_get

get原理

• 拼接 url（-->伪装请求头）
• 传递 req
• 结果 response

作业

• 爬取百度贴吧某html源码

from urllib import request
from urllib.parse import urlencode
from fake_useragent import UserAgent


def beauty_girl():
    try:
        browser = UserAgent()
        req_header = {
            'User-Agent': browser.random,
        }
        while True:
            print('正在下载...')
            url = 'https://tieba.baidu.com/f?'

            words = {
                'kw': '美女吧',
                'pn':i*50,
            }
            parmas_str = urlencode(words)
            full_url = url + parmas_str
            #请求头  响应
            req = request.Request(url=full_url,headers=req_header)
            response = request.urlopen(req)
            #文件名  内容
            filename = words['kw']+str(i+1)+'页.html'
            html_str = response.read().decode('utf-8')
            #添加至文件
            with open('./html/'+filename,'w') as file:
                print('正在写入...')
                file.write(html_str)
    except:
        print('已结束')

if __name__ =='__main__':
    beauty_girl()