java 自定义html模板 java htmlparser

Htmlparser一个分析html内容的很好用的工具。

htmlparser是一个纯的java写的html解析的库，它不依赖于其它的java库文件，主要用于改造或提取html。

它能超高速解析html，而且不会出错。现在htmlparser最新版本为2.0。

毫不夸张地说，htmlparser就是目前最好的html解析和分析的工具。

无论你是想抓取网页数据还是改造html的内容，用了htmlparser绝对会忍不住称赞。

附上一点儿代码，留个纪念。(⊙_⊙)

package home.study.htmlparser.main;

import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.HasChildFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.TextExtractingVisitor;

public class HtmlParserStudy
{
    private static String URL_ADDRESS = "http://localhost:8080/htmlparsertest/HTMLParserTester.html";

    public static void main(String[] args)
    {
        try {
            Parser parser = createParser();
            getEverythingInTags(parser);
            getNodeInformation(parser);
            getNodeInfoByFilter(parser);
        } catch (ParserException e) {
            e.printStackTrace();
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * Normal way to get a parser
     * 
     * @return parser
     * @throws ParserException
     * @throws MalformedURLException
     * @throws IOException
     */
    public static Parser createParser() throws ParserException, MalformedURLException, IOException
    {
        Parser parser = new Parser((HttpURLConnection) (new URL(URL_ADDRESS)).openConnection());
        return parser;
    }

    /**
     * The normal way to visit the content in page
     * 
     * @param parser
     * @throws ParserException
     */
    public static void getEverythingInTags(Parser parser) throws ParserException
    {
        // create a visitor
        TextExtractingVisitor visitor = new TextExtractingVisitor();
        // visit all the nodes in the parser given html page
        // there are several kinds of NodeVisitors
        parser.visitAllNodesWith(visitor);
        // get the text inside the tags
        String textInPage = visitor.getExtractedText();
        System.out.println(textInPage);
    }

    /**
     * Get the node then use it
     * 
     * @param parser
     * @throws ParserException
     */
    public static void getNodeInformation(Parser parser) throws ParserException
    {
        NodeList nodesHaveChildren = new NodeList();
        while (parser.elements().hasMoreNodes()) {
            Node currentNode = parser.elements().nextNode();
            NodeFilter aFilter = new TagNameFilter("a");
            NodeFilter hasChild = new HasChildFilter(aFilter);
            currentNode.collectInto(nodesHaveChildren, hasChild);
        }
        System.out.println(nodesHaveChildren.toHtml());
    }

    /**
     * NodeFilter contains AndFilter, OrFilter, CssSelectorNodeFilter,
     * HasAttributeFilter, HasChildFilter, HasParentFilter, HasSiblingFilter,
     * TagNameFilter and so on
     * 
     * @param parser
     * @throws ParserException
     */
    public static void getNodeInfoByFilter(Parser parser) throws ParserException
    {
        TagNameFilter trTag = new TagNameFilter("tr");
        NodeList trNodeList = parser.extractAllNodesThatMatch(trTag);
        for (int i = 0; i < trNodeList.size(); i++) {
            System.out.println(i + " node :");
            System.out.println(trNodeList.elementAt(i).toHtml());
        }
    }
}