python-爬虫案例9-代理器爬虫

可复制代码：

import re

import urllib.request

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

headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36")

opener=urllib.request.build_opener()

opener.addheaders=[headers]

urllib.request.install_opener(opener) ##安装成为全局

data=opener.open(url).read().decode("utf-8","ignore")

pat='href="(https://blog.csdn.net/.*?)"'

allurl=re.compile(pat).findall(data)

for i in range(0,len(allurl)):

    try:

        print("第"+str(i)+"次爬取")

        thisurl=allurl[i]

        file="E:/py/csdn/"+str(i)+".html"

        urllib.request.urlretrieve(thisurl,file)

        print("----成功----")

    except urllib.error.URLError as e:

        if hasattr(e,"code"):

            print(e.code)

        if hasattr(e,"reason"):

            print(e.reason)