Python Requests爬虫之求取关键词页面详解

import requestsif __name__=='__main__':    #step 1:搜索Url    url='https://123.sogou.com/'    #step 2:发起请求    #get方法会返回一个响应对象    response=requests.get(url=url)    #step 3:获取响应数据,text返回的是字符串形式的响应数据    page_text=response.text    print(page_text)    #step 4:持久化存储    with open('./sogou.html','w',encoding='utf-8') as fp:        fp.write(page_text)    print("爬取数据结束")import requests
if __name__=='__main__':
    #step 1:搜索Url
    url='https://123.sogou.com/'
    #step 2:发起请求
    #get方法会返回一个响应对象
    response=requests.get(url=url)
    #step 3:获取响应数据,text返回的是字符串形式的响应数据
    page_text=response.text
    print(page_text)
    #step 4:持久化存储
    with open('./sogou.html','w',encoding='utf-8') as fp:
        fp.write(page_text)
    print("爬取数据结束")

import requests
if __name__=='__main__':
    #UA伪装:将对应的User-Agent封装到一个字典中
    headers={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.9 Safari/537.36'
    }
    url='https://www.sogou.com/sie?'
    #处理url携带的参数:封装到字典中
    kw=input('enter a word:')
    param={
        'query':kw
    }
    #对指定的url发起的请求对应的url是携带参数的,并且请求过程中处理了参数
    response=requests.get(url=url,params=param,headers=headers)#headers是伪装 params输入关键词

    page_text=response.text#以文本的形式输出
    fileName=kw+'.html'#存储为网页形式
    with open(fileName,'w+',encoding='utf-8') as fp:
        fp.write(page_text)#写入fp
    print(fileName,"保存成功！！")