Html Parser

最新推荐文章于 2024-09-04 10:53:03 发布

xfyjg

最新推荐文章于 2024-09-04 10:53:03 发布

阅读量221

点赞数

分类专栏： java 文章标签： HTML Google J#

本文链接：https://blog.csdn.net/xfyjg/article/details/83555261

版权

java 专栏收录该内容

25 篇文章 0 订阅

订阅专栏

/*
    * 测试对<table><tr><td></td></tr></table>的解析
    */
    public void testTable() {
        Parser myParser;
        NodeList nodeList = null;
        myParser = Parser.createParser("<body> " + "<table id=’table1′ >"
        + "<tr><td>1-11</td><td>1-12</td><td>1-13</td>"
        + "<tr><td>1-21</td><td>1-22</td><td>1-23</td>"
        + "<tr><td>1-31</td><td>1-32</td><td>1-33</td></table>"
        + "<table id=’table2′ >"
        + "<tr><td>2-11</td><td>2-12</td><td>2-13</td>"
        + "<tr><td>2-21</td><td>2-22</td><td>2-23</td>"
        + "<tr><td>2-31</td><td>2-32</td><td>2-33</td></table>"
        + "</body>", "GBK");
        NodeFilter tableFilter = new NodeClassFilter(TableTag.class);
        OrFilter lastFilter = new OrFilter();
        lastFilter.setPredicates(new NodeFilter[] { tableFilter });
        try {
            nodeList = myParser.parse(lastFilter);
            for (int i = 0; i <= nodeList.size(); i++) {
                if (nodeList.elementAt(i) instanceof TableTag) {
                    TableTag tag = (TableTag) nodeList.elementAt(i);
                    TableRow[] rows = tag.getRows();

                    for (int j = 0; j < rows.length; j++) {
                        TableRow tr = (TableRow) rows[j];
                        TableColumn[] td = tr.getColumns();
                        for (int k = 0; k < td.length; k++) {
                            logger.fatal("<td>" + td[k].toPlainTextString());
                        }

                    }

                }
            }

        } catch (ParserException e) {
            e.printStackTrace();
        }
    }

/*
    * 测试NodeVisitor的用法，遍历所有节点
    */
    public void testVisitorAll() {
        try {
            Parser parser = new Parser();
            parser.setURL("http://www.google.com");
            parser.setEncoding(parser.getEncoding());

            NodeVisitor visitor = new NodeVisitor() {
                public void visitTag(Tag tag) {
                    logger.fatal("testVisitorAll() Tag name is :"
                    + tag.getTagName() + " \n Class is :"
                    + tag.getClass());
                }
            };
            parser.visitAllNodesWith(visitor);
        } catch (ParserException e) {
            e.printStackTrace();
        }
    }
    /*
    * 测试对指定Tag的NodeVisitor的用法
    */
    public void testTagVisitor() {
        try {
            Parser parser = new Parser(
                "<head><title>dddd</title>"
                + "<link href=http://www.yeeach.com/’/test01/css.css’ text=’text/css’ rel=’stylesheet’ />"
                + "<link href=http://www.yeeach.com/’/test02/css.css’ text=’text/css’ rel=’stylesheet’ />"
                + "</head>" + "<body>"
                + "<a href=http://www.yeeach.com/’http://www.yeeach.com’>yeeach.com</a>"
                + "</body>");
            NodeVisitor visitor = new NodeVisitor() {
                public void visitTag(Tag tag) {
                    if (tag instanceof HeadTag) {
                        logger.fatal("visitTag() HeadTag : Tag name is :"
                        + tag.getTagName() + " \n Class is :"
                        + tag.getClass() + "\n Text is :"
                        + tag.getText());
                    } else if (tag instanceof TitleTag) {
                        logger.fatal("visitTag() TitleTag : Tag name is :"
                        + tag.getTagName() + " \n Class is :"
                        + tag.getClass() + "\n Text is :"
                        + tag.getText());
                    } else if (tag instanceof LinkTag) {
                        logger.fatal("visitTag() LinkTag : Tag name is :"
                        + tag.getTagName() + " \n Class is :"
                        + tag.getClass() + "\n Text is :"
                        + tag.getText() + " \n getAttribute is :"
                        + tag.getAttribute("href"));
                    } else {
                        logger.fatal("visitTag() : Tag name is :"
                        + tag.getTagName() + " \n Class is :"
                        + tag.getClass() + "\n Text is :"
                        + tag.getText());
                    }
                }
            };
            parser.visitAllNodesWith(visitor);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    /*
    * 测试HtmlPage的用法
    */
    public void testHtmlPage() {
        String inputHTML = "<html>" + "<head>"
        + "<title>Welcome to the HTMLParser website</title>"
        + "</head>" + "<body>" + "Welcome to HTMLParser"
        + "<table id=’table1′ >"
        + "<tr><td>1-11</td><td>1-12</td><td>1-13</td>"
        + "<tr><td>1-21</td><td>1-22</td><td>1-23</td>"
        + "<tr><td>1-31</td><td>1-32</td><td>1-33</td></table>"
        + "<table id=’table2′ >"
        + "<tr><td>2-11</td><td>2-12</td><td>2-13</td>"
        + "<tr><td>2-21</td><td>2-22</td><td>2-23</td>"
        + "<tr><td>2-31</td><td>2-32</td><td>2-33</td></table>"
        + "</body>" + "</html>";
        Parser parser = new Parser();
        try {
        parser.setInputHTML(inputHTML);
        parser.setEncoding(parser.getURL());
        HtmlPage page = new HtmlPage(parser);
        parser.visitAllNodesWith(page);
        logger.fatal("testHtmlPage -title is :" + page.getTitle());
        NodeList list = page.getBody(); 
        for (NodeIterator iterator = list.elements(); iterator
        .hasMoreNodes();) {
        Node node = iterator.nextNode();
        logger.fatal("testHtmlPage -node is :" + node.toHtml());
        }
        } catch (ParserException e) {
    //     TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    /*
    * 测试LinkBean的用法
    */
    public void testLinkBean() {
        Parser parser = new Parser();
        LinkBean linkBean = new LinkBean();
        linkBean.setURL("http://www.google.com");
        URL[] urls = linkBean.getLinks();
        for (int i = 0; i < urls.length; i++) {
            URL url = urls[i];
            logger.fatal("testLinkBean() -url is :" + url);
        }
    }

   }

[quote]另外一种[/quote]

public class ParserTestCase extends TestCase {
    private static final Logger logger = Logger.getLogger(ParserTestCase.class);

    public ParserTestCase(String name) {
        super(name);
     }
    /*
     * 测试ObjectFindVisitor的用法
    */
    public void testImageVisitor() {
        try {
             ImageTag imgLink;
             ObjectFindingVisitor visitor = new ObjectFindingVisitor(ImageTag.class);
             Parser parser = new Parser();
             parser.setURL("http://www.google.com");
             parser.setEncoding(parser.getEncoding());
             parser.visitAllNodesWith(visitor);
             Node[] nodes = visitor.getTags();
            for (int i = 0; i < nodes.length; i++) {
                 imgLink = (ImageTag) nodes[i];
                 logger.fatal("testImageVisitor() ImageURL = "
                + imgLink.getImageURL());
                 logger.fatal("testImageVisitor() ImageLocation = "
                + imgLink.extractImageLocn());
                 logger.fatal("testImageVisitor() SRC = "
                + imgLink.getAttribute("SRC"));
             }
         }catch (Exception e) {
             e.printStackTrace();
         }
     }

    /*
     * 测试TagNameFilter用法
    */
    public void testNodeFilter() {
        try {
             NodeFilter filter = new TagNameFilter("IMG");
             Parser parser = new Parser();
             parser.setURL("http://www.google.com");
             parser.setEncoding(parser.getEncoding());
             NodeList list = parser.extractAllNodesThatMatch(filter);
            for (int i = 0; i < list.size(); i++) {
                 logger.fatal("testNodeFilter() " + list.elementAt(i).toHtml());
             }
         } catch (Exception e) {
             e.printStackTrace();
         }

     }
    /*
     * 测试NodeClassFilter用法
    */
    public void testLinkTag() {
        try {

             NodeFilter filter = new NodeClassFilter(LinkTag.class);
             Parser parser = new Parser();
             parser.setURL("http://www.google.com");
             parser.setEncoding(parser.getEncoding());
             NodeList list = parser.extractAllNodesThatMatch(filter);
            for (int i = 0; i < list.size(); i++) {
                 LinkTag node = (LinkTag) list.elementAt(i);
                 logger.fatal("testLinkTag() Link is :" + node.extractLink());
             }
         } catch (Exception e) {
             e.printStackTrace();
         }

     }
    /*
     * 测试<link href=" text=’text/css’ rel=’stylesheet’ />用法
    */
    public void testLinkCSS() {
        try {
             Parser parser = new Parser();
             parser
             .setInputHTML("<head><title>Link Test</title>"
            + "<link href=http://www.yeeach.com/’/test01/css.css’ text=’text/css’ rel=’stylesheet’ />"
            + "<link href=http://www.yeeach.com/’/test02/css.css’ text=’text/css’ rel=’stylesheet’ />"
            + "</head>" + "<body>");
             parser.setEncoding(parser.getEncoding());
             NodeList nodeList = null;
            for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
                 Node node = e.nextNode();
                 logger.fatal("testLinkCSS()" + node.getText()+ node.getClass());

             }
         } catch (Exception e) {
             e.printStackTrace();
         }
     }
    /*
     * 测试OrFilter的用法
    */
    public void testOrFilter() {
         NodeFilter inputFilter = new NodeClassFilter(InputTag.class);
         NodeFilter selectFilter = new NodeClassFilter(SelectTag.class);
         Parser myParser;
         NodeList nodeList = null;

        try {
             Parser parser = new Parser();
             parser
             .setInputHTML("<head><title>OrFilter Test</title>"
            + "<link href=http://www.yeeach.com/’/test01/css.css’ text=’text/css’ rel=’stylesheet’ />"
            + "<link href=http://www.yeeach.com/’/test02/css.css’ text=’text/css’ rel=’stylesheet’ />"
            + "</head>"
            + "<body>"
            + "<input type=’text’ value=’text1′ name=’text1′/>"
            + "<input type=’text’ value=’text2′ name=’text2′/>"
            + "<select><option id=’1′>1</option><option id=’2′>2</option><option id=’3′></option></select>"
            + "<a href=http://www.yeeach.com/’http://www.yeeach.com’>yeeach.com</a>"
            + "</body>");

             parser.setEncoding(parser.getEncoding());
             OrFilter lastFilter = new OrFilter();
             lastFilter.setPredicates(new NodeFilter[] { selectFilter,
             inputFilter });
             nodeList = parser.parse(lastFilter);
            for (int i = 0; i <= nodeList.size(); i++) {
                if (nodeList.elementAt(i) instanceof InputTag) {
                     InputTag tag = (InputTag) nodeList.elementAt(i);
                     logger.fatal("OrFilter tag name is :" + tag.getTagName()
                    + " ,tag value is:" + tag.getAttribute("value"));
                 }
                if (nodeList.elementAt(i) instanceof SelectTag) {
                         SelectTag tag = (SelectTag) nodeList.elementAt(i);
                         NodeList list = tag.getChildren();

                    for (int j = 0; j < list.size(); j++) {
                         OptionTag option = (OptionTag) list.elementAt(j);
                         logger
                         .fatal("OrFilter Option"
                        + option.getOptionText());
                     }

                 }
             }

         } catch (ParserException e) {
         e.printStackTrace();
         }
     }

   }