Re: [Htmlparser-developer] HTMLParser Sample App
Brought to you by:
derrickoswald
Menu
▾
▴
Re: [Htmlparser-developer] HTMLParser Sample App
|
From: Somik R. <so...@ya...> - 2002-03-12 08:52:14
|
Hi Don,
It will be appreciated if you can post usage doubts in the
htmlparser-user mailing list (link is at http://htmlparser.sourceforge.net).
To your query - the code you posted seems rather complex to do a not so
complex task :)
Here's how you would do it in HTML Parser (in the attached code). The
code I have given is the shortcut-way. There is a way to get much shorter
code that what I am providing you, but that requires getting into the design
docs of the parser - and writing a Table Scanner. Then your code could
become some this like this :
HTMLParser parser = new HTMLParser("http://www.nba.com");
HTMLNode node;
int tableCount = 0;
for (Enumeration e = parser.elements();e.hasMoreElements();) {
node = (HTMLNode) e.nextElement();
if (node instanceof HTMLTableNode) {
tableCount ++;
if (tableCount==4) {
HTMLTableNode tableNode = (HTMLTableNode)node;
tableNode.print();
}
}
}
Regards,
Somik
----- Original Message -----
From: "Don Taggart" <dta...@e-...>
To: <Htm...@li...>
Sent: Tuesday, March 12, 2002 1:33 AM
Subject: [Htmlparser-developer] HTMLParser Sample App
> Hi,
> I am attempting to grab the content of a certain table on any website. For
> instance I'd like to get all of the text, tags, comments, etc contained in
> the 4rth table I run across. I've been able to do this successfully using
> the htmleditorkit in swing, but it has a few bugs.
>
> Would your HTML Parser be useful for this scenario, and If so, could you
> give me some guidance on how to start.
>
> Thanks,
> Don
>
>
> Heres my code that goes and get the contents of the 4rth table at nba.com
>
> import java.io.*;
> import java.net.*;
> import java.util.*;
> import javax.swing.text.*;
> import javax.swing.text.html.*;
> import javax.swing.text.html.parser.*;
>
> /**
> * This small demo program shows how to use the
> * HTMLEditorKit.Parser and its implementing class
> * ParserDelegator in the Swing system.
> */
>
> public class HtmlParseDemo2 {
> public static void main(String [] args) {
> Reader r;
> String host = "";
> String spec = "http://www.nba.com";
> long endTime;
> long endTime2;
> long startTime = System.currentTimeMillis();
> String snippet = "";
>
>
> try {
> if (spec.indexOf("://") > 0) {
> URL u = new URL(spec);
> host = u.getHost();
> Object content = u.getContent();
>
> if (content instanceof InputStream) {
>
> r = new InputStreamReader((InputStream)content);
> }
> else if (content instanceof Reader) {
> r = (Reader)content;
> }
> else {
> throw new Exception("Bad URL content type.");
> }
> }
> else {
> r = new FileReader(spec);
> }
>
> endTime = System.currentTimeMillis();
> System.out.println("Time to complete connection: " +
(endTime -
> startTime));
>
> HTMLEditorKit.Parser parser;
> System.out.println("About to parse " + spec);
> parser = new ParserDelegator();
>
> HTMLParseLister2 snippetCallback = new HTMLParseLister2(host);
>
> file://Parse Away!
> parser.parse(r, snippetCallback, true);
> r.close();
>
>
> endTime2 = System.currentTimeMillis();
> System.out.println("Time to complete: " + (endTime2 -
> startTime));
> }
> catch (Exception e) {
> System.err.println("Error: " + e);
> e.printStackTrace(System.err);
> }
> }
> }
>
> /**
> * HTML parsing proceeds by calling a callback for
> * each and every piece of the HTML document. This
> * simple callback class simply prints an indented
> * structural listing of the HTML data.
> */
> class HTMLParseLister2 extends HTMLEditorKit.ParserCallback
> {
>
>
>
> int indentSize = 0;
> int tableNum = 0;
> String atts;
> String tabNum;
> String endTable;
> String tableLevel;
> Stack tableStack = new Stack();
> boolean finished = false;
> HTML.Tag selectedTag = HTML.Tag.TABLE;
> String selectedTable = Integer.toString(4);
> boolean inImportantTag = false;
> StringBuffer snippetString = new StringBuffer();
>
>
>
> private String host;
>
>
>
> public HTMLParseLister2(String host) {
> this.host = host;
> }
>
> public String getSnippet() {
> return snippetString.toString();
> }
>
> protected void indent() {
> indentSize += 4;
> }
>
> protected void unIndent() {
> indentSize -= 4; if (indentSize < 0) indentSize = 0;
> }
>
> protected void pIndent() {
> for(int i = 0; i < indentSize; i++) System.out.print(" ");
> }
>
> public void handleText(char[] data, int pos) {
> if (!tableStack.empty() && !finished)
> {
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)))
> {
> file://pIndent();
> String str = new String(data);
> System.out.println(str);
> }
> }
>
> if (inImportantTag)
> {
> String str = new String(data);
> System.out.println(str);
> }
> }
>
> // ********************************************************
> public void handleComment(char[] data, int pos) {
>
> if (!tableStack.empty() && !finished)
> {
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)))
> {
> file://pIndent();
> String str = new String(data);
> file://System.out.println("<!--" + str + "-->");
> file://indent();
> file://pIndent();
> }
> }
>
> if (inImportantTag)
> {
> String str = new String(data);
> System.out.println("<!--" + str + "-->");
> }
>
> }
> // ********************************************************
>
> // ********************************************************
> public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos)
{
> // Is this Tag One of the few that we want to list outside the chosen
> component
> if (t == HTML.Tag.STYLE || t == HTML.Tag.LINK)
> {
> atts = listAttributes(a);
> inImportantTag = true;
> System.out.print("<" + t.toString() + " " + atts + ">");
> return;
> }
>
> if (t == selectedTag && !finished)
> {
>
> file://pIndent();
> tableNum++;
> tabNum = Integer.toString(tableNum);
> tableStack.push(tabNum);
> atts = listAttributes(a);
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)))
> {
> file://System.out.println("<Table#" + tableLevel + ">");
>
> }
> }
>
> if (!tableStack.empty() && !finished) {
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)))
> {
> atts = listAttributes(a);
> System.out.println("<" + t.toString() + " " + atts + ">");
> }
> }
> }
> // ********************************************************
>
>
> // ********************************************************
> public void handleEndTag(HTML.Tag t, int pos) {
> if (inImportantTag)
> {
> inImportantTag = false;
> System.out.println("</" + t.toString() + ">");
> }
>
> if (!tableStack.empty() && !finished)
> {
> if (t == selectedTag)
> {
> file://unIndent();
> file://pIndent();
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable))){
> System.out.println("</" + t.toString() + ">");
> }
> if (tableStack.peek().equals(selectedTable))
> finished = true;
> endTable = (String) tableStack.pop();
> }
> }
> if (!tableStack.empty() && !finished) {
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)) && t != selectedTag) {
> file://pIndent();
> System.out.println("</" + t.toString() + ">");
> file://pIndent();
> }
> }
> }
> // ********************************************************
>
>
>
> // ********************************************************
> public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int
pos)
> {
>
>
>
>
> if (t == HTML.Tag.LINK && !finished)
> {
> atts = listAttributes(a);
> System.out.println("<" + t.toString() + " " + atts + ">");
> }
>
> if (!tableStack.empty() && !finished)
> {
>
>
> atts = listAttributes(a);
> if(a.getAttribute(HTML.Attribute.ENDTAG) != null)
> {
> handleEndTag(t, pos);
> return;
> }
> file://if (tableStack.peek() == selectedTable)
> file://pIndent();
>
> tableLevel = (String)tableStack.peek();
> if (Integer.parseInt(tableLevel) >=
> (Integer.parseInt(selectedTable)))
> System.out.println("<" + t.toString() + " " + atts + ">");
> }
> }
> // ********************************************************
>
>
>
>
> // ********************************************************
> private String listAttributes(AttributeSet attributes) {
> Enumeration e = attributes.getAttributeNames();
> String attString = "";
>
> while (e.hasMoreElements()) {
> Object name = e.nextElement();
> Object value = attributes.getAttribute(name);
>
> if (name.toString().equals("href") || name.toString().equals("src")
> || name.toString().equals("action"))
> {
> if (value.toString().charAt(0) == '/')
> value = host + value;
> }
> attString = attString + name + "=\"" + value + "\" ";
>
> }
> return attString;
> }
> // ********************************************************
>
> // ********************************************************
> public void handleError(String errorMsg, int pos){
> file://System.out.println("Parsing error: " + errorMsg + " at " +
pos);
> }
> }
>
>
> _______________________________________________
> Htmlparser-developer mailing list
> Htm...@li...
> https://lists.sourceforge.net/lists/listinfo/htmlparser-developer
|
