Jsoup Html parsing problem finding internal links data

Usually we have many internal links in a file. I want to parse a html file such that i get the headings of a page and its corresponding data in a map.

Steps i did:

1) Got all the internal reference elements

2) Parsed the document for the id = XXX where XXX == (element <a href="#XXX").

3) it takes me to the <span id="XXX">little text here </span> <some tags here too ><p> actual text here </p> <p> here too </p>

4) How to go from <span> to <p> ???

5) I tried going to parent of span and thought that its one of the child is <p> too... its true. But it also involves <p> of other internal links too.

EDIT: added an sample html file portion:

<li class="toclevel-1 tocsection-1"><a href="#Enforcing_mutual_exclusion">  
<span class="tocnumber">1</span> <span class="toctext">Enforcing mutual   exclusion</span>  </a><ul>  
<li class="toclevel-2 tocsection-2"><a href="#Hardware_solutions">  
<span class="tocnumber">1.1</span> <span class="toctext">Hardware solutions</span>  
</a></li> 
<li class="toclevel-2 tocsection-3"><a href="#Software_solutions">

<h2><span class="editsection">[<a href="/w/index.php?title=Mutual_exclusion&     
 amp;action=edit&amp;section=1" title="Edit section: Enforcing mutual exclusion">
 edit</a>]</span> <span class="mw-headline" id="Enforcing_mutual_exclusion"&g开发者_StackOverflow中文版t;

<comment --------------------------------------------------------------------    

**see the id above = Enforcing_mutual_exclusion**  which is same as first internal   
link . Jsoup takes me to this span element.  i want to access every <p> element after 
this <span> tag  before another <span> tag with id="any of the internal links"
------------------------------------------------------------------------------!>
Enforcing mutual exclusion</span></h2>
<p>There are both software and hardware solutions for enforcing mutual exclusion.  
The   different solutions are shown below.</p>
<h3><span class="editsection">[<a href="/w/index.php?title=Mutual_exclusion&  
amp;action=edit&amp;section=2" title="Edit section: Hardware solutions">
edit</a>]</span> <span class="mw-headline" id="Hardware_solutions">Hardware   
solutions</span></h3>

<p>On a <a href="/wiki/Uniprocessor" title="Uniprocessor" class="mw-  
 redirect">uniprocessor</a> system a common way to achieve mutual exclusion inside 
 <a href="/wiki/Kernel_(computing)" title="Kernel (computing)">kernels</a> is 
 disable <a href="/wiki/Interrupt" title="Interrupt">

Here is my code:

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.LinkedHashMap;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public final class Website {
private URL websiteURL ;
private Document httpDoc ;
LinkedHashMap<String, ArrayList<String>> internalLinks = 
        new LinkedHashMap<String, ArrayList<String>>();

public Website(URL __websiteURL) throws MalformedURLException, IOException, Exception{
    if(__websiteURL == null)
        throw new Exception();
    websiteURL = __websiteURL;
    httpDoc = Jsoup.parse(connect());

    System.out.println("Parsed the http file to Document");
}


/* Here is my function: i first gets all the internal links in internalLinksElements. 
   I then get the href name of <a ..> tag so that i can search for it in documnet.

*/
public void getDataWithHeadingsTogether(){
    Elements internalLinksElements;
    internalLinksElements = httpDoc.select("a[href^=#]");
    for(Element element : internalLinksElements){

// some inline links were bad. i only those having span as their child. 
        Elements spanElements = element.select("span");
        if(!spanElements.isEmpty()){
            System.out.println("Text(): " + element.text());  // this can not give what i want
            //  ok i get the href tag name that would be the id
            String href = element.attr("href") ; 
            href = href.replace("#", "");
            System.out.println(href);
            // selecting the element where we have that id.
            Element data = httpDoc.getElementById(href);
            // got the span
            if(data == null)
                continue;
            Elements children = new Elements();
            // problem is here.
            while(children.isEmpty()){
                // going to its element unless gets some data.
                data = data.parent();
                System.out.println(data);
                children = data.select("p");
            }
            // its giving me all the data of file. thats bad.
            System.out.println(children.text());
        }
    }
}
/**
 * 
 * @return String Get all the headings of the document.
 * @throws MalformedURLException
 * @throws IOException
 */
@SuppressWarnings("CallToThreadDumpStack")
public String connect() throws MalformedURLException, IOException{
    // Is this thread safe ? url.openStream();
    BufferedReader  reader = null;
    try{
        reader = new BufferedReader( new InputStreamReader(websiteURL.openStream()));
        System.out.println("Got the reader");
    } catch(Exception e){
        e.printStackTrace();
        System.out.println("Bye");
        String html = "<html><h1>Heading 1</h1><body><h2>Heading 2</h2><p>hello</p></body></html>";
        return html;
    }
    String inputLine, result  = new String();
    while((inputLine = reader.readLine()) != null){
        result += inputLine;
    }
    reader.close();
    System.out.println("Made the html file");
    return result;
}




/**
 * 
 * @param argv all the command line parameters.
 * @throws MalformedURLException
 * @throws IOException
 */
public static void main(String[] argv) throws MalformedURLException, IOException, Exception{
    System.setProperty("proxyHost", "172.16.0.3");
    System.setProperty("proxyPort","8383");
     System.out.println("Sending url");

     // a html file or any url place here ------------------------------------
     URL url = new URL("put a html file here "); 
    Website website = new Website(url);

    System.out.println(url.toString());
    System.out.println("++++++++++++++++++++++++++++++++++++++++++++++++");
    website.getDataWithHeadingsTogether();

}
}

I think you need to understand that the <span>s that you are locating are children of header elements, and that the data you want to store is made up of siblings of that header.

Therefore, you need to grab the <span>'s parent, and then use nextSibling to collect nodes that are your data for that <span>. You need to stop collecting data when you run out of siblings, or you encounter another header element, because another header indicates the start of the next item's data.