private IEnumerable <KeyValuePair <string, int> > searchDocuments(string keyword, int topCount)
{
var files = Directory.GetFiles(@"BotApp\Docs\");
Dictionary <string, int> docsFound = new Dictionary <string, int>();
foreach (var file in files)
{
PdfReader pdfReader = new PdfReader(file);
var occurences = 0;
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
occurences += currentPageText.Split(' ').Count(i => i.Equals(keyword) || i.Contains(keyword) || i.Equals(keyword.ToLower()) || i.Contains(keyword.ToLower()));
}
pdfReader.Close();
docsFound.Add(file, occurences);
}
var foundDocsWithEntity = docsFound.Where(i => i.Value > 0);
foundDocsWithEntity.OrderByDescending(i => i.Value);
if (foundDocsWithEntity.Count() >= topCount)
{
return(foundDocsWithEntity.Take(topCount));
}
else
{
return(foundDocsWithEntity);
}
}
//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 LeArquivo(string fileName)
{
var text = new StringBuilder();
// The PdfReader object implements IDisposable.Dispose, so you can
// wrap it in the using keyword to automatically dispose of it
using (var pdfReader = new PdfReader(fileName))
{
// Loop through each page of the document
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(
pdfReader,
page,
strategy);
currentText =
Encoding.UTF8.GetString(Encoding.Convert(
Encoding.Default,
Encoding.UTF8,
Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
}
return(text.ToString());
}
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();
}
}
/// <summary>
/// Read pdf and return content as string.
/// </summary>
/// <param name="options"></param>
/// <param name="cancellationToken"></param>
/// <returns>Object { string Content }</returns>
public static Output ReadPdf([PropertyTab] Options options, CancellationToken cancellationToken)
{
var text = new StringBuilder();
using (var reader = options.ReadFromFile ? new iText.Kernel.Pdf.PdfReader(options.PdfLocation) : new iText.Kernel.Pdf.PdfReader(new MemoryStream(options.InputBytes)))
{
// For possible form flattening.
var writer = new PdfWriter(new MemoryStream());
var doc = new PdfDocument(reader, writer);
var form = iText.Forms.PdfAcroForm.GetAcroForm(doc, false);
if (form != null)
{
form.FlattenFields();
}
if (options.Page == 0)
{
for (var i = 1; i <= doc.GetNumberOfPages(); i++)
{
cancellationToken.ThrowIfCancellationRequested();
var strategy = new SimpleTextExtractionStrategy();
text.Append(PdfTextExtractor.GetTextFromPage(doc.GetPage(i), strategy));
}
}
else
{
var strategy = new SimpleTextExtractionStrategy();
text.Append(PdfTextExtractor.GetTextFromPage(doc.GetPage(options.Page), strategy));
}
}
return(new Output {
Content = text.ToString()
});
}
public static string pdfText(string path)
{
PdfReader reader = new PdfReader(path);
string text = string.Empty;
for (int page = 1; page <= reader.NumberOfPages; page++)
{
text = PdfTextExtractor.GetTextFromPage(reader, page);//\n
iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy itp = new SimpleTextExtractionStrategy();
//char[] delimiters = new char[] { '\n', '|', '\r' };
string[] strArray = text.Split('\n');
foreach (var item in strArray)
{
if (item.Contains("Sample No"))
{
string strItem = item.Replace("Sample No", "");
string[] sampleItems = strItem.Split('\t');
string[] sampleItems1 = strItem.Split(' ');
}
if (item.Contains("Oil on Label"))
{
string strOilItem = item.Replace("Oil on Label", "");
string[] oilItems = strOilItem.Split('\t');
string[] oilItems1 = strOilItem.Split(' ');
}
}
}
reader.Close();
return(text);
}
private string getContent(PdfReader pdfReader, string page)
{
string pdfText = null;
int pageCount = pdfReader.NumberOfPages;
if (page == "全部")
{
for (int pg = 1; pg <= pageCount; pg++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);
pdfText += value;
}
}
else
{
for (int pg = 1; pg <= pageCount; pg++)
{
if (Convert.ToInt32(page) == pg)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);
pdfText = value;
break;
}
}
}
return(pdfText);
}
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 GetText(string FileName)
{
try
{
PdfReader reader = new PdfReader(FileName);
int numberPage = reader.NumberOfPages;
StringBuilder textPages = new StringBuilder();
for (int i = 0; i < numberPage; i++)
{
ITextExtractionStrategy textExtractionStrategy = new 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();
return(textPages.ToString());
}
catch (Exception ex)
{
throw new Exception(ex.Message);
}
}
/// <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);
}
public void openpdf(string fn)
{
try
{
// FileStream fs=new FileStream(fn,FileMode.Create,FileAccess.Write,FileShare.None);
var text = new StringBuilder();
PdfReader pdfr = new PdfReader(fn);
for (int i = 1; i <= pdfr.NumberOfPages; i++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(pdfr, i, strategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
inputTextBox.Text = text.ToString();
}
catch (Exception ex)
{
MessageBox.Show("Error Occured: " + ex.Message);
}
// MessageBox.Show("PDF file is opened");
}
/*
* public static string SpirePDF(string inputFileName, string outputFileName)
* {
* //The Spire Returns a watermark
* PdfDocument document = new PdfDocument();
* document.LoadFromFile(inputFileName);
*
* //Save doc file to html
* document.SaveToFile(outputFileName, FileFormat.HTML);
*
* return "success";
* }
*/
public static string ConvertPdf(string inputFileName, string outputFileName)
{
if (string.IsNullOrEmpty(inputFileName) || string.IsNullOrEmpty(outputFileName))
{
return("File name error");
}
else if (!File.Exists(inputFileName))
{
return("File is not exist");
}
else
{
PdfReader pr = new PdfReader(inputFileName);
int maxPage = pr.NumberOfPages;
pr.Close();
StreamWriter outFile = new StreamWriter(outputFileName, true, System.Text.Encoding.UTF8);
int page = 1;
while (page <= maxPage)
{
ITextExtractionStrategy its = new SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader(inputFileName);
outFile.Write(PdfTextExtractor.GetTextFromPage(reader, page, its));
reader.Close();
page++;
}
outFile.Close();
}
return("success");
}
private async Task <string> pdfTextExtract(string sFilePath)
{
string texto;
try
{
PdfReader reader = new PdfReader(sFilePath);
iText.Kernel.Pdf.PdfDocument pdf = new iText.Kernel.Pdf.PdfDocument(reader);
texto = string.Empty;
for (int page = 1; page <= pdf.GetNumberOfPages(); page++)
{
ITextExtractionStrategy its = new SimpleTextExtractionStrategy();
String s = PdfTextExtractor.GetTextFromPage(pdf.GetPage(page), its);
//s = System.Text.Encoding.UTF8.GetString(ASCIIEncoding.Convert(System.Text.Encoding.Default, System.Text.Encoding.UTF8, System.Text.Encoding.Default.GetBytes(s)));
texto = texto + s;
}
reader.Close();
}
catch (Exception Ex)
{
await new MessageDialog("Error al abrir archivo: " + Ex.Message).ShowAsync();
return(null);
}
return(texto);
}
// metodo para obter o conteudo do arquivo pdf com base num path ftp
public static string GetContentFilePdfFTP(string fileName)
{
StringBuilder text = new StringBuilder();
try
{
using (WebClient request = new WebClient())
{
request.Credentials = new NetworkCredential("tce\\usr_sharepoint", "@(tce)");
byte[] fileData = request.DownloadData("ftp://10.140.100.55/se" + fileName);
using (PdfReader reader = new PdfReader(fileData))
{
var strategy = new SimpleTextExtractionStrategy();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
var currentPageText = PdfTextExtractor.GetTextFromPage(reader, page, strategy);
text.Append(RemoverAcentos(currentPageText));
}
}
}
}
catch (WebException ex)
{
}
int maxPermitidoString = 65535;
int conteudoPDFLimite = (text.Length > maxPermitidoString) ? maxPermitidoString : text.Length;
return(text.ToString(0, conteudoPDFLimite));
}
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 static string GetAttendeeName(string fileName)
{
string text = string.Empty;
try
{
PdfReader pdfReader = new PdfReader(fileName);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
text = PdfTextExtractor.GetTextFromPage(pdfReader, 1, strategy);
text = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(text)));
pdfReader.Close();
if (text.Contains("\n"))
{
text = text.Substring(0, text.IndexOf("\n")).Trim();
}
}
catch (Exception ex)
{
ShowErrorMessage(ex, "getting attendee name");
}
return(text);
}
public string GetPdfContent(string filePath)
{
try
{
string pdffilename = filePath;
PdfReader pdfReader = new PdfReader(pdffilename);
int numberOfPages = pdfReader.NumberOfPages;
string text = string.Empty;
for (int i = 1; i <= numberOfPages; ++i)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
text += PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy);
}
pdfReader.Close();
return(text);
}
catch (Exception ex)
{
//StreamWriter wlog = File.AppendText(System.AppDomain.CurrentDomain.SetupInformation.ApplicationBase + "\\mylog.log");
//wlog.WriteLine("出错文件：" + "原因：" + ex.ToString());
//wlog.Flush();
//wlog.Close();
return(null);
}
}
/*
* 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 static void ReadPdfFile(string inputFileName)
{
if (File.Exists(inputFileName))
{
PdfReader pdfReader = new PdfReader(inputFileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
StringBuilder text = new StringBuilder();
if (Regex.Match(currentText, @"说(\s+)*明(\s+)*书(\s+)*附").Success)
{
OutValues.Add(new OutputValue
{
FileName = System.IO.Path.GetFileNameWithoutExtension(inputFileName),
TotalPageCount = pdfReader.NumberOfPages,
DrawingsStarts = page.ToString(),
DrawingsEnds = pdfReader.NumberOfPages.ToString()
});
return;
}
text.Append(currentText);
}
OutValues.Add(new OutputValue
{
FileName = System.IO.Path.GetFileNameWithoutExtension(inputFileName),
TotalPageCount = pdfReader.NumberOfPages,
DrawingsStarts = "NOT FOUND",
DrawingsEnds = "NOT FOUND"
});
pdfReader.Close();
}
}
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 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());
}
public static async Task Run(Stream myBlob, string name, TraceWriter log)
{
log.Info($"Text Processing beginning for {name} ({myBlob.Length} Bytes)");
var reader = new PdfReader(myBlob);
var extractionStrategy = new SimpleTextExtractionStrategy();
log.Info($"Extracting text from the PDF");
List <dynamic> pages = new List <dynamic>();
StringBuilder content = new StringBuilder();
for (int i = 1; i <= Math.Min(1000, reader.NumberOfPages); i++)
{
string page = PdfTextExtractor.GetTextFromPage(reader, i, extractionStrategy);
content.AppendLine(page);
pages.Add(new { id = i.ToString(), text = page.Substring(0, Math.Min(4096, page.Length)) });
}
log.Info($"Finding key phrases");
Dictionary <string, int> keyPhrases = await GetKeyPhrases(pages, log);
var top10Phrases = keyPhrases.OrderByDescending(pair => pair.Value).Take(10).Select(kp => kp.Key);
log.Info($"Building summary");
string summary = BuildSummary(content.ToString(), top10Phrases);
SearchServiceClient serviceClient = new SearchServiceClient(SearchServiceName, new SearchCredentials(SearchServiceAPIKey));
ISearchIndexClient indexClient = serviceClient.Indexes.GetClient(IndexName);
string documentId = HttpServerUtility.UrlTokenEncode(Encoding.UTF8.GetBytes(name));
log.Info($"Uploading document to Azure Search using ID: {documentId}");
await UploadToAzureSeearch(indexClient, documentId, keyPhrases.Keys.ToList(), summary, log);
}
/// <summary>
/// Extracts a text from a PDF file.
/// </summary>
/// <param name="fileName">The full path to the pdf file.</param>
/// <param name="success">Indicate if operation was successfull.</param>
/// <returns>The extracted text.</returns>
internal static String ExtractText(String fileName, out bool success)
{
String result = String.Empty;
PdfReader reader = null;
success = false;
try
{
reader = new PdfReader(fileName);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
for (int page = 1; page <= reader.NumberOfPages; page++)
{
SimpleTextExtractionStrategy strategy = parser.ProcessContent(page, new SimpleTextExtractionStrategy());
result += strategy.GetResultantText();
}
success = true;
return result;
}
catch (Exception)
{
return String.Empty;
}
finally
{
if (reader != null)
{
reader.Close();
}
}
}
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);
}
}
public static string GetText(string filePath)
{
var sb = new StringBuilder();
try
{
using (PdfReader reader = new PdfReader(filePath))
{
string prevPage = "";
for (int page = 1; page <= reader.NumberOfPages; page++)
{
ITextExtractionStrategy its = new SimpleTextExtractionStrategy();
var s = PdfTextExtractor.GetTextFromPage(reader, page, its);
if (prevPage != s)
{
sb.Append(s);
}
prevPage = s;
}
reader.Close();
}
}
catch (Exception e)
{
throw e;
}
return(sb.ToString());
}
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());
}
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 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());
}
}
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());
}
public string GetText(string filePath)
{
using (var reader = new PdfReader(filePath))
{
using (var pdfDoc = new PdfDocument(reader))
{
var text = new StringBuilder();
for (var page = 1; page <= pdfDoc.GetNumberOfPages(); page++)
{
var strategy = new SimpleTextExtractionStrategy();
var pageContent = PdfTextExtractor.GetTextFromPage(pdfDoc.GetPage(page), strategy);
text.Append(pageContent);
}
var fileTextWithoutNewLine = new Regex("[\r\n]+").Replace(text.ToString(), " ");
var fileText = new Regex("[^a-zA-Z0-9 -]").Replace(fileTextWithoutNewLine, "");
var regex = new Regex("[^\\s]+");
var words = regex.Matches(fileText).Cast <Match>().Select(m => m.Value.ToLower());
return(string.Join(" ", words));
}
}
}
