htmlparsertest.java

解析html文件与解析excel文件的方法

package demo;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.ArrayList;
import java.util.List;

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.HasChildFilter;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.CompositeTag;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.TableTag;
import org.htmlparser.tags.TitleTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
import org.htmlparser.visitors.ObjectFindingVisitor;

public class HTMLParserTest {
	public static void main(String args[]) throws Exception
	 {
	  String path = "D:\\ticket\\demo_ liyidan_report.htm";
	  StringBuffer sbStr = new StringBuffer();
	  BufferedReader reader  = new BufferedReader(new FileReader(new File(path)));
	  String temp = "";
	  while((temp=reader.readLine())!=null)
	  {
	   sbStr.append(temp);
	   sbStr.append("\r\n");
	  }
	  reader.close();
	  String result = sbStr.toString();
	  //System.out.println(sbStr);
	   //readAll(result);
	   //readTextAndLink(result);
	    // readByHtml(result);
	    // readTextAndTitle(result);
	  //readTable(result,"sessionline");
	  test7(result);
	 }
	 
	private static void test6(String resource) throws Exception {
		Parser myParser = new Parser(resource);
		myParser.setEncoding("GBK");
		String filtertable = "table";
		NodeFilter textfilter = new TagNameFilter(filtertable);
		NodeList textnodeList = myParser.extractAllNodesThatMatch(textfilter);
		for(int i=0;i<textnodeList.size();i++){
			TableTag tabletag = (TableTag) textnodeList.elementAt(i);
			Node node=tabletag.getFirstChild();
			NodeFilter childfilter=new HasChildFilter();
			String line=tabletag.toHtml();
			int linkstart=line.indexOf("href=");
			int linkend=line.indexOf("target");
			String link=line.substring(linkstart+6,linkend-2);
			System.out.println(line);
			System.out.println("==============");
			System.out.println(link);
			System.out.println("==============");
		}
	}
	
	private static void test7(String result){
		try {
			   Parser parser = new Parser(result);
			   parser.setEncoding("gbk");
			   TagNameFilter filter = new TagNameFilter("tr");
			   // width='600' border='0' align='center' cellpadding='0'
			   // cellspacing='1' bgcolor='336699'>
			   HasAttributeFilter tableAttribute2 = new HasAttributeFilter("class", "sessionline");
			  // HasAttributeFilter tableAttribute3 = new HasAttributeFilter("bgcolor", "#FFFFFF");
			   AndFilter anFilter = new AndFilter();
			   anFilter.setPredicates(new NodeFilter[] { filter, tableAttribute2});

			   NodeList nl = parser.extractAllNodesThatMatch(anFilter);
			   for (int i = 0; i < nl.size(); i++) {
				    NodeList nl2 = new NodeList();
				    nl.elementAt(i).collectInto(nl2, new TagNameFilter("td"));
				    String nl2_1 = nl2.elementAt(1).toPlainTextString();
				    String nl2_2 = nl2.elementAt(2).toPlainTextString();
				    String nl2_3 = nl2.elementAt(3).toPlainTextString();
				    String nl2_4 = nl2.elementAt(4).toPlainTextString();
				    // Fund fund = new Fund();
				     //fund.setName(nl2.elementAt(1).toPlainTextString());
				     //fund.setCode(nl2.elementAt(2).toPlainTextString());
				     //fund.setCompany(nl2.elementAt(5).toPlainTextString());
				     //fund.setManager(nl2.elementAt(6).toPlainTextString());
				     //fund.setScale(new BigDecimal(nl2.elementAt(7).toPlainTextString()));
				    // fundDao.persistFund(fund);
				    System.out.println(nl2_1+"     "+nl2_2+"    "+nl2_3+"    "+nl2_4);
			   }
			  } catch (ParserException e) {
				  e.printStackTrace();
			  }
	}
	
	 //鎸夐〉闈㈡柟寮忓