public static String extractText(InputStream src) throws IOException {
StringBuilder text = new StringBuilder();
COSDocument cosDoc = null;
PDDocument pdDoc = null;
try {
PDFParser parser = new PDFParser(src);
parser.parse();
cosDoc = parser.getDocument();
PDFTextStripper stripper = new PDFTextStripper();
pdDoc = new PDDocument(cosDoc);
int nbPages = pdDoc.getDocumentCatalog().getPages().getCount();
for (int i = 0; i < nbPages; i++) {
stripper.setStartPage(i + 1);
stripper.setEndPage(i + 1);
text.append(stripper.getText(pdDoc));
}
} finally {
try {
if (cosDoc != null) {
cosDoc.close();
}
} catch (IOException e) {
// Do nada
}
try {
if (pdDoc != null) {
pdDoc.close();
}
} catch (IOException e) {
// Do nada
}
}
return text.toString();
}
private String pdfToText(InputStream in) {
PDFParser parser = null;
PDDocument pdDoc = null;
COSDocument cosDoc = null;
PDFTextStripper pdfStripper;
try {
parser = new PDFParser(in);
parser.parse();
cosDoc = parser.getDocument();
pdfStripper = new PDFTextStripper();
pdDoc = new PDDocument(cosDoc);
return pdfStripper.getText(pdDoc);
// System.out.println(parsedText.replaceAll("[^A-Za-z0-9. ]+", ""));
} catch (Exception e) {
e.printStackTrace();
try {
if (cosDoc != null) cosDoc.close();
if (pdDoc != null) pdDoc.close();
} catch (Exception e1) {
e.printStackTrace();
}
}
return null;
}
public static String getContent(PDFParser parser) throws IOException {
parser.parse();
COSDocument cosDoc = parser.getDocument();
PDFTextStripper pdfStripper = new PDFTextStripper();
PDDocument pdDoc = new PDDocument(cosDoc);
String content = pdfStripper.getText(pdDoc);
cosDoc.close();
pdDoc.close();
return content;
}
/** Extracts the textual contents from a PDF file as one long string. */
public String extractPDFContents(File f) throws IOException {
FileInputStream fi = new FileInputStream(f);
PDFParser parser = new PDFParser(fi);
parser.parse();
fi.close();
COSDocument cd = parser.getDocument();
PDFTextStripper stripper = new PDFTextStripper();
String result = stripper.getText(new PDDocument(cd));
cd.close();
return result;
}
public static String extract(File pdfFile) throws IOException {
checkNotNull(pdfFile, "pdfFile");
PDFParser parser = new PDFParser(new FileInputStream(pdfFile));
parser.parse();
COSDocument cosDoc = parser.getDocument();
PDFTextStripper pdfStripper = new PDFTextStripper();
PDDocument pdDoc = new PDDocument(cosDoc);
pdfStripper.setStartPage(1);
pdfStripper.setEndPage(pdDoc.getNumberOfPages());
pdfStripper.setSortByPosition(true);
String pdfText = pdfStripper.getText(pdDoc);
pdDoc.close();
cosDoc.close();
return pdfText;
}
String pdftoText(String fileName) {
System.out.println("Parsing text from PDF file " + fileName + "....");
File f = new File(fileName);
if (!f.isFile()) {
System.out.println("File " + fileName + " does not exist.");
return null;
}
try {
parser = new PDFParser(new FileInputStream(f));
} catch (Exception e) {
System.out.println("Unable to open PDF Parser.");
return null;
}
try {
parser.parse();
cosDoc = parser.getDocument();
pdfStripper = new PDFTextStripper();
pdDoc = new PDDocument(cosDoc);
parsedText = pdfStripper.getText(pdDoc);
} catch (Exception e) {
System.out.println("An exception occured in parsing the PDF Document.");
e.printStackTrace();
try {
if (cosDoc != null) cosDoc.close();
if (pdDoc != null) pdDoc.close();
} catch (Exception e1) {
e.printStackTrace();
}
return null;
}
System.out.println("Done.");
return parsedText;
}
