Examples of org.htmlparser.scanners.TagScanner

org.htmlparser.scanners.TagScanner
TagScanner is an abstract superclass which is subclassed to create specific scanners, that operate on a tag's strings, identify it, and can extract data from it.
If you wish to write your own scanner, then you must implement scan(). You MAY implement evaluate() as well, if your evaluation logic is not based on a simple text match. You MUST implement getID() - which identifies your scanner uniquely in the hashtable of scanners.
Also, you have a feedback object provided to you, should you want to send log messages. This object is instantiated by Parser when a scanner is added to its collection.

    }


    public void testRemoveChars()
    {
        String test = "hello\nworld\n\tqsdsds";
        TagScanner scanner = new TagScanner()
        {
            public Tag scan(
                Tag tag,
                String url,
                NodeReader reader,

View Full Code Here

    }


    public void testRemoveChars2()
    {
        String test = "hello\r\nworld\r\n\tqsdsds";
        TagScanner scanner = new TagScanner()
        {
            public Tag scan(
                Tag tag,
                String url,
                NodeReader reader,
                String currLine)
            {
                return null;
            }
            public boolean evaluate(String s, TagScanner previousOpenScanner)
            {
                return false;
            }
            public String[] getID()
            {
                return null;
            }


        };
        String result = scanner.removeChars(test, "\r\n");
        assertEquals("Removing Chars", "helloworld\tqsdsds", result);
    }

View Full Code Here

    {
        createParser("");
        parser.registerScanners();
        parser.removeScanner(new FormScanner("", parser));
        Map scanners = parser.getScanners();
        TagScanner scanner = (TagScanner) scanners.get("FORM");
        assertNull("shouldnt have found scanner", scanner);
    }

View Full Code Here

            boolean found = false;
            Node retVal = null;
            // Find the first word in the scanners
            String firstWord = extractWord(tagContents.toString());
            // Now, get the scanner associated with this.
            TagScanner scanner = (TagScanner) scanners.get(firstWord);


            // Now do a deep check
            if (scanner != null
                && scanner.evaluate(
                    tagContents.toString(),
                    reader.getPreviousOpenScanner()))
            {
                found = true;
                TagScanner save;
                save = reader.getPreviousOpenScanner();
                reader.setPreviousOpenScanner(scanner);
                retVal = scanner.createScannedNode(this, url, reader, tagLine);
                reader.setPreviousOpenScanner(save);
            }

View Full Code Here

            boolean found = false;
            Node retVal = null;
            // Find the first word in the scanners
            String firstWord = extractWord(tagContents.toString());
            // Now, get the scanner associated with this.
            TagScanner scanner = (TagScanner) scanners.get(firstWord);


            // Now do a deep check
            if (scanner != null
                && scanner.evaluate(
                    tagContents.toString(),
                    reader.getPreviousOpenScanner()))
            {
                found = true;
                TagScanner save;
                save = reader.getPreviousOpenScanner();
                reader.setPreviousOpenScanner(scanner);
                retVal = scanner.createScannedNode(this, url, reader, tagLine);
                reader.setPreviousOpenScanner(save);
            }

View Full Code Here

                    // There is a filter. Find if the associated filter of this node
                    // matches the specified filter
                    if (!(node instanceof Tag))
                        continue;
                    Tag tag = (Tag) node;
                    TagScanner scanner = tag.getThisScanner();
                    if (scanner == null)
                        continue;


                    String tagFilter = scanner.getFilter();
                    if (tagFilter == null)
                        continue;
                    if (tagFilter.equals(filter))
                        System.out.println(node.toString());
                }

View Full Code Here

    assertTrue("OPTION tag could not be identified", TagScanner.isXMLTagFound(node, "OPTION"));
  }


  public void testRemoveChars() {
    String test = "hello\nworld\n\tqsdsds";
    TagScanner scanner = new TagScanner() {
      public Tag scan(Tag tag, String url, NodeReader reader, String currLine) {
        return null;
      }


      public boolean evaluate(String s, TagScanner previousOpenScanner) {

View Full Code Here

    assertEquals("Removing Chars", "helloworld\tqsdsds", result);
  }


  public void testRemoveChars2() {
    String test = "hello\r\nworld\r\n\tqsdsds";
    TagScanner scanner = new TagScanner() {
      public Tag scan(Tag tag, String url, NodeReader reader, String currLine) {
        return null;
      }


      public boolean evaluate(String s, TagScanner previousOpenScanner) {
        return false;
      }


      public String[] getID() {
        return null;
      }


    };
    String result = scanner.removeChars(test, "\r\n");
    assertEquals("Removing Chars", "helloworld\tqsdsds", result);
  }

View Full Code Here

      boolean found = false;
      Node retVal = null;
      // Find the first word in the scanners
      String firstWord = extractWord(tagContents.toString());
      // Now, get the scanner associated with this.
      TagScanner scanner = (TagScanner) scanners.get(firstWord);


      // Now do a deep check
      if (scanner != null && scanner.evaluate(tagContents.toString(), reader.getPreviousOpenScanner())) {
        found = true;
        TagScanner save;
        save = reader.getPreviousOpenScanner();
        reader.setPreviousOpenScanner(scanner);
        retVal = scanner.createScannedNode(this, url, reader, tagLine);
        reader.setPreviousOpenScanner(save);
      }

View Full Code Here

          // node
          // matches the specified filter
          if (!(node instanceof Tag))
            continue;
          Tag tag = (Tag) node;
          TagScanner scanner = tag.getThisScanner();
          if (scanner == null)
            continue;


          String tagFilter = scanner.getFilter();
          if (tagFilter == null)
            continue;
          if (tagFilter.equals(filter))
            System.out.println(node.toString());
        }

View Full Code Here

0 1

TOP

Related Classes of org.htmlparser.scanners.TagScanner

org.htmlparser.Parser

org.htmlparser.StringNode

org.htmlparser.tags.data.TagData

org.htmlparser.tags.EndTag

org.htmlparser.tags.Tag

org.htmlparser.tests.ParserTest

org.htmlparser.tests.scannersTests.TagScannerTest

java.util.Hashtable

java.util.Map

org.htmlparser.util.ParserException

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.