public void MergePDFs(List <string> sourcePDFs, string outputFile)
{
PDFHelper.DisplayTrialPopupIfNecessary();
foreach (string sourcePDF in sourcePDFs)
{
this.mergeUtility.addSource(sourcePDF);
}
if (!PDFHelper.AddStamp)
{
this.mergeUtility.setDestinationFileName(outputFile);
this.mergeUtility.mergeDocuments();
}
else
{
string str = Path.Combine(Path.GetTempPath(), string.Concat(Path.GetRandomFileName(), ".pdf"));
this.mergeUtility.setDestinationFileName(str);
this.mergeUtility.mergeDocuments();
PDDocument pDDocument = PDDocument.load(new java.io.File(str));
pDDocument = PDFHelper.AddTrialStampIfNecessary(pDDocument);
pDDocument.save(outputFile);
if (pDDocument != null)
{
pDDocument.close();
}
if (System.IO.File.Exists(str))
{
System.IO.File.Delete(str);
}
}
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
/// <summary>
/// Validates the PDF File Downloaded and the text present in the file
/// </summary>
/// <param name="pdfFileName">The folder or filepath.</param>
/// <param name="textToCheck">The text to be validated.</param>
/// <returns>if the text is present or not</returns>
public static bool ExtractAndValidateTextFromPDF(string pdfFileName, string textToCheck)
{
try
{
string result = string.Empty;
bool validateText = false;
PDDocument doc = PDDocument.load(pdfFileName);
PDFTextStripper stripper = new PDFTextStripper();
result = stripper.getText(doc);
doc.close();
if (result.Length != 0)
{
byte[] bytes = Encoding.Default.GetBytes(result.ToString());
string decodedresult = Encoding.UTF8.GetString(bytes);
string outputPDF = decodedresult.Replace(" ", null).Replace("\r", null).Replace("\n", null);
string validationString = textToCheck.Replace(" ", null);
validateText = outputPDF.Contains(validationString);
}
return(validateText);
}
catch (Exception)
{
throw;
}
}
/// <summary>
/// Get a thumbnail of the document, if possible
/// </summary>
/// <param name="sizeX">The maximum X size of the thumbnail</param>
/// <param name="sizeY">The maximum y size of the thumbnail</param>
/// <param name="forceFullSize">True if the thumbnail should be exatly XxY pixels and False if the thumbnail
/// should fit inside a XxY box but should maintain its aspect ratio</param>
/// <returns>A JPEG byte thumbnail or null if the thumbnail can´t be generated</returns>
public override byte[] GetThumbnail(int sizeX, int sizeY, bool forceFullSize)
{
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
return(null);
}
try
{
org.pdfbox.pdfviewer.PageDrawer pagedrawer = new
org.pdfbox.pdfviewer.PageDrawer();
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
int count = doc.getNumberOfPages();
java.util.List pages = doc.getDocumentCatalog().getAllPages();
if (pages.size() > 0)
{
PDPage page = pagedrawer.getPage();
java.awt.image.BufferedImage image = page.convertToImage();
java.io.ByteArrayOutputStream os = new java.io.ByteArrayOutputStream();
ImageIO.write(image, "jpg", os);
byte[] data = os.toByteArray();
return(data);
}
}
catch (Exception e)
{
log.Error("Failed to get the thumbnail from the PDF file " + Name, e);
}
return(null);
}
public override string[] ExtractKeyWordCandidatesFromFile()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract creation date from empty bytes for file " + Name);
return(null);
}
try
{
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
// TODO Internationalize this conversion
text = doc.getDocumentInformation().getKeywords();
}
catch (Exception e)
{
log.Warn("Failed to get the keywords from the PDF file " + Name, e);
}
string[] returnText = null;
if (!string.IsNullOrEmpty(text))
{
returnText = text.Split(new char[] { ',', ';' });
}
return(returnText);
}
public string parsePDF(string filepath)
{
PDDocument document = PDDocument.load(filepath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(document));
}
/// <summary>
/// Get text from the binary using PDFBox
/// </summary>
/// <returns>The text of the binary or null if we could not process the text</returns>
public override string GetTextFromDocumentBinary()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract text from empty bytes for file " + Name);
return(null);
}
try
{
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(doc);
}
catch (Exception e)
{
log.Error("Failed to get the text from the PDF file " + Name, e);
}
return(text);
}
/// <summary>
/// 读取
/// </summary>
/// <param name="file"></param>
/// <returns></returns>
public string Read(IFormFile file)
{
/*var ss = Directory.GetCurrentDirectory();//获取项目路径
* var st = _hostingEnvironment.ContentRootPath;//获取项目路径
* var fileDir = ss+"\\pdf";
* if (Directory.Exists(fileDir))
* {
* Directory.Delete(fileDir,true);
* }
* Directory.CreateDirectory(fileDir);
* //string fileName = file.FileName;
* //string filePath= fileDir + $@"\{fileName}";
* var fileName = DateTime.Now.ToString("yyyyMMddHHmmss") +
* Path.GetExtension(file.FileName);
* var filePath = Path.Combine(fileDir, fileName);
* using (FileStream fs = System.IO.File.Create(filePath))
* {
* file.CopyTo(fs);
* fs.Flush();
* }
* var files = new FileInfo(filePath);*/
// string currentDirectory = Path.GetDirectoryName((new PdfController()).GetType().Assembly.Location);
PDDocument doc = PDDocument.load(@"G:/Read.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
return(text);
}
/// <summary>
/// 通过文件流方式解析PDF
/// </summary>
/// <param name="pdfStream">PDF流</param>
/// <param name="tableContainType">表格包含样式</param>
/// <returns></returns>
public static PDFModel Parser(byte[] pdfStream, TableContainType tableContainType)
{
PDFModel fileContent = null;
//打开文件
PDDocument reader = null;
try
{
InputStream sbs = new ByteArrayInputStream(pdfStream);
reader = PDDocument.load(sbs);
fileContent = Parser(reader, tableContainType);
}
catch (Exception ex)
{
if (reader != null)
{
reader.close();
reader = null;
}
return(null);
}
finally
{
reader.close();
reader = null;
}
return(fileContent);
}
static void Main(string[] args)
{
if (args == null || args.Length < 2)
{
System.Console.WriteLine("Usage: " + AppDomain.CurrentDomain.FriendlyName + " <original PDF filename> <watermark text> [new PDF filename]" + Environment.NewLine +
" For example: " + AppDomain.CurrentDomain.FriendlyName + " myDoc.pdf \"This is a Draft\"");
}
else
{
string origName = args[0];
string watermarkTxt = args[1];
if (!System.IO.File.Exists(origName))
{
System.Console.WriteLine("Error: cannot find the original PDF file(" + origName + "). Please correct the filename or the path and try again.");
}
else
{
PDDocument origDoc = PDDocument.load(new java.io.File(origName)); // NOTE: PDDocument.load() only takes java.io.File, not System.IO.File from C#.Net
PDPageTree allPages = origDoc.getPages();
PDFont font = PDType1Font.HELVETICA_BOLD;
for (int i = 0, len = allPages.getCount(); i < len; ++i)
{
PDPage pg = (PDPage)allPages.get(i);
addWatermarkText(origDoc, pg, font, "This is a draft!!!");
}
origDoc.save("watermarked_" + origName);
origDoc.close();
}
}
}
public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
//ExtractText(pdfStripper, pdfDocument,
// string.Format(@"c:\Users\tri.hoang\Desktop\temp\epub-belastingblad\2014-08\pdf\page_{0}.txt", i.ToString().PadLeft(5, '0')));
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
public PDFValidator(string fileName, string password)
{
try
{
this.IsValid = true;
if (!System.IO.File.Exists(fileName))
{
Console.WriteLine("The PDF file does not Exist.");
}
else
{
PDDocument pDDocument = null;
pDDocument = (!string.IsNullOrEmpty(password) ? PDDocument.load(new java.io.File(fileName), password) : PDDocument.load(new java.io.File(fileName)));
if (pDDocument.isEncrypted())
{
this.IsPasswordProtected = true;
}
this.CheckAllPages(pDDocument);
if (pDDocument != null)
{
pDDocument.close();
}
}
}
catch (InvalidPasswordException invalidPasswordException)
{
this.IsPasswordProtected = true;
this.IsValid = false;
}
catch (Exception exception)
{
this.ErrorMessage = string.Format("PDF analysis failed With exception {0}", exception.Message);
this.IsValid = false;
}
}
private void GetSubFolders(DirectoryInfo sourceDirectoryInfo)
{
DirectoryInfo[] directories = sourceDirectoryInfo.GetDirectories();
for (int i = 0; i < (int)directories.Length; i++)
{
this.GetSubFolders(directories[i]);
}
this.mergeUtility = new PDFMergerUtility();
FileInfo[] files = sourceDirectoryInfo.GetFiles("*.pdf");
for (int j = 0; j < (int)files.Length; j++)
{
FileInfo fileInfo = files[j];
this.mergeUtility.addSource(fileInfo.FullName);
}
if (!PDFHelper.AddStamp)
{
this.mergeUtility.setDestinationFileName(Path.Combine(this.outputFolder, string.Concat(sourceDirectoryInfo.Name, ".pdf")));
this.mergeUtility.mergeDocuments();
}
else
{
string str = Path.Combine(Path.GetTempPath(), string.Concat("aquaforest\\pdftoolkit\\", Path.GetRandomFileName(), ".pdf"));
this.mergeUtility.setDestinationFileName(str);
this.mergeUtility.mergeDocuments();
PDDocument pDDocument = PDDocument.load(new java.io.File(str));
pDDocument = PDFHelper.AddTrialStampIfNecessary(pDDocument);
pDDocument.save(Path.Combine(this.outputFolder, string.Concat(sourceDirectoryInfo.Name, ".pdf")));
if (System.IO.File.Exists(str))
{
System.IO.File.Delete(str);
}
}
}
public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
var text = " ";
try
{
text = stripper.getText(doc);
return(text);
}
catch (UnauthorizedAccessException e)
{
MessageBox.Show("Невозможно скопировать текст из Пдф " + PDFFilePath + ". " + e.Message, "Сообщение об ошибке");
return("");
}
catch (FileLoadException FLe)
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". " + FLe.Message, "Сообщение об ошибке");
return("");
}
catch when(text == "")
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". ", "Сообщение об ошибке");
return("");
}
finally
{
doc.close();
}
}
protected internal String ConvertPDFToDoc(string PDFpath)
{
try
{
PDDocument PDFdoc = null;
PDFTextStripper textstrip = new PDFTextStripper();
String StringDocx = String.Empty;
String DocxPath = String.Empty;
PDFdoc = PDDocument.load(PDFpath);
StringDocx = textstrip.getText(PDFdoc);
PDFdoc.close(); //cierra el pdf
///DocxPath = fn.CreateFolderToSaveDocs(fn.GenerateName()); ///genera la ruta para guardar el archivo.
DocxPath = fn.CreateFolderToSaveDocs(fileName); ///genera la ruta para guardar el archivo.
var wordDoc = DocX.Create(DocxPath);
wordDoc.InsertParagraph(StringDocx);
wordDoc.Save();
////Process.Start("winword.exe", DocxPath);
return(DocxPath);
}
catch (Exception)
{
return("");
}
}
/// <summary>
/// Method for extracting PDF data
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public string ExtractTextFromPdf(string filename)
{
String text = "";
try{
if (checkFileExists(filename))
{
_log.Info(filename + "exists in the download folder");
PDDocument doc = null;
try{
doc = PDDocument.load(getPDFFilePath(filename));
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(doc);
}
catch (Exception e) {
_log.Info("Exception in Extracting data from file " + filename + ".pdf" + e.StackTrace);
_log.Info("Exception in Extracting data from file " + filename + ".pdf" + e.StackTrace);
}
finally{
if (doc != null)
{
doc.close();
}
}
}
else
{
Assert.Fail("PDF file not found in 'Downloads' folder.");
}
}
catch (Exception e) {
_log.Info("Exception in extracting text from PDF: " + e.Message);
}
return(text);
}
/**
* 提取部分页面文本
* @param file pdf文档路径
* @param startPage 开始页数
* @param endPage 结束页数
*/
public static string ExtractTXT(String file, int startPage, int endPage)
{
String content = string.Empty;
try
{
PDDocument document = PDDocument.load(file);
//获取一个PDFTextStripper文本剥离对象
PDFTextStripper stripper = new PDFTextStripper();
// 设置按顺序输出
stripper.setSortByPosition(true);
// 设置起始页
stripper.setStartPage(startPage);
// 设置结束页
stripper.setEndPage(endPage);
//获取文本内容
content = stripper.getText(document);
document.close();
}
catch (java.io.FileNotFoundException ex)
{
}
catch (java.io.IOException ex)
{
}
return(content);
}
public Exception ShowZUGFeRD(string filepath, out string message)
{
try
{
PDDocument doc = PDDocument.load(filepath);
// now check the contents (like MustangReaderTest)
NE4ZUGFeRDImporter zi = new NE4ZUGFeRDImporter();
zi.extract(filepath);
// ZUGFeRD lesen
if (zi.canParse())
{
zi.parse();
// ZUGFeRD Daten als string zurück
message = string.Format("Menge: {0}\nRechnungsempfänger: {1}\nReferenz: {2}",
zi.getAmount(), zi.getHolder(), zi.getForeignReference());
}
else
{
message = "Keine ZUGFeRD Daten gefunden!";
}
//return ok
return(null);
}
catch (Exception ex)
{
message = ex.InnerException.ToString();
return(ex);
}
}
public static Info ReadDocInfo(string fileName)
{
Info result = new Info();
try
{
PDDocument pDoc = PDDocument.load(fileName);
PDDocumentInformation docInfo = pDoc.getDocumentInformation();
if (docInfo != null)
{
var author = docInfo.getAuthor();
var title = docInfo.getTitle();
var summary = docInfo.getSubject();
var keywords = docInfo.getKeywords();
result.Author = author;
result.Title = title;
result.Summary = summary;
result.Keywords = keywords;
}
}
catch (Exception ex)
{
}
return(result);
}
private void btnShowPDF_Click(object sender, EventArgs e)
{
PDDocument PDF = PDDocument.load(textBox1.Text);
PDFTextStripper stripper = new PDFTextStripper();
richTextBox1.Text = (stripper.getText(PDF));
}
private static void KamilPdfTest(string input)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
// stripper.getText(doc);
Matrix line = stripper.getTextLineMatrix();
// int page_nr = stripper.getCurrentPageNo();
PDPage page = stripper.getCurrentPage();
Matrix line2 = stripper.getTextMatrix();
int char_cnt = stripper.getTotalCharCnt();
string article_start = stripper.getArticleStart();
string article_end = stripper.getArticleEnd();
string pdf = stripper.getText(doc); // wrzuca caly tekst do sringa - dziala
char_cnt = pdf.Length;
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
public string parseUsingPDFBox(string input)
{
PDDocument doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
public void ExtractText(string inpufFileName, string outputFileName)
{
#if false
IFilterTextReader.FilterReader reader = new FilterReader(inpufFileName);
var data = reader.ReadToEnd();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(data);
}
#else
PDDocument doc = null;
try
{
doc = PDDocument.load(inpufFileName);
PDFTextStripper stripper = new PDFTextStripper();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(stripper.getText(doc));
}
}
finally
{
if (doc != null)
{
doc.close();
}
}
#endif
}
static void Main(string[] args)
{
PDDocument doc = PDDocument.load("lopreacamasa.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
Console.Write(pdfStripper.getText(doc));
}
private string GetTextFromPdfFile(string fileName)
{
PDDocument doc = PDDocument.load(fileName);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
private static string ReadPdf(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
return(text);
}
public ReportReaderTest_11062013()
{
//
// TODO: Add constructor logic here
//
//doc = PDDocument.load(@"C:\Users\Arnold\Documents\Projects\PSEGet3\trunk\PSEGetTest\stockQuotes_11062013.pdf");
doc = PDDocument.load(@"C:\PSEGet\Reports\stockQuotes_12172013.pdf");
}
public static string PdfFileReader(FileInfo fileName)
{
PDDocument doc = PDDocument.load(fileName.FullName);
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
return(text);
}
public void ToTxt(string absoluteFilePath, string outputPath)
{
using (PDDocument pdf = PDDocument.load(new java.io.File(absoluteFilePath)))
{
Writer output = new PrintWriter(outputPath, "utf-8");
//new PDFDomTree().writeText(pdf, output);
output.close();
}
}
