filtercontent.java

本程序是专门用于从网页上自动收集cmi,cnki上的被引文献的数据

package cn.ac.cintcm.spider;

import org.htmlparser.NodeFilter;
import org.htmlparser.filters.AndFilter;
import org.htmlparser.filters.HasAttributeFilter;
import org.htmlparser.filters.TagNameFilter;

public class FilterContent {

	public NodeFilter[] getFileter() {
        TagNameFilter filter0 = new TagNameFilter ();
        filter0.setName ("INPUT");
        HasAttributeFilter filter1 = new HasAttributeFilter ();
        filter1.setAttributeName ("type");
        filter1.setAttributeValue ("hidden");
        NodeFilter[] array0 = new NodeFilter[2];
        array0[0] = filter0;
        array0[1] = filter1;
        AndFilter filter2 = new AndFilter ();
        filter2.setPredicates (array0);
        NodeFilter[] array1 = new NodeFilter[1];
        array1[0] = filter2;
        return array1;
	}
}