// --------------------------------------------------------------------------- /** * Extracts text from a PDF document. * @param src the original PDF document */ public string ExtractText(byte[] src) { PdfReader reader = new PdfReader(src); MyTextRenderListener listener = new MyTextRenderListener(); PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener); PdfDictionary pageDic = reader.GetPageN(1); PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES); processor.ProcessContent( ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic ); return(listener.Text.ToString()); }
// --------------------------------------------------------------------------- /** * Extracts text from a PDF document. * @param src the original PDF document */ public string ExtractText(byte[] src) { PdfReader reader = new PdfReader(src); MyTextRenderListener listener = new MyTextRenderListener(); PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener); PdfDictionary pageDic = reader.GetPageN(1); PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES); processor.ProcessContent( ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic ); return listener.Text.ToString(); }