From 613288d07b7c098c9710e67eb0d784157b83e7e9 Mon Sep 17 00:00:00 2001 From: popjdh Date: Thu, 20 Jul 2023 16:46:08 +0800 Subject: [PATCH] =?UTF-8?q?=E5=AF=B9GETCHU=E4=BD=BF=E7=94=A8=E6=8C=87?= =?UTF-8?q?=E5=AE=9A=E7=BC=96=E7=A0=81"EUC-JIS-2004"("EUC-JP"=E7=BC=96?= =?UTF-8?q?=E7=A0=81=E7=9A=84=E8=B6=85=E9=9B=86)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- scrapinglib/getchu.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scrapinglib/getchu.py b/scrapinglib/getchu.py index d3494ff..0cc76d8 100644 --- a/scrapinglib/getchu.py +++ b/scrapinglib/getchu.py @@ -69,7 +69,7 @@ class wwwGetchu(Parser): def getHtml(self, url, type = None): """ 访问网页(指定EUC-JP) """ - resp = httprequest.get(url, cookies=self.cookies, proxies=self.proxies, extra_headers=self.extraheader, encoding='euc-jp', verify=self.verify, return_type=type) + resp = httprequest.get(url, cookies=self.cookies, proxies=self.proxies, extra_headers=self.extraheader, encoding='euc_jis_2004', verify=self.verify, return_type=type) if '404 Page Not Found' in resp \ or '<title>未找到页面' in resp \ or '404 Not Found' in resp \