public static String Extract(String sPattern, int iOffset, String sText) {
String sResult = "";
try {
Scanner document_scanner = new Scanner(sText);
int iCountOcurr = 0;
int iFirstLine = 0;
String sLine = "";
Boolean bReading = false;
Boolean bIsEmpty = true;
while (document_scanner.hasNext()) {
sLine = document_scanner.next();
/// Pattern detected
if (sLine.indexOf(sPattern) > -1) {
iCountOcurr++;
}
/// Number of pattern has been reached
if (iCountOcurr == iOffset) {
bReading = true;
}
if (bReading && bIsEmpty) {
if (iFirstLine != 0) {
/// Stop
if (sLine.indexOf(sStop) > -1) {
bReading = false;
bIsEmpty = false;
} else {
sResult += " " + sLine;
}
} else {
sResult += " " + sLine;
}
System.out.println("sResult:" + sResult + "\n");
iFirstLine++;
}
}
document_scanner.close();
// Print number of times the search pattern was found
// System.out.println("Found Input "+ iCountOcurr + " times");
} catch (Exception e) {
sResult = "Error buscar parrafo: " + e.getMessage();
}
return sResult;
}
public static String GetText(String sUrl) {
String sRet = "";
try {
System.out.print(" Connecting to: " + sUrl + "... \n");
InputStream inputStream = new URL(sUrl).openStream();
System.out.print(" Stream readed from: " + sUrl + "\n");
HWPFDocument docx = new HWPFDocument(inputStream);
WordExtractor we = new WordExtractor(docx);
sRet = we.getText();
we.close();
} catch (Exception e) {
sRet = "Error al leer el archivo" + e.getMessage();
}
return sRet;
}
