Examples of org.htmlparser.lexer.Lexer.nextNode()

org.htmlparser.lexer.Lexer.nextNode()
Get the next node from the source. @return A Remark, Text or Tag, or null if nomore lexemes are present. @exception ParserException If there is a problem with theunderlying page.

        node = lexer.nextNode();
        if (node == null)
            fail ("too few nodes");
        else
            assertStringEquals("bad html", html, node.toHtml());
        assertNull("too many nodes", lexer.nextNode());
    }


    /**
     * See bug #899413 bug in javascript end detection.
     */

View Full Code Here

        Node node;
        
        string = "\na='\\'';\n";
        html = string + "</script>";
        lexer = new Lexer (html);
        node = lexer.nextNode (true);
        if (node == null)
            fail ("too few nodes");
        else
            assertStringEquals ("bad string", string, node.toHtml());
        assertNotNull ("too few nodes", lexer.nextNode (true));

View Full Code Here

        node = lexer.nextNode (true);
        if (node == null)
            fail ("too few nodes");
        else
            assertStringEquals ("bad string", string, node.toHtml());
        assertNotNull ("too few nodes", lexer.nextNode (true));
        assertNull ("too many nodes", lexer.nextNode (true));
    }


    /**
     * See bug #1227213 Particular SCRIPT tags close too late.

View Full Code Here

        if (node == null)
            fail ("too few nodes");
        else
            assertStringEquals ("bad string", string, node.toHtml());
        assertNotNull ("too few nodes", lexer.nextNode (true));
        assertNull ("too many nodes", lexer.nextNode (true));
    }


    /**
     * See bug #1227213 Particular SCRIPT tags close too late.
     */

View Full Code Here

        final String content = node.getDataAsString();
        final Lexer lexer = new Lexer(content);
        Node cursor = null;


        try {
            while ((cursor = lexer.nextNode()) != null) {
                if (cursor instanceof Remark) {
                    items.add(new SimpleComment(cursor.getText()));
                } else if (cursor instanceof Text) {
                    items.add(new SimpleText(cursor.toHtml()));
                } else if (cursor instanceof org.htmlparser.Tag) {

View Full Code Here

      byte[] bytes = html.getBytes();
      ByteArrayInputStream bais = new ByteArrayInputStream(bytes);
      Page page = new Page(bais, "UTF-8");
      Lexer lexer = new Lexer(page);
      Node node;
      while ((node = lexer.nextNode()) != null) {
        if (node instanceof Tag) {
          Tag tag = (Tag)node;
          if (tag.getTagName().equalsIgnoreCase("A") && !tag.isEndTag()) {
            assertEquals("href", "http://example.com/api?a=1&amp;b=2&c=3&#34;", tag.getAttribute("HREF"));

View Full Code Here

      ByteArrayInputStream bais = new ByteArrayInputStream(bytes);
      Page page = new Page(bais, "UTF-8");
      Lexer lexer = new Lexer(page);
      Node node;


      node = lexer.nextNode();
      // HTMLParser returns CDATA section as TagNode
      assertTrue(node instanceof TagNode);
      TagNode tag = (TagNode)node;
      // whose tagName is "![CDATA[" *plus* non-whitespace chars following
      // it.  And if they are alphabets, they get capitalized.

View Full Code Here

0 1 2 3

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.