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 2023-09-22 15:58:12 +08:00
parent 33eb17e2b7
commit 1e7c4c0e68
1 changed files with 1 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
language_learning/python/2021.11.17_zhihu/zhihu.py
View File

@ -17,16 +17,6 @@ day = datetime.datetime.now().day
# 由于没有模拟登录知乎，因此只能爬取到最新的两篇文章 # 由于没有模拟登录知乎，因此只能爬取到最新的两篇文章
authors = ["https://www.zhihu.com/people/guanjihuan/posts"] # Guan authors = ["https://www.zhihu.com/people/guanjihuan/posts"] # Guan
# authors = []
# html = urlopen('https://www.guanjihuan.com/others').read().decode('utf-8') # 打开网页
# soup = BeautifulSoup(html, features='lxml') # 放入soup中
# 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('www.zhihu.com/people/', href): # 文章的链接
# if href not in authors:
# authors.append(href)
match_href = [] match_href = []
for i0 in range(len(authors)): for i0 in range(len(authors)):
start_link = authors[i0] start_link = authors[i0]
@ -55,6 +45,7 @@ for n in numbers:
# 获取内容并写入文件 # 获取内容并写入文件
f = open('zhihu.html', 'w', encoding='UTF-8') f = open('zhihu.html', 'w', encoding='UTF-8')
f.write('<meta charset="utf-8"><style type="text/css">a{text-decoration: none;color: #004e4e;}a:hover {text-decoration: underline;color: red; }</style>') f.write('<meta charset="utf-8"><style type="text/css">a{text-decoration: none;color: #004e4e;}a:hover {text-decoration: underline;color: red; }</style>')
f.write('<p>'+str(year)+'.'+str(month).rjust(2,'0')+'.'+str(day).rjust(2,'0')+' 已更新</p>') f.write('<p>'+str(year)+'.'+str(month).rjust(2,'0')+'.'+str(day).rjust(2,'0')+' 已更新</p>')
for href in match_href_new: for href in match_href_new:
try: try: