爬取代理ip并验证可用性，写入csv文件

1.使用xpath提取数据
2.使用telnet验证代理是否可用
3.将可用数据追加写入csv文件，ip地址、端口各占一列
代码如下：

#!/usr/bin/python3.7.3
# coding:utf-8
# Author:cj
# contact: ingchang@qq.com
# Time:2019/8/26
# desc:爬取代理http://www.89ip.cn，验证可用，保存本地文件

import requests
from lxml import etree
import csv
import telnetlib


def pagesproxies():
    # 提取第1到10页数据
    urllist = [f'http://www.89ip.cn/index_{page}.html' for page in range(1,11)]
    pages = {}
    for list in urllist:
        onepage = getproxies(list)
        pages.update(onepage)
    return pages


def getproxies(url):
    # 提取一页数据
    ip_strip = []
    port_strip = []
    r = requests.get(url=url)
    html = etree.HTML(r.text)
    ip = html.xpath("//tr/td[1]/text()")
    port = html.xpath("//tr/td[2]/text()")
    # 处理提取字段的空格等符号
    for i in ip:
        i = i.strip()
        ip_strip.append(i)

    for j in port:
        j = j.strip()
        port_strip.append(j)
    # 将两个列表生成对应的字典
    return dict(zip(ip_strip,port_strip))


def telnet(proxiesdata):
    # 检查是否可用，将可用代理返回
    num = 0
    newdict = {}
    for key, value in proxiesdata.items():
        try:
            telnetlib.Telnet(host=key, port=value, timeout=3.0)
        except:
            print('%s:%s connect failure' % (key,value))
        else:
            print('%s:%s connect success' % (key,value))
            num += 1
            newdict[key] = value
    print("可用代理共%s个" % num)
    return newdict


def download(proxiescheckeddata):
    try:
        file_path = r"C:\\Users\\cj\\Desktop\\newip.csv"
        with open(file_path,"a",newline='') as f:
            writer = csv.writer(f)
            for key,value in proxiescheckeddata.items():
                writer.writerow([key,value])
    except Exception:
         print("error!")


if __name__ == '__main__':
    test = pagesproxies()
    check = telnet(test)
    download(check)