displayallelements.java

HTML解析器是一个Java库

import net.htmlparser.jericho.*;
import java.util.*;
import java.io.*;
import java.net.*;

public class DisplayAllElements {
	public static void main(String[] args) throws Exception {
		String sourceUrlString="data/test.html";
		if (args.length==0)
		  System.err.println("Using default argument of \""+sourceUrlString+'"');
		else
			sourceUrlString=args[0];
		if (sourceUrlString.indexOf(':')==-1) sourceUrlString="file:"+sourceUrlString;
		MicrosoftTagTypes.register();
		PHPTagTypes.register();
		PHPTagTypes.PHP_SHORT.deregister(); // remove PHP short tags for this example otherwise they override processing instructions
		MasonTagTypes.register();
		Source source=new Source(new URL(sourceUrlString));
		List<Element> elementList=source.getAllElements();
		for (Element element : elementList) {
			System.out.println("-------------------------------------------------------------------------------");
			System.out.println(element.getDebugInfo());
			if (element.getAttributes()!=null) System.out.println("XHTML StartTag:\n"+element.getStartTag().tidy(true));
			System.out.println("Source text with content:\n"+element);
		}
		System.out.println(source.getCacheDebugInfo());
  }
}