Python BeautifulSoup库 Python实战快速上手BeautifulSoup库爬取专栏标题和地址

pip install beautifulsoup4
# 上面的安装失败使用下面的 使用镜像
pip install beautifulsoup4 -i http://pypi.tuna.tsinghua.edu.cn/simple

from bs4 import BeautifulSoup
import requests
url='https://blog.csdn.net/weixin_42403632/category_11076268.html'
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
html=requests.get(url,headers=headers).text
s=BeautifulSoup(html,'html.parser')
title =s.select('h2')
for i in title:
    print(i.text)

from bs4 import BeautifulSoup
import requests
url='https://blog.csdn.net/weixin_42403632/category_11076268.html'
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
html=requests.get(url,headers=headers).text
s=BeautifulSoup(html,'html.parser')
title =s.select('.column_article_title')
for i in title:
    print(i.text)

from bs4 import BeautifulSoup
html='''<div class="crop-img-before">
         <img src="" alt="" id="cropImg">
      </div>
        <div id='title'>
        测试成功
        </div>
      <div class="crop-zoom">
         <a href="javascript:;" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="bt-reduce">-</a><a href="javascript:;" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="bt-add">+</a>
      </div>
      <div class="crop-img-after">
         <div  class="final-img"></div>
      </div>'''
s=BeautifulSoup(html,'html.parser')
title =s.select('#title')
for i in title:
    print(i.text)

from bs4 import BeautifulSoup
html='''<div class="crop-img-before">
         <img src="" alt="" id="cropImg">
      </div>
        <div id='title'>
        456456465
        <h1>测试成功</h1>
        </div>
      <div class="crop-zoom">
         <a href="javascript:;" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="bt-reduce">-</a><a href="javascript:;" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="bt-add">+</a>
      </div>
      <div class="crop-img-after">
         <div  class="final-img"></div>
      </div>'''
s=BeautifulSoup(html,'html.parser')
title =s.select('#title')
for i in title:
    print(i.text)
title =s.select('#title h1')
for i in title:
    print(i.text)

title =s.select('a')
for i in title:
    print(i['href'])

from bs4 import BeautifulSoup
import requests
import re
url='https://blog.csdn.net/weixin_42403632/category_11298953.html'
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
html=requests.get(url,headers=headers).text
s=BeautifulSoup(html,'html.parser')
title =s.select('.column_article_list li a')
for i in title:
    print((re.findall('原创.*?\n(.*?)\n',i.text))[0].lstrip())
    print(i['href'])