549479',
'md5': 'fe6033d297591288fa1c1f780386f07a', 'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': { 'info_dict': {
'id': '549479', 'id': '549479',
@ -18,7 +15,7 @@ class NewgroundsIE(InfoExtractor):
'uploader': 'Burn7', 'uploader': 'Burn7',
} }
}, { }, {
'url': 'http://www.newgrounds.com/portal/view/673111', 'url': 'https://www.newgrounds.com/portal/view/673111',
'md5': '3394735822aab2478c31b1004fe5e5bc', 'md5': '3394735822aab2478c31b1004fe5e5bc',
'info_dict': { 'info_dict': {
'id': '673111', 'id': '673111',
@ -29,24 +26,20 @@ class NewgroundsIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) media_id = self._match_id(url)
music_id = mobj.group('id') webpage = self._download_webpage(url, media_id)
webpage = self._download_webpage(url, music_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title') r'<title>([^>]+)</title>', webpage, 'title')
uploader = self._html_search_regex( uploader = self._html_search_regex(
[r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'], r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
webpage, 'uploader')
music_url_json_string = self._html_search_regex( music_url = self._parse_json(self._search_regex(
r'({"url":"[^"]+"),', webpage, 'music url') + '}' r'"url":("[^"]+"),', webpage, ''), media_id)
music_url_json = json.loads(music_url_json_string)
music_url = music_url_json['url']
return { return {
'id': music_id, 'id': media_id,
'title': title, 'title': title,
'url': music_url, 'url': music_url,
'uploader': uploader, 'uploader': uploader,