Shop/src/util/HtmlParsePro.java

这里只显示每个文件的开头 60 行。登录后可以解锁完整代码。

微信扫码关注公众号，代码整理好后第一时间通知你。

package util;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.*;
import org.htmlparser.*;
import org.htmlparser.filters.*;
import org.htmlparser.tags.ImageTag;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.visitors.HtmlPage;

public class HtmlParsePro
{

    public HtmlParsePro()
    {
    }

    public String getUrlContent(String urlPath, String charType)
        throws Exception
    {
        URL url = new URL(urlPath);
        URLConnection conn = url.openConnection();
        conn.setDoOutput(true);
        InputStream inputStream = conn.getInputStream();
        InputStreamReader isr = new InputStreamReader(inputStream, charType);
        StringBuffer sb = new StringBuffer();
        BufferedReader in = new BufferedReader(isr);
        String inputLine;
        while((inputLine = in.readLine()) != null) 
        {
            if(inputLine != null && !"".equals(inputLine) && !"".equals(inputLine.trim()))
            {
                inputLine = inputLine.trim();
                sb.append(inputLine);
                sb.append("\n");
            }
        }
        return sb.toString();
    }

    public List getLinkUrl(String urlPath, String site, String charType)
    {
    	try{
        List temp;
        String result = getUrlContent(urlPath, charType);
        Parser parser = Parser.createParser(result, charType);
        NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
        NodeFilter imgFilter = new NodeClassFilter(ImageTag.class);
        NodeFilter frameFilter = new TagNameFilter("iframe");
        OrFilter lastFilter = new OrFilter();
        lastFilter.setPredicates(new NodeFilter[] {
            linkFilter, imgFilter, frameFilter
        });
        NodeList nodelist = parser.parse(lastFilter);
        Node nodes[] = nodelist.toNodeArray();
        String line = "";
        temp = new ArrayList();