From dbaa7d402b3b7ea297a76185125de75a43d804fc Mon Sep 17 00:00:00 2001 From: guanjihuan Date: Sun, 8 May 2022 15:45:28 +0800 Subject: [PATCH] Update zhihu.py --- language_learning/2021.11.17_zhihu/zhihu.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/language_learning/2021.11.17_zhihu/zhihu.py b/language_learning/2021.11.17_zhihu/zhihu.py index fc2d78f..14a9345 100644 --- a/language_learning/2021.11.17_zhihu/zhihu.py +++ b/language_learning/2021.11.17_zhihu/zhihu.py @@ -24,7 +24,7 @@ for i0 in range(len(authors)): all_a_tag = soup.find_all('a', href=True) # 获取超链接标签 for a_tag in all_a_tag: href = a_tag['href'] # 超链接字符串 - if re.search('//zhuanlan.zhihu.com/p/', href): # 文章的链接 + if re.search('//zhuanlan.zhihu.com/p/', href) and not re.search('edit', href): # 文章的链接 if re.search('https:', href)==None: # 如果链接不是完整的，那么补充完整 href = 'https:'+ href if href not in match_href: