工具:python3
本文主要介绍用urllib去抓取网页。
去看看百度首页
from urllib import request import chardet if __name__ == "__main__": headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"} url="https://www.baidu.com/" req=request.Request(url,headers=headers) response = request.urlopen(req) html = response.read() charset = chardet.detect(html) print("chardet去查看默认编码信息:%s" % charset) print("响应码:%s" % response.getcode()) print(html)
结果