HTML Parser

最新推荐文章于 2021-06-16 05:54:57 发布

原创最新推荐文章于 2021-06-16 05:54:57 发布 · 887 阅读

0 ·

CC 4.0 BY-SA版权

Java/Groovy&Grails 专栏收录该内容

16 篇文章

订阅专栏

本文介绍了一种使用Java实现的HTML解析器的应用案例，通过访问指定网页并抓取页面信息，包括文本、链接及标题等内容。

HTML Parser 用于对HTML进行解析，并从中攫取你所需的信息。

Java版：

http://htmlparser.sourceforge.net/

http://www.ibm.com/developerworks/cn/java/l-html-parser/

Htmlparser的使用范例：

package com.amigo.htmlparser;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;

import org.htmlparser.filters.*;
import org.htmlparser.*;
import org.htmlparser.nodes.*;
import org.htmlparser.tags.*;
import org.htmlparser.util.*;
import org.htmlparser.visitors.*;

public class HTMLParserTest {

    public static void main(String args[]) throws Exception {
        String path = "http://www.blogjava.net/amigoxie";
        URL url = new URL(path);
        URLConnection conn = url.openConnection();
        conn.setDoOutput(true);

        InputStream inputStream = conn.getInputStream();
        InputStreamReader isr = new InputStreamReader(inputStream, "utf8");
        StringBuffer sb = new StringBuffer();
        BufferedReader in = new BufferedReader(isr);
        String inputLine;

        while ((inputLine = in.readLine()) != null) {
            sb.append(inputLine);
            sb.append("\n");
        }

        String result = sb.toString();

        readByHtml(result);
        readTextAndLinkAndTitle(result);
    }


    public static void readByHtml(String content) throws Exception {
        Parser myParser;
        myParser = Parser.createParser(content, "utf8");
        HtmlPage visitor = new HtmlPage(myParser);
        myParser.visitAllNodesWith(visitor);

        String textInPage = visitor.getTitle();
        System.out.println(textInPage);
        NodeList nodelist;
        nodelist = visitor.getBody();

        System.out.print(nodelist.asString().trim());
    }

    public static void readTextAndLinkAndTitle(String result) throws Exception {
        Parser parser;
        NodeList nodelist;
        parser = Parser.createParser(result, "utf8");
        NodeFilter textFilter = new NodeClassFilter(TextNode.class);
        NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
        NodeFilter titleFilter = new NodeClassFilter(TitleTag.class);
        OrFilter lastFilter = new OrFilter();
        lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter, titleFilter });
        nodelist = parser.parse(lastFilter);
        Node[] nodes = nodelist.toNodeArray();
        String line = "";

        for (int i = 0; i < nodes.length; i++) {
            Node node = nodes[i];
            if (node instanceof TextNode) {
                TextNode textnode = (TextNode) node;
                line = textnode.getText();
            } else if (node instanceof LinkTag) {
                LinkTag link = (LinkTag) node;
                line = link.getLink();
            } else if (node instanceof TitleTag) {
                TitleTag titlenode = (TitleTag) node;
                line = titlenode.getTitle();
            }

            if (isTrimEmpty(line))
                continue;
            System.out.println(line);
        }
    }


    public static boolean isTrimEmpty(String astr) {
        if ((null == astr) || (astr.length() == 0)) {
            return true;
        }
        if (isBlank(astr.trim())) {
            return true;
        }
        return false;
    }

    public static boolean isBlank(String astr) {
        if ((null == astr) || (astr.length() == 0)) {
            return true;
        } else {
            return false;
        }
    }
}
PHP版：