网易微博抓取信息抓取 程序代码

网易微博抓取信息抓取 程序代码 主函数: package com; import java.io.BufferedWriter; import java.io.File; import java.io.FileWriter; import java.net.HttpURLConnection; import java.net.URL; import java.util.Calendar; import java.util.TimerTask; import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.filters.AndFilter; import org.htmlparser.filters.HasAttributeFilter; import org.htmlparser.filters.TagNameFilter; import org.htmlparser.util.NodeList; public class SohuTask extends TimerTask { public void run() { try { sohuParser(); Thread.sleep(10); } catch (InterruptedException e){ e.printStackTrace(); } } public void sohuParser(){ try{ String url = " method=click&f=ws_gs_id"; //BufferedReader in1=new BufferedReader(new InputStreamReader(System.in)); //url=in1.readLine(); Parser parser = new Parser( (HttpURLConnection) (new URL(url)).openConnection() ); Parser parser1= new Parser( (HttpURLConnection) (new URL(url)).openConnection() ); // 这里是控制测试的局部，后面的例子修改的就是这个地方 。 NodeFilter tag =new TagNameFilter("p"); NodeFilter tag1 =new TagNameFilter("a"); NodeFilter filter = new HasAttributeFilter ("class","message"); NodeFilter filter1=new HasAttributeFilter ("class","time"); NodeFilter last =new AndFilter(tag,filter); NodeFilter last1 =new AndFilter(tag1,filter1); NodeList nodes = parser.extractAllNodesThatMatch (last); NodeList nodes1 = parser1.extractAllNodesThatMatch (last1); if(nodes!=null) { for (int i = 0; i