httpclient+HTMLParser 的应用(多线程版)

今天利用多线程将《httpclient+HTMLParser的应用 》中的google翻译和爱词霸翻译合并起来，代码如下：

1.multithreadDict.java

package MultiTread; import java.util.Scanner; public class multithreadDict { public static void main(String[] args) throws InterruptedException { System.out.print("Input the word > "); Scanner s = new Scanner(System.in); String input= s.nextLine(); GoogleDict google=new GoogleDict(input); google.start(); //google.sleep(2000); IcibaDict iciba=new IcibaDict(input); iciba.start(); //iciba.sleep(4000); } }

注：本来我想先显示google翻译的结果，后显示爱词霸翻译的结果，但即使使用sleep函数也很难保证这一点。

      Java线程调度是Java多线程的核心，只有良好的调度，才能充分发挥系统的性能，提高程序的执行效率。

      这里要明确的一点，不管程序员怎么编写调度，只能最大限度的影响线程执行的次序，而不能做到精准控制。

     线程休眠是使线程让出CPU的最简单的做法之一，线程休眠时候，会将CPU资源交给其他线程，以便能轮换执行，当休眠一定时间后，线程会 苏醒，进入准备状态等待执行。

     线程休眠的方法是Thread.sleep(long millis) 和Thread.sleep(long millis, int nanos) ，均为静态方法。简单说，哪个线程调用sleep，就休眠哪个线程。

2.GoogleDict.java

package MultiTread; import java.io.File; import java.io.FileWriter; import java.net.URI; import org.apache.http.HttpEntity; import org.apache.http.HttpResponse; import org.apache.http.client.HttpClient; import org.apache.http.client.methods.HttpGet; import org.apache.http.client.utils.URIUtils; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.util.EntityUtils; import org.htmlparser.Node; import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.filters.OrFilter; import org.htmlparser.filters.TagNameFilter; import org.htmlparser.util.NodeList; import org.htmlparser.visitors.TextExtractingVisitor; class GoogleDict extends Thread { private String searchterm=null; public GoogleDict(String input) { this.searchterm=input; } public void run() { String text=null; //http://www.google.com/dictionary?source=translation&hl=zh-CN&q=computer&langpair=en|zh-CN try { HttpClient httpclient = new DefaultHttpClient(); String searchstring = "source=translation&hl=zh-CN&q=" + searchterm + "&langpair=en%7Czh-CN"; URI uri=URIUtils.createURI("http", "www.google.com", -1, "/dictionary", searchstring, null); HttpGet httpget = new HttpGet(uri); HttpResponse response = httpclient.execute(httpget); HttpEntity entity = response.getEntity(); if (entity != null) { Parser parser = new Parser(EntityUtils.toString(entity)); parser.setEncoding("gb2312"); //NodeFilter filter_tab_content =new OrFilter( new TagNameFilter("div"),new TagNameFilter("span")); NodeFilter filter_tab_content=new TagNameFilter("div"); //NodeFilter filter_tab_content=new TagNameFilter("span"); NodeList nodelist_tab_content = parser.parse(filter_tab_content); int length = nodelist_tab_content.size(); if(searchterm.getBytes().length==searchterm.length()) { for (int i = 10; i < length-3; i++) { Node node_tab_content = nodelist_tab_content.elementAt(i); Parser parser_tab_content = new Parser(node_tab_content .toHtml()); TextExtractingVisitor visitor_tab_content = new TextExtractingVisitor(); parser_tab_content.visitAllNodesWith(visitor_tab_content); text = text+"/n"+visitor_tab_content.getExtractedText().trim(); } } else { for (int i = 8; i < length-3; i++) { Node node_tab_content = nodelist_tab_content.elementAt(i); Parser parser_tab_content = new Parser(node_tab_content .toHtml()); TextExtractingVisitor visitor_tab_content = new TextExtractingVisitor(); parser_tab_content.visitAllNodesWith(visitor_tab_content); text = text+"/n"+visitor_tab_content.getExtractedText().trim(); } } text=text.replaceAll("相关搜索", "相关搜索:"); text=text.replaceAll("null", ""); text=text.replaceAll("/n/n", "/n"); text=text.replaceAll("/n/n", "/n"); text=text.replaceAll("/n/n", "/n"); System.out.println("-----------------------------------------" + "谷歌翻译-------------------------------------------"); System.out.println(uri); System.out.println(text); File f = new File("D://study/Java/GoogleDict/" + searchterm + ".txt"); FileWriter fw = new FileWriter(f); fw.write(text); fw.flush(); fw.close(); } } catch(Exception e) { e.printStackTrace(); } } }

注：在使用HTMLParser处理google翻译返回的结果时，由于同时存在<span>...</span>,<div>...</div>,<span><div>...</div></span>三种标签，导致处理比较困难，个人对HTMLParser库也不是很熟悉，所以最终所得结果并不是很满意。

3.IcibaDict.java

package MultiTread; import java.io.File; import java.io.FileWriter; import org.apache.http.HttpEntity; import org.apache.http.HttpResponse; import org.apache.http.client.HttpClient; import org.apache.http.client.methods.HttpGet; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.util.EntityUtils; import org.htmlparser.Node; 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; import org.htmlparser.visitors.TextExtractingVisitor; class IcibaDict extends Thread { private String searchterm=null; public IcibaDict(String input) { this.searchterm=input; } public void run() { String text=null,webContent=null; try { HttpClient httpclient = new DefaultHttpClient(); String searchstring = "http://www.iciba.com/" + searchterm + "/"; HttpGet httpget = new HttpGet(searchstring); HttpResponse response = httpclient.execute(httpget); HttpEntity entity = response.getEntity(); if (entity != null) { String content=EntityUtils.toString(entity); content=content.replaceAll("<a href", " <a href"); Parser parser = new Parser(content); parser.setEncoding("gb2312"); NodeFilter filter_tab_content = new AndFilter(new TagNameFilter( "div"), new HasAttributeFilter("class", "tab_content")); NodeList nodelist_tab_content = parser.parse(filter_tab_content); int length = nodelist_tab_content.size(); for (int i = 0; i < length; i++) { Node node_tab_content = nodelist_tab_content.elementAt(i); Parser parser_tab_content = new Parser(node_tab_content .toHtml()); TextExtractingVisitor visitor_tab_content = new TextExtractingVisitor(); parser_tab_content.visitAllNodesWith(visitor_tab_content); text = text+"/n"+visitor_tab_content.getExtractedText().trim(); } parser.reset(); NodeFilter filter_web = new AndFilter(new TagNameFilter( "div"), new HasAttributeFilter("class", "content_block")); NodeList nodelist_web = parser.parse(filter_web); Node node_web = nodelist_web.elementAt(0); if(node_web!=null) { Parser parser_web = new Parser(node_web.toHtml()); TextExtractingVisitor visitor_web = new TextExtractingVisitor(); parser_web.visitAllNodesWith(visitor_web); webContent=visitor_web.getExtractedText().trim(); } text=text+webContent; text=text.replaceAll(" ", ""); text=text.replaceAll(" ", ""); text=text.replaceAll(" ", "/n"); text=text.replaceAll("/n/n/n", "/n"); text=text.replaceAll("/n/n", "/n"); text=text.replaceAll("/n/n", "/n"); text=text.replaceAll(" ", ""); text=text.replace("null", ""); text=text.replace("相关搜索", ""); text=text.replace("句库",""); text=text.replace("韦氏词典",""); text=text.replace("Dictionary", ""); System.out.println("*************************************" + "爱词霸翻译*************************************"); System.out.println(searchstring); System.out.println(text); File f = new File("D://study/Java/IcibaDict/" + searchterm + ".txt"); FileWriter fw = new FileWriter(f); fw.write(text); fw.flush(); fw.close(); } } catch(Exception e) { e.printStackTrace(); } } }