<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>代理 on 庞玉栋个人博客</title><link>https://pangyd.com/tags/%E4%BB%A3%E7%90%86/</link><description>Recent content in 代理 on 庞玉栋个人博客</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Wed, 11 Dec 2019 10:22:35 +0800</lastBuildDate><atom:link href="https://pangyd.com/tags/%E4%BB%A3%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>猎聘网站爬虫（代理池+邮件提醒+写入flume服务端）</title><link>https://pangyd.com/post/225-flume/</link><pubDate>Thu, 31 Oct 2019 11:44:38 +0800</pubDate><guid>https://pangyd.com/post/225-flume/</guid><description>&lt;pre lay-lang="Python" class="layui-code" skin="notepad"># coding=utf-8
import requests
import re
import time
import json
from demo2 import soct
import pymysql
import random
import smtplib
import email.mime.multipart
import email.mime.text
&lt;p>import socket&lt;/p>class Spider():

 def __init__(self):
 self.ls = []
 self.count = 0
 self.USER_AGENTS = [
 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
 "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
 "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
 "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
 "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
 "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
 "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
 "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
 "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
 "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
 "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
 "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
 ]

 def emial(self):
 try:
 subject = 'python执行日志'
 content = "可用{}个代理ip，所有url已经爬取完毕".format(len(self.ls))
 msg = email.mime.multipart.MIMEMultipart()
&lt;p> msg['from'] = '******@qq.com'&lt;/p></description></item></channel></rss>