htmlparser visitor用法 自定义标签 大文件快速读取，并分析，彻底解决 outofmemery错误

 

package htmlparser;

import org.htmlparser.tags.CompositeTag;

public class CnTag extends CompositeTag {
	private  String[] mIds;

	private  String[] mEndTagEnders;

	public CnTag(String mi, String me) {
		this.mIds=new String[]{mi};
		this.mEndTagEnders=new String[]{me};
	}

	public String[] getIds() {
		return mIds;
	}

	public String[] getEndTagEnders() {
		return mEndTagEnders;
	}

}

 

visitor提取html中的自定义标签内容，在大的html文件提取时，extractAllNodesThatMatch这个会显示内存溢出，因此采用以下的方法

 

 

 

package htmlparser;

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.PrototypicalNodeFactory;
import org.htmlparser.visitors.ObjectFindingVisitor;

public class TestJDBC {
	public static String content = "";// content保存文件内容，

	public static void main(String[] args) throws IOException,Exception {
		File file = new File("c:/NC_003075.html");//new File("c:/NC_003075.html");
		String txt="c:/DQ063642.html";
txt=loadAFileToStringDE2(file);

		extractText(txt);
	}

public static String extractText(String inputHtml) throws Exception {
		StringBuffer text = new StringBuffer();
		Parser   parser   =   new   Parser(inputHtml);
		
		
		PrototypicalNodeFactory p = new PrototypicalNodeFactory();
		p.registerTag(new CnTag("INSDSeq_primary-accession","INSDSeq_primary-accession"));
		parser.setNodeFactory(p);
		ObjectFindingVisitor visitor = new ObjectFindingVisitor(CnTag.class);
		
		parser.visitAllNodesWith(visitor); 
		
		Node[] nodes = visitor.getTags();
		
		for (Node node : nodes) {
			System.out.println("***********************"
					+ node.toPlainTextString().trim());

		for (int i=0 ;i<nodes.length;i++){
			Node summaryNode = (Node)nodes[i];
			String   textInPage =summaryNode.toPlainTextString();  		    
	        System.out.println("!!!"+textInPage);   
		}
		
		return text.toString();
	}

 

读取文件，大型的文件，比如几十兆以上的

 

public static String loadAFileToStringDE2(File f) throws IOException {
		long beginTime = System.currentTimeMillis();
		InputStream is = null;
		String ret = null;
		try {
			is = new FileInputStream(f);
			long contentLength = f.length();
			byte[] ba = new byte[(int) contentLength];
			is.read(ba);
			ret = new String(ba);
		} finally {
			if (is != null) {
				try {
					is.close();
				} catch (Exception e) {
				}
			}
		}
		long endTime = System.currentTimeMillis();
		System.out.println("method 2:" + (endTime - beginTime) + "ms");
		return ret;
	}