guanjihuan/guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update zhihu.py

Browse Source
This commit is contained in:
guanjihuan 2022-05-08 15:45:28 +08:00
parent 67f6b35a48
commit dbaa7d402b
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
language_learning/2021.11.17_zhihu/zhihu.py
View File

@ -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 all_a_tag = soup.find_all('a', href=True) # 获取超链接标签
for a_tag in all_a_tag: for a_tag in all_a_tag:
href = a_tag['href'] # 超链接字符串 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 if re.search('https:', href)==None: # 如果链接不是完整的，那么补充完整
href = 'https:'+ href href = 'https:'+ href
if href not in match_href: if href not in match_href: