requests网页采集器

最新推荐文章于 2024-09-06 23:41:09 发布

YLFHFX

最新推荐文章于 2024-09-06 23:41:09 发布

阅读量101

点赞数

文章标签： html python 爬虫

本文链接：https://blog.csdn.net/YLFHFX/article/details/128435965

版权

import requests
if __name__ == "__main__":
    url = "http://sogou.com/web"
    # 处理url参数:封装到字典中
    kw = input("输入一个参数")
    params = {
        "query": kw
    }

    #user-agent伪装
    headers = {
        "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.0.12022 SLBChan/30",
        "cookie":"IPLOC=CN5200; SUID=F4DABD75492CA20A0000000063A801DC; SUV=1671954909692186; ABTEST=7|1671954910|v17; SNUID=785630F88D887C2EDB78C2448D8D3C14; sst0=104; ld=lZllllllll20$l4OlllllpnoxRylllllNbTzdlllllUlllllpylll5@@@@@@@@@@",

    }

    #对指定的url发起请求
    resp = requests.get(url, params=params,headers=headers)

    print(resp.status_code)

    page_text = resp.text
    file_name=  kw+".html"
    with open(file_name,"w",encoding="utf-8") as fp:
        fp.write(page_text)
    print("保存成功")