Python爬虫

import requests

import re

headers={

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'

 }

R=requests.get('https://tieba.baidu.com/f?kw=%E5%AD%99%E7%AC%91%E5%B7%9D',headers=headers)

print(re.findall("""<a rel="noopener" href=".*?" title="(.*?)" target="_blank" class="j_th_tit ">.*?</a>""",R.content.decode(),re.DOTALL))

 

 

headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'}

R=requests.get('https://36kr.com/',headers=headers)

url1=re.findall("""<a class="article-item-title weight-bold" href="(.*?)" target="_blank" sensors_operation_list="page_flow">.*?</a>""",R.text)

url2=['https://36kr.com'+i for i in url1]

print(url2)

title=re.findall("""<a class="article-item-title weight-bold" href=".*?" target="_blank" sensors_operation_list="page_flow">(.*?)</a>""",R.text)

print(title)