requests基础爬取流程

Posted 2021-03-01 huahuawang

# 需求：爬取搜狗首页的页面数据
import requests
if __name__ == ‘__main__‘:
    # 1指定url
    url = ‘https://www.sogou.com/‘
    # 2发起请求
    res = requests.get(url=url) # get方法会返回一个响应对象
    # 3 获取响应数据.text返回的是字符串形式的响应数据
    page_text = res.text
    print(page_text)
    # 4 持久化存储
    fp =  open(‘./sogou.html‘,‘w‘,encoding=‘utf-8‘)
    fp.write(page_text)
    print(‘爬取数据成功‘)