httpclient+HTMLParser的应用

最新推荐文章于 2018-09-09 01:33:00 发布

原创最新推荐文章于 2018-09-09 01:33:00 发布 · 874 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#string #filter #null #dictionary #web #class

Programming 专栏收录该内容

10 篇文章

订阅专栏

本文介绍了一个使用Java编写的简单在线翻译工具，该工具利用HTTPClient调用Google翻译和爱词霸的服务来实现英文到中文的翻译功能。文章详细展示了如何构建HTTP请求、解析HTML响应并提取翻译结果。

使用httpclient调用google翻译以及爱词霸翻译，并使用HTMLParser对返回的结果进行处理，以此实现一个简单的在线翻译小程序，目前还没通过多线程编程合并两个翻译工具。

------------------------------------------------------------------------调用google翻译----------------------------------------------------------------------

import java.io.File; import java.io.FileWriter; import java.io.IOException; import java.net.URI; import java.net.URISyntaxException; import java.util.Scanner; import org.apache.http.HttpEntity; import org.apache.http.HttpResponse; import org.apache.http.ParseException; import org.apache.http.client.ClientProtocolException; 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.util.ParserException; import org.htmlparser.visitors.TextExtractingVisitor; public class GoogleDict { public static void main(String[] args) throws ClientProtocolException, IOException, ParserException, ParseException, URISyntaxException { System.out.print("Input the word > "); Scanner s = new Scanner(System.in); String searchterm = s.nextLine(); String text=null; //http://www.google.com/dictionary?source=translation&hl=zh-CN&q=computer&langpair=en|zh-CN 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); System.out.println(uri+"/n"); 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")); 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+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+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"); System.out.println(text); File f = new File("D://study/Java/GoogleDict/" + searchterm + ".txt"); FileWriter fw = new FileWriter(f, true); fw.write(text); fw.flush(); fw.close(); } } }

--------------------------------------------------------------------------调用爱词霸翻译---------------------------------------------------------------------

import java.io.File; import java.io.FileWriter; import java.io.IOException; import java.util.Scanner; import org.apache.http.HttpEntity; import org.apache.http.HttpResponse; import org.apache.http.ParseException; import org.apache.http.client.ClientProtocolException; 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.util.ParserException; import org.htmlparser.visitors.TextExtractingVisitor; public class IcibaDict { public static void main(String[] urgs) throws ClientProtocolException, IOException, ParserException, ParseException { System.out.print("Input the word : "); Scanner s = new Scanner(System.in); String searchterm = s.nextLine(); String text=null,webContent=null; 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(); //System.out.println(text); //System.out.println("****************************************"); } 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", "/n"); text=text.replaceAll("/n/n/n", "/n"); 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(text); File f = new File("D://study/Java/IcibaDict/" + searchterm + ".txt"); FileWriter fw = new FileWriter(f, true); fw.write(text); fw.flush(); fw.close(); } } }