From e3b224a330833e1ecd2a66776ad3b6a1109da916 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 26 Feb 2021 18:17:34 +0100 Subject: [PATCH] [ninegag] unscape title(#28201) --- haruhi_dl/extractor/ninegag.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/haruhi_dl/extractor/ninegag.py b/haruhi_dl/extractor/ninegag.py index 440f865bc..14390823b 100644 --- a/haruhi_dl/extractor/ninegag.py +++ b/haruhi_dl/extractor/ninegag.py @@ -2,10 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - determine_ext, ExtractorError, + determine_ext, int_or_none, try_get, + unescapeHTML, url_or_none, ) @@ -14,7 +15,7 @@ class NineGagIE(InfoExtractor): IE_NAME = '9gag' _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P[^/?&#]+)' - _TEST = { + _TESTS = [{ 'url': 'https://9gag.com/gag/ae5Ag7B', 'info_dict': { 'id': 'ae5Ag7B', @@ -29,7 +30,11 @@ class NineGagIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, } - } + }, { + # HTML escaped title + 'url': 'https://9gag.com/gag/av5nvyb', + 'only_matching': True, + }] def _real_extract(self, url): post_id = self._match_id(url) @@ -43,7 +48,7 @@ class NineGagIE(InfoExtractor): 'The given url does not contain a video', expected=True) - title = post['title'] + title = unescapeHTML(post['title']) duration = None formats = []