欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

使用动态代理IP让爬虫效率提高N倍 博客分类: Java 动态代理IP数据抓取数据爬虫IP被封禁换IP抓数据 

程序员文章站 2024-02-22 08:54:52
...
package com.goubanjia.test;

import java.io.BufferedInputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.util.ArrayList;
import java.util.List;

import org.jsoup.Jsoup;

import com.gargoylesoftware.htmlunit.BrowserVersion;
import com.gargoylesoftware.htmlunit.ProxyConfig;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlPage;

public class TestDynamicIp {
	public static List ipList = new ArrayList();
	public static boolean gameOver = false;
	public static void main(String[] args) {
		long fetchIpSeconds = 5;
		int threadNum = 10;
		int testTime = 3;
		String order = "这里换成你的订单号,百度全网代理IP获取";
		System.out.println(">>>>>>>>>>>>>>全网代理动态IP测试开始<<<<<<<<<<<<<<");
		System.out.println("***************");
		System.out.println("接口返回IP为国内各地区,每次最多返回10个");
		System.out.println("提取IP间隔 " + fetchIpSeconds + " 秒 ");
		System.out.println("开启爬虫线程 " + threadNum);
		System.out.println("爬虫目标网址  http://1212.ip138.com/ic.asp");
		System.out.println("测试次数 3 ");
		System.out.println("***************\n");
		TestDynamicIp tester = new TestDynamicIp();
		new Thread(tester.new GetIP(fetchIpSeconds * 1000, testTime, order)).start();
		for (int i = 0; i < threadNum; i++) {
			tester.new Ip138Tester(100).start();
		}
		while(!gameOver){
			try {
				Thread.sleep(100);
			} catch (InterruptedException e) {
				e.printStackTrace();
			}
		}
		System.out.println(">>>>>>>>>>>>>>全网代理动态IP测试结束<<<<<<<<<<<<<<");
		System.exit(0);
	}
    
	// 抓取IP138,检测IP
	public class Ip138Tester extends Thread{
		@Override
		public void run() {
			while(!gameOver){
				webParseHtml("http://1212.ip138.com/ic.asp");
				try {
					Thread.sleep(sleepMs);
				} catch (InterruptedException e) {
					e.printStackTrace();
				}
			}
		}
		
		long sleepMs = 200;
		public Ip138Tester(long sleepMs) {
			this.sleepMs = sleepMs;
		}
		public String webParseHtml(String parentUrl) {
			String html = "";
			WebClient client = new WebClient();
			try {
				client.getOptions().setThrowExceptionOnFailingStatusCode(false);
				client.getOptions().setJavaScriptEnabled(false);
				client.getOptions().setCssEnabled(false);
				client.getOptions().setThrowExceptionOnScriptError(false);
				client.getOptions().setTimeout(10000); // 10s超时
				client.getOptions().setAppletEnabled(true);
				client.getOptions().setGeolocationEnabled(true);
				client.getOptions().setRedirectEnabled(true);
				
				String ipport = getAProxy();
				if (ipport != null) {
					ProxyConfig proxyConfig = new ProxyConfig(ipport.split(":")[0], Integer.parseInt(ipport.split(":")[1]));
					client.getOptions().setProxyConfig(proxyConfig);
				}else {
					System.out.print(".");
					return "";
				}
			
				HtmlPage page = client.getPage(parentUrl);
				html = page.asXml();
				
				if (html.length() > 0) {
					html = Jsoup.parse(html).select("center").first().text();
				}
				
				System.out.println(getName() + " 使用代理 " + ipport + "请求IP138返回:" + html);
				
			} catch (Exception e) {
				return webParseHtml(parentUrl);
			} finally {
				client.close();
			}
			return html;
		}
		
	    private String getAProxy() {
	    	if (ipList.size() > 0) {
	    		String ip = ipList.get((int)(Math.random() * ipList.size()));
	    		return ip ;
			}
			return null;
		}
	}
	
	// 定时获取动态IP
	public class GetIP implements Runnable{
		long sleepMs = 1000;
		int maxTime = 3;
		String order = "";
		
		public GetIP(long sleepMs, int maxTime, String order) {
			this.sleepMs = sleepMs;
			this.maxTime = maxTime;
			this.order = order;
		}
		
		@Override
		public void run() {
			long getIpTime = 0;
			int time = 1;
			while(!gameOver){
				if(time >= 4){
					gameOver = true;
					break;
				}
				try {
					java.net.URL url = new java.net.URL("http://dynamic.goubanjia.com/dynamic/get/" + order + ".html?ttl");
			    	HttpURLConnection connection = (HttpURLConnection)url.openConnection();
			    	connection.setConnectTimeout(3000);
			    	connection = (HttpURLConnection)url.openConnection();
			    	
			        InputStream raw = connection.getInputStream();  
			        InputStream in = new BufferedInputStream(raw);  
			        byte[] data = new byte[in.available()];
			        int bytesRead = 0;  
			        int offset = 0;  
			        while(offset < data.length) {  
			            bytesRead = in.read(data, offset, data.length - offset);  
			            if(bytesRead == -1) {  
			                break;  
			            }  
			            offset += bytesRead;  
			        }  
			        in.close();  
			        raw.close();
					String[] res = new String(data, "UTF-8").split("\n");
					List ipList = new ArrayList();
					for (String ip : res) {
						try {
							String[] parts = ip.split(",");
							if (Integer.parseInt(parts[1]) > 0) {
								ipList.add(parts[0]);
							}
						} catch (Exception e) {
						}
					}
					if (ipList.size() > 0) {
						TestDynamicIp.ipList = ipList;
						System.out.println("第" + ++getIpTime + "次获取动态IP " + ipList.size() + " 个");
						time += 1;
					}
				} catch (Exception e) {
					e.printStackTrace();
					System.err.println(">>>>>>>>>>>>>>获取IP出错");
				}
				try {
					Thread.sleep(sleepMs);
				} catch (InterruptedException e) {
					e.printStackTrace();
				}
			}
		}
	}
}

 

   完整项目包下载地址:http://www.goubanjia.com/download/test-dynamic-ip.zip

 

   使用动态代理IP,完全避免了被封IP的风险,爬虫效率直接提升了3倍以上。

 

   请填写全网代理IP订单号,填写之后才可以提取到IP哦