diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-10 20:09:09 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-10 20:09:09 +0800 |
commit | 6c3affcb18f7eabf7d428e5efe474e0547ab25cb (patch) | |
tree | 62de01d3c0dfc6d924b059489a89fb1cd7c1c30b | |
parent | c6129feb7f8313941a4d2044fa4b45ceaa0a91c7 (diff) |
[newgrounds] Fix uploader extraction
Closes #10584
Also change test URLs to HTTPS, as proposed by
@stepshal in #10593.
Closes #10593
-rw-r--r-- | ChangeLog | 6 | ||||
-rw-r--r-- | youtube_dl/extractor/newgrounds.py | 23 |
2 files changed, 14 insertions, 15 deletions
@@ -1,3 +1,9 @@ +version <unreleased> + +Extractors +* [newgrounds] Fix uploader extraction (#10584) + + version 2016.09.08 Extractors diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index 705940323..9bea610c8 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -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, |