python简单爬虫代理ip并写入xls案例

仅爬虫  某ip代理首页（如果需要爬虫第1，2...页，外加一个url循环）

import  requests
import xlwt
from bs4 import BeautifulSoup

header={'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.9',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Cookie':'channelid=0; sid=1639363412353498; _gcl_au=1.1.1713166161.1639364780; Hm_lvt_7ed65b1cc4b810e9fd37959c9bb51b31=1639364781; Hm_lpvt_7ed65b1cc4b810e9fd37959c9bb51b31=1639364781; _ga=GA1.2.2049648863.1639364781; _gid=GA1.2.709356791.1639364781; _gat=1',
'Host':'www.kuaidaili.com',
'Sec-Fetch-Mode':'navigate',
'Sec-Fetch-Site':'cross-site',
'Sec-Fetch-User':'?1',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}

req=requests.get('https://www.kuaidaili.com/free/',headers=header).text

soup =BeautifulSoup(req,'html.parser')
'''req表示被解析的html格式内容 html.parser表示解析的用的解释器'''
'''
<tr>
<td data-title="IP">000000</td>
<td data-title="PORT">57903</td>
<td data-title="匿名度">高匿名</td>
<td data-title="类型">HTTP</td>
<td data-title="位置">浙江省杭州市  电信</td>
<td data-title="响应速度">6秒</td>
<td data-title="最后验证时间">2021-12-12 21:31:01</td>
</tr>'''

workbook=xlwt.Workbook(encoding='ascii')
worksheet=workbook.add_sheet('cehi')
lis=['IP','PORT','匿名度','类型','位置','响应速度','最后验证时间']
for i in range(7):
    worksheet.write(0,i,lis[i])
a=1 #判断、控制换行插入
j=1
for i in soup.find_all('td'):
    if a%8==0:
        j+=1
        a=1
    worksheet.write(j,a-1,i.get_text())
    a += 1
workbook.save('文件名.xls') # 保存文件