Examples of org.htmlparser.Parser

org.htmlparser.Parser

ahoo.com",new DefaultHTMLParserFeedback()); // In this example, we are registering all the common scanners parser.registerScanners(); for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode(); node.print(); } Below is some sample code to parse Yahoo.com and print only the text information. This scanning will run faster, as there are no scanners registered here.

 Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback()); // In this example, none of the scanners need to be registered // as a string node is not a tag to be scanned for. for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode(); if (node instanceof StringNode) {        	 StringNode stringNode = (StringNode)node;         System.out.println(stringNode.getText());     }  }

The above snippet will print out only the text contents in the html document.
Here's another snippet that will only print out the link urls in a document. This is an example of adding a link scanner.

 Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback()); parser.addScanner(new LinkScanner("-l")); for (NodeIterator i = parser.elements();e.hasMoreNodes();) { Node node = i.nextNode();     if (node instanceof LinkTag) { LinkTag linkTag = (LinkTag)node;         System.out.println(linkTag.getLink());     }  }

@see Parser#elements()

         }
         bos.close();


         String html = new String(bos.toByteArray());


         Parser parser = Parser.createParser(html, null);
         StringBean sb = new StringBean();


         // read links or not
         // sb.setLinks(true); //TODO make this configurable


         // extract text
         parser.visitAllNodesWith(sb);


         String text = sb.getStrings();
         refined_text = (text != null) ? text : ""; // delete(text);


      }

View Full Code Here

         }
         bos.close();


         String html = new String(bos.toByteArray());


         Parser parser = Parser.createParser(html, null);
         StringBean sb = new StringBean();


         // read links or not
         // sb.setLinks(true);


         // extract text
         parser.visitAllNodesWith(sb);


         String text = sb.getStrings();
         refined_text = (text != null) ? text : ""; // delete(text);


      }

View Full Code Here

            bos.write(buffer, 0, len);
         bos.close();


         String html = new String(bos.toByteArray());


         Parser parser = Parser.createParser(html, null);
         StringBean sb = new StringBean();


         // read links or not
         // sb.setLinks(true); //TODO make this configurable


         // extract text
         parser.visitAllNodesWith(sb);


         String text = sb.getStrings();
         refined_text = (text != null) ? text : ""; // delete(text);


      }

View Full Code Here

                                   String loginUrl, String contentType) throws IOException, 
                                                           ParserException {
        logger.debug("Processing an HTML document");


        String stream = null;
        Parser parser = null;
        NodeVisitor visitor = null;


        // Retrieve HTML stream
        stream = 
                readFully(new InputStreamReader(method.getResponseBodyAsStream()));


        // Protection
        if (stream != null) {
            logger.debug("Stream content size: " + stream.length());
            // Parse HTML stream to replace any links to include the path to the valve
            parser = Parser.createParser(stream, null);


            // Instantiate visitor
            visitor = new HTTPVisitor(url, loginUrl);
            // Parse nodes
            parser.visitAllNodesWith(visitor);


            // Get writer
            PrintWriter out = response.getWriter();


            // Push HTML content

View Full Code Here


        if (log.isDebugEnabled()) {
            log.debug("Parsing html of: " + baseUrl);
        }


        Parser htmlParser = null;
        try {
            String contents = new String(html,encoding); 
            htmlParser = new Parser();
            htmlParser.setInputHTML(contents);
        } catch (Exception e) {
            throw new HTMLParseException(e);
        }


        // Now parse the DOM tree
        try {
            // we start to iterate through the elements
            parseNodes(htmlParser.elements(), new URLPointer(baseUrl), urls);
            log.debug("End   : parseNodes");
        } catch (ParserException e) {
            throw new HTMLParseException(e);
        }

View Full Code Here

      e.printStackTrace();
    }*/
    List<Map<String,String>> result = new ArrayList<Map<String,String>>();
    int count = 0;
    try {
      Parser parser = new Parser();
      parser.setInputHTML(inputHTML);
      parser.setEncoding("UTF-8");    
      NodeList nl = parser.parse(null); 
      NodeList trs = nl.extractAllNodesThatMatch(new TagNameFilter("tr"),true);
      String regex = "([a-z]+) *= *\"?((?:(?! [a-z]+ *=|/? *>|\").)+)";
        Pattern p = Pattern.compile(regex, Pattern.DOTALL);
        for(int i=0;i<trs.size();i++) {
          NodeList nodes = trs.elementAt(i).getChildren();

View Full Code Here

        
        if (log.isDebugEnabled()) {
            log.debug("Parsing html of: " + baseUrl);
        }
        
        Parser htmlParser = null;
    try {
      String contents = new String(html);
      htmlParser = new Parser();
            htmlParser.setInputHTML(contents);
    } catch (Exception e) {
      throw new HTMLParseException(e);
    }


    // Now parse the DOM tree
    try {
      // we start to iterate through the elements
      parseNodes(htmlParser.elements(), new URLPointer(baseUrl), urls);
      log.debug("End   : parseNodes");
    } catch (ParserException e) {
      throw new HTMLParseException(e);
    }

View Full Code Here

    SortedSet<HtmlConverterPSpan> visibleSpansSoFar = new TreeSet<HtmlConverterPSpan>();
    SortedSet<HtmlConverterPSpan> linebreaksFromHtmlTags = new TreeSet<HtmlConverterPSpan>();


    // process
    try {
      Parser parser = new Parser(documentText);
      NodeList list = parser.parse(null);
      HtmlConverterVisitor visitor = new HtmlConverterVisitor(newlineInducingTags, skipWhitespaces);
      list.visitAllNodesWith(visitor);
      visibleSpansSoFar = visitor.getTextSpans();
      linebreaksFromHtmlTags = visitor.getLinebreaksFromHtmlTags();
    } catch (ParserException e) {

View Full Code Here

  public void process(JCas jcas) throws AnalysisEngineProcessException {
    String documentText = jcas.getDocumentText();
    List<AnnotationFS> annotations = new ArrayList<AnnotationFS>();
    List<AnnotationFS> annotationStack = new ArrayList<AnnotationFS>();
    try {
      Parser parser = new Parser(documentText);
      NodeList list = parser.parse(null);
      HtmlVisitor visitor = new HtmlVisitor(jcas, onlyContent);
      list.visitAllNodesWith(visitor);
      annotations = visitor.getAnnotations();
      annotationStack = visitor.getAnnotationStack();
    } catch (ParserException e) {

View Full Code Here

        sb.append(line + "\n");
      }


      String document = sb.toString();


      Parser parser = new Parser(document);
      NodeList list = parser.parse(null);
      HtmlDocumentationVisitor visitor = new HtmlDocumentationVisitor(document);
      list.visitAllNodesWith(visitor);
      map.putAll(visitor.getMap());
    } catch (Exception e) {
      RutaIdeUIPlugin.error(e);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.htmlparser.Parser

cn.edu.pku.dr.requirement.elicitation.tools.HtmlTransformer

com.gnizr.core.util.FormatUtil

com.knowgate.hipermail.DBMimeMessage

com.knowgate.hipermail.HtmlMimeBodyPart

com.lanyuan.util.HttpClientUtils

com.vgo.movie.thread.DetailFilmThread

com.waxayaz.TomcatMI.core.utils.repoManager.TomcatRepositoryManager

com.wordpress.util.StringUtil

fitnesse.fixtures.PageDriver

fitnesse.slim.converters.MapEditor

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.