HTML Citation Extraction

Value

Script

URL inputURL = null;
if (base != void) {
  inputURL = new URL(new URL(base), url);
}
else {
  inputURL = new URL(url);
}
URLConnection con = inputURL.openConnection();
InputStream in = con.getInputStream();

InputStreamReader isr = new InputStreamReader(in);
Reader inReader = new BufferedReader(isr);

StringBuffer buf = new StringBuffer();
int ch;
while ((ch = inReader.read()) > -1) {
  buf.append((char)ch);
}
inReader.close();
contents = buf.toString();


//String NEWLINE = System.getProperty("line.separator");
//
//URL inputURL = null;
//if (base != void) {
//	inputURL = new URL(new URL(base), url);
//} else {
//	inputURL = new URL(url);
//}
//StringBuffer result = new StringBuffer();
//BufferedReader reader = new BufferedReader(new InputStreamReader(inputURL.openStream()));
//String line = null;
//while ((line = reader.readLine()) != null) {
//	result.append(line);
//	result.append(NEWLINE);
//}
//
//contents = result.toString();

Script

// Copied and Hacked by Jeffery Adamus
//   based on getImageLinks by Alan Williams
String lowerCaseContent = document.toLowerCase();
int index = 0;
int endUL = 0;


List ulElements = new ArrayList();
while ((index = lowerCaseContent.indexOf("
", index)) != -1) {

	index+= 4;

         if (( endUL = lowerCaseContent.indexOf("
", index)) == -1){
		 debugLog += " break" + endUL;
         	break;
         }


	String strLink = document.substring(index, endUL);
         index = endUL;

	if ( strLink.indexOf( "