private void IText7ReadPDF()
{
StringBuilder text = new StringBuilder();
string fileName = @"C:\Users\Administrator\Desktop\巨力电梯x(3).pdf";
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
//var res = ConvertToHebrew(currentText);
text.Append(currentText);
}
pdfReader.Close();
}
//var read = new iText.Kernel.Pdf.PdfReader(@"C:\Users\Administrator\Desktop\巨力电梯x(3).pdf");
//var doc = new iText.Kernel.Pdf.PdfDocument(read);
//StringBuilder sb = new StringBuilder();
////var info = doc.GetDocumentInfo();
//for (int i = 1; i < doc.GetNumberOfPages(); i++)
//{
// sb.Append(iText.Kernel.Pdf.Canvas.Parser.PdfTextExtractor.GetTextFromPage(doc.GetPage(i)));
//}
//div
//doc.GetDocumentInfo().;
}
private static int LoadAllPDFs(string folder, TextBox TB)
{
int PDFCounter = 0;
StringBuilder text = new StringBuilder();
var files = Directory.GetFiles(folder + @"\");
foreach (var file in files)
{
using (PdfReader pdfReader = new PdfReader(file))
{
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
PDFCounter++;
text.Append("\n{NEWARTICLE}\n");
}
TB.Text = text.ToString();
return(PDFCounter);
}
public static string Mainlog()
{
string strx = string.Empty;
string main = "";
try
{
//adding the pdf to the rich text box
PdfReader reader = new PdfReader("main.pdf");
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strx = strx + s;
}
main = strx;
reader.Close();
}
catch (Exception ex)
{
}
return(main);
}
public static void SetProperties(string filename)
{
Filename = filename;
FileInfo fi = new FileInfo(Filename);
Size = Math.Round(Convert.ToDouble(fi.Length) / (1048576), 2); //1048576=1024*1024
Extension = fi.Extension;
if (Extension == ".pdf")
{
DocumentType = "Portable Document Format(.pdf)";
PdfReader pdfr = new PdfReader(Filename);
StringBuilder pdfText = new StringBuilder();
TotalPages = pdfr.NumberOfPages;
//loop to read pdf page by page
for (int page = 1; page <= pdfr.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfr, page, strategy);
currentText =
Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
pdfText.Append(currentText);
}
pdfr.Close();
string completetext = pdfText.ToString();
// NoOfWords=completetext.Split(' ').Length;
NoOfWords = Regex.Matches(completetext, @"[A-Za-z0-9]+").Count;
}
else if (Extension == ".odt")
{
DocumentType = "Open Document Format(.odt)";
ComputeStatistics();
}
else if (Extension == ".docx")
{
DocumentType = "Microsoft Word Document(.docx)";
ComputeStatistics();
}
else
{
DocumentType = "Word 97-2003 document(.doc)";
ComputeStatistics();
}
}
private List <InvoiceItem> GetFaturaItems(string fileName)
{
var result = new List <InvoiceItem>();
try
{
PdfReader reader = new PdfReader(fileName);
var its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String rawTextV = PdfTextExtractor.GetTextFromPage(reader, 1, its);
var pageVencimento = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(rawTextV)));
var vencimento = GetVencimento(pageVencimento);
for (int pageNumber = 1; pageNumber < reader.NumberOfPages + 1; pageNumber++)
{
its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String rawText = PdfTextExtractor.GetTextFromPage(reader, pageNumber, its);
var page = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(rawText)));
result.AddRange(ParsePage(page, vencimento));
}
reader.Close();
}
catch (Exception)
{
//TODO: Bug Hidden
}
return(result);
}
public string Parse()
{
if (!File.Exists(this._fileName))
{
throw new FileNotFoundException();
}
StringBuilder text = new StringBuilder();
if (File.Exists(_fileName))
{
PdfReader pdfReader = new PdfReader(_fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
text.Append("\r\n");
}
pdfReader.Close();
}
return(text.ToString());
}
private void button1_Click(object sender, EventArgs e)
{
OpenFileDialog dlg = new OpenFileDialog();
string filePath;
dlg.Filter = "PDF Files(*.PDF)|*.PDF|All Files(*.*)|*.*";
if (dlg.ShowDialog() == DialogResult.OK)
{
filePath = dlg.FileName.ToString();
string strText = string.Empty;
try
{
PdfReader reader = new PdfReader(filePath);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
richTextBox1.Text = strText;
}
reader.Close();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
}
/*
* Convert a PDF file to a text by extracting just the text.
*/
public static string Convert(string infile)
{
StringBuilder strPdfContent = new StringBuilder();
PdfReader reader = new PdfReader(infile);
/*
* This conversion code is thanks to the developers of iTextSharp and asturcon at
* http://www.codeproject.com/Questions/770857/Convert-PDF-tp-text-formatted-using-iTextSharp-csh
* Before this was used, manual conversion was done with Adobe Acrobat or Microsoft Word.
* They both convert very badly - missing spaces, linefeeds, reversed lines, etc. Their problems appear
* to be related to how they handle default character encoding on Windows. For an explanation, see:
* https://www.informit.com/guides/content.aspx?g=dotnet&seqNum=163
*/
for (int i = 1; i <= reader.NumberOfPages; i++)
{
ITextExtractionStrategy objExtractStrategy = new SimpleTextExtractionStrategy();
string strLineText = PdfTextExtractor.GetTextFromPage(reader, i, objExtractStrategy);
strLineText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(strLineText)));
strPdfContent.Append(strLineText);
strPdfContent.Append("\n");
}
reader.Close();
string text = strPdfContent.ToString();
return(text);
}
public string ReadPdfFile(string fileName)
{
StringBuilder text = new StringBuilder();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
var datar = pdfReader.AcroFields.Fields.Select(x => x.Key + ": " + pdfReader.AcroFields.GetField(x.Key)).ToList();
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
List <string> dataarr = new List <string>();
dataarr = datar;
XmlSerializer serializer = new XmlSerializer(typeof(List <string>));
using (TextWriter writer = new StreamWriter(_path + "test.xml"))
{
serializer.Serialize(writer, dataarr);
}
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
return(text.ToString());
}
public void GetPDFText(string fileName)
{
StringBuilder text = new StringBuilder();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (int i = 1; i <= pdfReader.NumberOfPages; i++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
texts.Add(currentText);
}
PDFText = text.ToString();
pdfReader.Close();
if (PDFText.Contains(JPM_TAG))
{
data = new JPMData();
}
}
}
public string Open(RichTextBox docBox, Label LabelShowFileName)
{
OpenFileDialog openFileDialog = new OpenFileDialog();
openFileDialog.Filter = "TXT File (*.txt)|*.txt|RTF File (*.rtf)|*.rtf|PDF File (*.pdf)|*.pdf";
if (openFileDialog.ShowDialog() == true)
{
TextRange doc = new TextRange(docBox.Document.ContentStart, docBox.Document.ContentEnd);
LabelShowFileName.Content = System.IO.Path.GetFileName(openFileDialog.FileName);
var textType = System.IO.Path.GetExtension(openFileDialog.FileName).ToLower();
switch (textType)
{
case ".rtf":
{
var text = File.ReadAllText(openFileDialog.FileName, Encoding.GetEncoding(1251));
FlowDocument flowDocument = new FlowDocument();
flowDocument.Blocks.Add(new System.Windows.Documents.Paragraph(new Run(text)));
docBox.Document = flowDocument;
}
break;
case ".txt":
{
var text = File.ReadAllText(openFileDialog.FileName, Encoding.GetEncoding(1251));
FlowDocument flowDocument = new FlowDocument();
flowDocument.Blocks.Add(new System.Windows.Documents.Paragraph(new Run(text)));
docBox.Document = flowDocument;
}
break;
case ".pdf":
{
string strText = string.Empty;
PdfReader reader = new PdfReader(openFileDialog.FileName.ToString());
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
string s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s))); // Encoding s
strText += s;
}
reader.Close();
FlowDocument flowDocument = new FlowDocument();
flowDocument.Blocks.Add(new System.Windows.Documents.Paragraph(new Run(strText)));
docBox.Document = flowDocument;
}
break;
}
}
return(openFileDialog.FileName);
}
//Este metodo lee el PDF
public string ReadPdfFile(object Filename)
{
string strText = string.Empty;
//try para obtener el error en caso de que ocurra
try
{
PdfReader readerPdf = new PdfReader((string)Filename);
for (int page = 1; page <= readerPdf.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader((string)Filename);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
}
//Manejo de errores
catch (Exception ex)
{
//Muestro el error en caso de que ocurra
lblMsjs.ForeColor = Color.Crimson;
lblMsjs.Text = ex.Message.ToString();
}
//retorno el texto
return(strText);
}
/// <summary>
/// Reads the text of the given page
/// put the text in the given StringBuilder
/// </summary>
/// <param name="file"></param>
/// <returns>String builder with the Data</returns>
private StringBuilder ReadText(string file)
{
StringBuilder textBuilder = new StringBuilder();
if (File.Exists(file))
{
PdfReader pdfReader = new PdfReader(file);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(
ASCIIEncoding.Convert(
Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)
));
if (!String.IsNullOrEmpty(currentText))
{
textBuilder.Append(currentText);
}
}
pdfReader.Close();
}
return(textBuilder);
}
/// <summary>
/// Writing the extracted date into textfile.
/// </summary>
/// <param name="reader"> Open reader to the to read pdf file </param>
/// <param name="page"> which page are we going to extract the information from the pdf file </param>
/// <param name="its"> Which extraction strategy do we use when extracting our data </param>
/// <param name="outPath"> Where is the textfile located in my computer </param>
///
private static void WriteInfile(PdfReader reader, int page, ITextExtractionStrategy its, string outPath)
{
string strText = string.Empty;
strText = PdfTextExtractor.GetTextFromPage(reader, page, its);
strText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(strText)));
string[] lines = strText.Split('\n');
foreach (string line in lines)
{
using (System.IO.StreamWriter file = new System.IO.StreamWriter(outPath, true))
{
string test = line + "\0";
int index = test.Length;
if (index > 0 && index < 55 && !char.IsPunctuation(test[index - 2]) && !char.IsDigit(test[0]))
{
Console.WriteLine("TITLE = " + line + " " + index);
file.Write("Title - - - - - ");
file.WriteLine(line + "\n");
}
else
{
file.WriteLine(line);
}
}
}
using (System.IO.StreamWriter file = new System.IO.StreamWriter(outPath, true))
file.WriteLine("- - - - - - - - - - - - - - - - - - - - - - - - - - - ");
}
/// <summary>
/// Get Text from PDF page
/// </summary>
/// <param name="filepath">PDF Filepath</param>
/// <param name="page">Document Page number (optional)</param>
/// <returns>Page Content as Text</returns>
public static string GetPDFPageAsText(string filepath, int page = 1)
{
if (!System.IO.File.Exists(filepath))
{
throw new Exception(Properties.Resources.FileNotFoundError);
}
string content = string.Empty;
// Open a new memory stream
using (var ms = new System.IO.MemoryStream())
{
// Create a new pdf reader and get the first page
PdfReader myPdfReader = new PdfReader(filepath);
if (page < 1 || page > myPdfReader.NumberOfPages)
{
throw new Exception(Properties.Resources.WrongPageNumber);
}
string nonformatcontent = PdfTextExtractor.GetTextFromPage(myPdfReader, page, new SimpleTextExtractionStrategy());
content = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(nonformatcontent)));
}
return(content);
}
public string ReadTextPDF(string path)
{
try
{
PdfReader reader = new PdfReader(path);
int numberPage = reader.NumberOfPages;
StringBuilder textPages = new StringBuilder();
for (int i = 0; i < numberPage; i++)
{
ITextExtractionStrategy textExtractionStrategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
string textPage = PdfTextExtractor.GetTextFromPage(reader, i + 1, textExtractionStrategy);
textPage = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(textPage)));
textPages.Append(textPage);
}
reader.Close();
string txt = textPages.ToString();
return(txt);
}
catch (Exception ex)
{
throw new Exception(ex.Message);
}
}
/// <summary>
/// Get all Text from PDF
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public static string GetEntirePDFAsText(string filepath)
{
if (!System.IO.File.Exists(filepath))
{
throw new Exception(Properties.Resources.FileNotFoundError);
}
string content = string.Empty;
// Open a new memory stream
using (var ms = new System.IO.MemoryStream())
{
// Create a new pdf reader and get the first page
PdfReader myPdfReader = new PdfReader(filepath);
for (int i = 1; i <= myPdfReader.NumberOfPages; i++)
{
string nonformatcontent = PdfTextExtractor.GetTextFromPage(myPdfReader, i, new SimpleTextExtractionStrategy());
string pagebreak = (i > 1) ? "\n" : "";
content += pagebreak + Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(nonformatcontent)));
}
}
return(content);
}
public static string ParsePdf(string filename)
{
if (!File.Exists(filename))
{
throw new FileNotFoundException("fileName");
}
using (PdfReader textreader = new PdfReader(filename))
{
StringBuilder sb = new StringBuilder();
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
for (int page = 0; page < textreader.NumberOfPages; page++)
{
string text = PdfTextExtractor.GetTextFromPage(textreader, page + 1, strategy);
if (!string.IsNullOrWhiteSpace(text))
{
sb.Append(Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(text))));
}
}
string sb_final = sb.ToString();
int new_file_name_index = sb_final.IndexOf("Number");
int startValue = new_file_name_index + 8;
string new_file_name = sb_final.Substring(startValue, 6);
return(new_file_name);
}
}
private void UTF8Encoding(string someText)
{
//throw new NotImplementedException();
//foreach ( ) {
//byte[] utf = Encoding.UTF8.GetBytes(v);
//Console.WriteLine(utf);
// create a string to convert to a byte array...
//String someText = "some ascii text to convert";
Console.WriteLine(someText);
// encode the string as an ASCII byte array
byte[] myASCIIBytes = Encoding.ASCII.GetBytes(someText);
Console.WriteLine(BitConverter.ToString(myASCIIBytes));
// convert the ASCII byte array to a UTF-8 byte array
byte[] myUTF8Bytes = ASCIIEncoding.Convert(Encoding.ASCII, Encoding.UTF8, myASCIIBytes);
Console.WriteLine(BitConverter.ToString(myUTF8Bytes));
// reconstitute a string from the UTF-8 byte array
String deserialisedText = Encoding.UTF8.GetString(myUTF8Bytes);
Console.WriteLine(deserialisedText);
//... only convert ASCII characters in the
// range 0x00 - 0x7F to avoid loss of value.
}
private static async Task <string> ParsePDF(string url, string filename)
{
var text = new StringBuilder();
await Client.DownloadFileTaskAsync(
url, filename);
if (File.Exists(filename))
{
Console.WriteLine("file exists");
var pdfReader = new PdfReader(filename);
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
return(text.ToString());
}
//[Dependency]
//public IF0413Repository F0413Repository { get; set; }
//[Dependency]
//public IF0413Business F0413Business { get; set; }
//[Dependency]
//public IF0414Business F0414Business { get; set; }
public String BuscarDatosPdf(string nombreArchivo)
{
/*path = path + “/ extjs.pdf”;
* string salida = ReadPdfFile(path);
*
* y luego defino el método*/
try
{
PdfReader reader2 = new PdfReader(nombreArchivo);
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader(nombreArchivo);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
reader2.Close();
return(strText);
}
catch (IOException ex)
{
throw new ExportException("Error: No se encuentra el archivo o recurso: " + nombreArchivo + ". --> Traza Original: " + ex.StackTrace);
}
}
public string ParsePdfPage(string fileName)
{
if (fileName.Length == 0)
{
return("");
}
if (fileName.Length > 0)
{
if (!File.Exists(fileName))
{
return("Not found file: " + fileName);
}
pReader = new PdfReader(fileName);
totalPage = pReader.NumberOfPages;
FileInfo f = new FileInfo(fileName);
size = f.Length;
}
StringBuilder sb = new StringBuilder();
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string text = PdfTextExtractor.GetTextFromPage(pReader, pPage, strategy);
if (text.Length > 0)
{
sb.Append(Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(text))));
}
return(sb.ToString());
}
//lines of code required to convert a pdf file to text
private void btn_Convert_Click(object sender, EventArgs e)
{
string filePath;
filePath = textboxFilePath.Text.ToString();
string strText = string.Empty;
try
{
PdfReader reader = new PdfReader(filePath);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
rtxt_Paragraph.Text = strText;
labelFilePath.Text = labelFilePath.Text + @"\" + textboxFileName.Text;
}
reader.Close();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
public string ParsePdf(string fileName)
{
if (!File.Exists(fileName))
{
return("Not found file: " + fileName);
}
using (PdfReader reader = new PdfReader(fileName))
{
StringBuilder sb = new StringBuilder();
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
totalPage = reader.NumberOfPages;
FileInfo f = new FileInfo(fileName);
size = f.Length;
for (int page = 0; page < totalPage; page++)
{
string text = PdfTextExtractor.GetTextFromPage(reader, page + 1, strategy);
if (text.Length > 0)
{
sb.Append(Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(text))));
}
}
reader.Close();
return(sb.ToString());
}
}
//Allows to read inside a PDF to find specific text inside the document
public string GetPDF(string path)
{
StringBuilder text = new StringBuilder();
try
{
if (File.Exists(path))
{
PdfReader pdfReader = new PdfReader(path);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
}
catch (Exception ex)
{
System.Windows.MessageBox.Show("Impossible de lire le fichier" + ex.ToString());
}
return(text.ToString());
}
public string ReadPdfFile(object fileName)
{
//var filename=Server.MapPath("~") +fileName;
var filename = _hostingEnvironment.WebRootPath + (string)fileName;
//var c=GetFileEncoding(filename);
Encoding.RegisterProvider(CodePagesEncodingProvider.Instance);
StringBuilder text = new StringBuilder();
if (File.Exists(filename))
{
PdfReader pdfReader = new PdfReader(filename);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
return(text.ToString());
}
private void button3_Click(object sender, EventArgs e)
{
/*string src = "ejemplo.pdf";
* string dest = "Ejemplo4.pdf";
*
* File.Copy(src,dest);
*
*
* MessageBox.Show("Pdf copiado con exito");*/
String archivo = textBox6.Text;
PdfReader inputDocument = new PdfReader(archivo);
StringBuilder text = new StringBuilder();
for (int page = 1; page <= inputDocument.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(inputDocument, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
inputDocument.Close();
MessageBox.Show(text.ToString());
}
static void Main(string[] args)
{
StringBuilder text = new StringBuilder();
var invoiceLines = new List <string[]>();
//ImageText();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
ImageText();
var strategy = new LocationTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
var strings = currentText.Split('\n');
var invoiceItems = GetInvoiceItems(strings);
WriteExcel(page.ToString(), invoiceItems);
if (invoiceItems.Count == 0)
{
}
}
pdfReader.Close();
}
}
public static void ReadPDFLog(string type, RichTextBox rt)
{
string strx = string.Empty;
string name = "";
if (type == "toDo")
{
name = "todo.pdf";
}
else if (type == "done")
{
name = "done.pdf";
}
try
{
//adding the pdf to the rich text box
PdfReader reader = new PdfReader(name);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strx = strx + s;
rt.Text = strx;
}
reader.Close();
}
catch (Exception ex)
{
MessageBox.Show("No local logs found, please create new");
}
}
public String readTextData(String readText)
{
String str = null;
if (readText.Substring(readText.Length - 3, 3).Equals("pdf"))
{
PdfReader reader = new PdfReader((string)readText);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
str = str + s;
}
reader.Close();
}
else
{
str = System.IO.File.ReadAllText(@readText);
}
str.Replace("\n", " ");
return(str);
}
