如何改

Question

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.ImageTag;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class Catenate {
public static void main(String[] args) throws Exception {
String url = "http://www.bradfordexchange.com/";
extracLinks(url);
}

// 获取一个网页上所有的链接和图片链接
@SuppressWarnings("serial")
public static void extracLinks(String url) {
    try {
        Parser parser = new Parser(url);
        parser.setEncoding("utf-8");
        // 过滤 <frame> 标签的 filter，用来提取 frame 标签里的 src 属性所、表示的链接
        NodeFilter frameFilter = new NodeFilter() {
            public boolean accept(Node node) {
                if (node.getText().contains("category")
                 || node.getText().contains("mcategory")
                //|| node.getText().startsWith("frame src=")
                // || node.getText().startsWith("img src=")
                ) {
                    return true;
                } else {
                    return false;
                }
            }
        };
        // OrFilter 来设置过滤 <a> 标签，<img> 标签和 <frame> 标签，三个标签是 or 的关系
        OrFilter linkFilter = new OrFilter(new NodeClassFilter(
                LinkTag.class), frameFilter);
        // 得到所有经过过滤的标签
        NodeList list = parser.extractAllNodesThatMatch(linkFilter);
        for (int i = 0; i < list.size(); i++) {
            Node tag = list.elementAt(i);
            if (tag instanceof LinkTag)// <a> 标签
            {
                LinkTag link = (LinkTag) tag;
                String linkUrl = link.getLink();// url
                String text = link.getLinkText();// 链接文字
                System.out.println(linkUrl + "********" + text);
            } else if (tag instanceof ImageTag)// <img> 标签
            {
                ImageTag image = (ImageTag) list.elementAt(i);
                System.out.print(image.getImageURL() + "********");// 图片地址
                System.out.println(image.getText());// 图片文字
            } else// <frame> 标签
            {
                // 提取 frame 里 src 属性的链接如 <frame src="test.html"/>
                String frame = tag.getText();
                int start = frame.indexOf("src=");
                frame = frame.substring(start);
                int end = frame.indexOf(" ");
                if (end == -1)
                    end = frame.indexOf(">");
                frame = frame.substring(5, end - 1);
                System.out.println(frame);
            }
        }
    } catch (ParserException e) {
        e.printStackTrace();
    }
}

}

有运行结果就是最后报空指针异常

Answer 1

[code="java"]
import org.htmlparser.Node;

import org.htmlparser.NodeFilter;

import org.htmlparser.Parser;

import org.htmlparser.filters.NodeClassFilter;

import org.htmlparser.filters.OrFilter;

import org.htmlparser.tags.ImageTag;

import org.htmlparser.tags.LinkTag;

import org.htmlparser.util.NodeList;

import org.htmlparser.util.ParserException;

public class Catenate {   
    public static void main(String[] args) throws Exception {   
        String url = "http://www.bradfordexchange.com/";   
        extracLinks(url);   
    }   

    // 获取一个网页上所有的链接和图片链接   
    @SuppressWarnings("serial")   
    public static void extracLinks(String url) {   
        try {   
            Parser parser = new Parser(url);   
            parser.setEncoding("utf-8");   
            // 过滤 <frame> 标签的 filter，用来提取 frame 标签里的 src 属性所、表示的链接   
            NodeFilter frameFilter = new NodeFilter() {   
                public boolean accept(Node node) {   
                    if (node.getText().contains("category")   
                            || node.getText().contains("mcategory")   
                            //|| node.getText().startsWith("frame src=")   
                            // || node.getText().startsWith("img src=")   
                    ) {   
                        return true;   
                    } else {   
                        return false;   
                    }   
                }   
            };   
            // OrFilter 来设置过滤 <a> 标签，<img> 标签和 <frame> 标签，三个标签是 or 的关系   
            OrFilter linkFilter = new OrFilter(new NodeClassFilter(   
                    LinkTag.class), frameFilter);   
            // 得到所有经过过滤的标签   
            NodeList list = parser.extractAllNodesThatMatch(linkFilter);   
            for (int i = 0; i < list.size(); i++) {   
                Node tag = list.elementAt(i);   
                if (tag instanceof LinkTag)// <a> 标签   
                {   
                    LinkTag link = (LinkTag) tag;   
                    String linkUrl = link.getLink();// url   
                    String text = link.getLinkText();// 链接文字   
                    System.out.println(linkUrl + "********" + text);   
                } else if (tag instanceof ImageTag)// <img> 标签   
                {   
                    ImageTag image = (ImageTag) list.elementAt(i);   
                    System.out.print(image.getImageURL() + "********");// 图片地址   
                    System.out.println(image.getText());// 图片文字   
                } else// <frame> 标签   
                {   
                    // 提取 frame 里 src 属性的链接如 <frame src="test.html"/>   
                    String frame = tag.getText();   
                    int start = frame.indexOf("src=");   
                    if (start >= 0) {  
                        frame = frame.substring(start);   
                        int end = frame.indexOf(" ");   
                        if (end == -1)   
                            end = frame.indexOf(">");   
                        frame = frame.substring(5, end - 1);   
                        System.out.println(frame);  
                    }  
                }   
            }   
        } catch (ParserException e) {   
            e.printStackTrace();   
        }   
    }   

}   

[/code]