public static String getFileContent(File file) throws FileNotFoundException, IOException {
String ext = FilenameUtils.getExtension(file.getName());
String outContent = "";
try {
if (ext.toLowerCase().equals("doc")) {
if (file != null) {
WordExtractor we = new WordExtractor(new FileInputStream(file));
outContent = we.getText();
} else {
logger.warning("file not found : " + file);
}
} else if (ext.toLowerCase().equals("pdf")) {
PDDocument doc = PDDocument.load(file);
PDFTextStripper text = new PDFTextStripper();
outContent = text.getText(doc);
doc.close();
} else if (StringHelper.isHTML(file.getName())) {
return loadStringFromFile(file);
}
} catch (Throwable t) {
logger.warning("error when read : " + file + "+ [" + t.getMessage() + "]");
t.printStackTrace();
}
return outContent;
}
/**
* Extracts text from a Word document and stores it in the document.
*
* @param inputStream An input stream pointing to the Word document to be read.
* @throws IOException
*/
private static char[] loadMSWord(InputStream inputStream) throws IOException {
POIFSFileSystem fs = new POIFSFileSystem(inputStream);
HWPFDocument doc = new HWPFDocument(fs);
WordExtractor we = new WordExtractor(doc);
char[] origText = we.getText().toCharArray();
return origText;
}
/**
* save the converted text (without any processing) to the given file.
*
* @param filename
* @return
*/
public void DOC2Text(String filename) {
try {
File output =
new File(filename); // The text file where you are going to store the extracted data
wr = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(output)));
WordExtractor extractor = new WordExtractor(dc);
String[] fileData = extractor.getParagraphText();
for (int i = 0; i < fileData.length; i++) {
if (fileData[i] != null) wr.write(fileData[i]);
}
wr.close();
} catch (Exception e) {
e.printStackTrace();
}
}
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;
}