python爬取csdn所有文章_Python爬取CSDN首页的全部文章

import re

import urllib.request

url="https://blog.csdn.net/"

#伪装成浏览器User-Agent        Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0

headers=("User-Agent","Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0")

opener=urllib.request.build_opener()

opener.addheader=[headers]

#将opener对象安装为全局

urllib.request.install_opener(opener)

data=urllib.request.urlopen(url).read()

data=data.decode("utf-8","ignore")

print(len(data))

#设置正则

pat='