获取免费ip_存入excel_用了线程池_封装清晰

from lxml import etree
import time
import requests
from multiprocessing.pool import ThreadPool   #线程池
import xlwt

class Visit():   #访问代理ip

    def __init__(self):
        self.i = 0
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
        }
        self.f = xlwt.Workbook(encoding='utf-8')
        self.sheet1 = self.f.add_sheet(u'sheet1', cell_overwrite_ok=True)

    def get_html(self,url):  # 请求页面

        try:
            res = requests.get(url, headers=self.headers)
            res.encoding = res.apparent_encoding
            if res.status_code == 200:
                html = res.text
                return html
            else:
                time.sleep(0.1)
                return self.get_html(url)
        except Exception as e:  # except BaseException  这个也可以     e是打印出错误的原因
            print("问题是", e)

    def parse(self,response): #解析
        content = etree.HTML(response)  # 标准的使用 xpath套路
        list_tr = content.xpath("//table[@class=\"layui-table\"]/tbody//tr")
        for tr in list_tr:
            li_ip = str(tr.xpath("./td[1]/text()")[0]).replace("\t", '').replace("\n", '')
            li_port = str(tr.xpath("./td[2]/text()")[0]).replace("\t", '').replace("\n", '')
            #print(li_ip, li_port)
            text_ip = "http://{}:{}".format(li_ip,li_port)
            self.Test_ip(text_ip)
    def Test_ip(self,text_ip):
        try:
            requests.get('http://wenshu.court.gov.cn/', proxies={"http": text_ip})  #这个地方也可以写res.status_code == 200: 作为判断
        except:
            print('代理链接失败connect failed',text_ip)
        else:
            print('代理成功success',text_ip)
            self.excel_write(text_ip)


    def excel_write(self,text_ip):

        self.sheet1.write(self.i, 0, text_ip)
        self.i += 1
        self.f.save(r'e:\get_ip.xls')  # 保存
if __name__ == '__main__':
    url = "http://www.89ip.cn/"
    pool = ThreadPool(16)#实现一个线程池 ，参数是线程的数量, 这里就是两个线程等待调用
    a = Visit()
    a.parse(a.get_html(url))  # 解析详细页面， 调用requests请求
    for i in range(2,11):
        next_page = "http://www.89ip.cn/index_{}.html".format(i)
        a.parse(a.get_html(next_page))
        pool.apply_async(a.parse(a.get_html(next_page)))  # 这个线程池传参很精髓
    pool.close()  # 关闭线程池， 不在提交任务，
    pool.join()  # 等待线程池里面的任务 运行完毕