/// <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);
}
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;
}
}
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();
}
}
}
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);
}
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 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();
}
}
public PdfOcrResult Execute(byte[] bytes)
{
PDDocument document = null;
try
{
LoadPdf(bytes, ref document);
List allPages = document.getDocumentCatalog().getAllPages();
if (allPages.size() == 0)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
//only first page
PDPage page = (PDPage)allPages.get(0);
PDStream contents = page.getContents();
if (contents == null)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
var items = new PdfToCharacters().GetItems(page, page.findResources(), page.getContents().getStream());
if (items.Count == 0)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
var mediaBox = page.findMediaBox();
var height = mediaBox?.getHeight() ?? 0;
var width = mediaBox?.getWidth() ?? 0;
var itemsArray = items.ToArray();
var keywords = "";
try
{
keywords = document.getDocumentInformation()?.getKeywords();
}
catch (Exception) { } // we do not know if PDF box can fail on this, if there is no keywords or something else. We dont really care we just want the keywords if possible.
return(new PdfOcrResult()
{
Items = itemsArray, Height = height, Width = width, Keywords = keywords
});
}
catch (PdfReadException)
{
throw;
}
catch (Exception e)
{
throw new PdfReadException("Pdf could not be loaded. It is not a redable pdf.", e);
}
finally
{
document?.close();
}
}
/// <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;
}
}
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 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
}
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);
}
/**
* 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);
}
/**
* string getFilePath(string path)
* {
* // Specify the path to save the uploaded file to.
* string savePath = "C:\\Users\\DR.AKUL\\Documents\\Visual Studio 2010\\Projects\\PlagijatorFinder\\PlagijatorFinder\\uploadFiles\\";
*
* // Get the name of the file to upload.
* string fileName = FileUpload1.FileName;
*
* // Create the path and file name to check for duplicates.
* path = savePath + fileName + ".txt";
* return path;
* }
**/
private static string parseUsingPDFBox(string filename)
{
PDDocument doc = PDDocument.load(filename);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
doc.close();
return(text);
}
public string ParseFile(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
doc.close();
return(text);
}
private void button_Click(object sender, RoutedEventArgs e)
{
PDDocument doc = null;
Mouse.OverrideCursor = Cursors.Wait;
try
{
doc = PDDocument.load(Properties.Settings.Default.PdfPath);
PDFTextStripper stripper = new PDFTextStripper();
string data = stripper.getText(doc);
MatchCollection match = Regex.Matches(data, "FA\\d{8}", RegexOptions.IgnoreCase);
if (match.Count > 0)
{
try
{
XmlDocument xml = new XmlDocument();
xml.Load(this.filePath.Text);
xml.Save(this.filePath.Text + ".backup");
var manager = new XmlNamespaceManager(xml.NameTable);
manager.AddNamespace("dat", "http://www.stormware.cz/schema/version_2/data.xsd");
int count = 0;
foreach (var item in match)
{
string request = "/dat:dataPack/dat:dataPackItem[@id=\"" + item + "\"]";
try
{
foreach (XmlNode node in xml.SelectNodes(request, manager))
{
node.ParentNode.RemoveChild(node);
count++;
}
}
catch (Exception ex)
{
}
}
xml.Save(this.filePath.Text);
MessageBox.Show("Erased " + count + " items.");
}
catch (Exception ex)
{
MessageBox.Show(ex.Message + "\nPlease check request XPath syntax.", "Error", MessageBoxButton.OK);
}
}
}
finally
{
if (doc != null)
{
doc.close();
}
}
Mouse.OverrideCursor = null;
}
string get_text_from_pdf_by_pdfbox(string path)
{
PDDocument pdffile = PDDocument.load(new java.io.File(path));
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(pdffile);
pdffile.close();
//File.WriteAllText(dst, text, Encoding.GetEncoding("GBK"));
return(text);
}
static private string[] PDFToTextPDFBox(string file, string[] split, StringSplitOptions option)
{
string pdftext = string.Empty;
PDDocument doc = PDDocument.load(file);
PDFTextStripper stripper = new PDFTextStripper();
pdftext = stripper.getText(doc);
doc.close();
return(pdftext.Split(split, option));
}
public void pdfExtract(string keyWord, string path)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(path);
if (doc.isEncrypted())
{
doc.close();
return;
}
PDFTextStripper stripper = new PDFTextStripper();
bool isExist = stripper.getText(doc).ToLower().Contains(keyword);
if (isExist)
{
pdfCount++;
Task.Run(() =>
{
Add_Item(Path.GetFileNameWithoutExtension(path), path, Path.GetExtension(path));
});
Thread.Sleep(200);
}
doc.close();
}
catch
{
try
{
if (doc != null)
{
doc.close();
}
}
catch
{
return;
}
return;
}
}
public static void pdf2txt(string pdfName, string txtfileName)
{
PDDocument doc = PDDocument.load(pdfName);
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
StreamWriter writer = new StreamWriter(txtfileName, false, Encoding.GetEncoding("gb2312"));
writer.Write(text);
writer.Close();
doc.close();
}
private string GetTextFromSimplePdf()
{
PDDocument doc = null;
try
{
doc = PDDocument.load(_location.FullName);
var stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
doc?.close();
}
}
/// <summary>
/// 通过文件名解析PDF
/// </summary>
/// <param name="pdfFileName">PDF文件路径</param>
/// <param name="tableContainType">表格包含样式</param>
/// <returns></returns>
public static PDFModel Parser(string pdfFileName, TableContainType tableContainType)
{
if (!System.IO.File.Exists(pdfFileName))
{
return(null);
}
//打开文件
PDFModel fileContent = null;
PDDocument reader = null;
try
{
reader = PDDocument.load(new java.io.File(pdfFileName));
fileContent = Parser(reader, tableContainType);
}
catch (Exception ex)
{
if (reader != null)
{
reader.close();
reader = null;
}
return(null);
}
finally
{
if (reader != null)
{
reader.close();
reader = null;
}
}
return(fileContent);
}
public static string ReadPdfAsText(string filename)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(filename);
var stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
doc?.close();
}
}
public void SplitByTopLevelBookmarks()
{
if (this.CheckOutput())
{
PDFHelper.DisplayTrialPopupIfNecessary();
try
{
PDDocumentCatalog documentCatalog = this.pdfDocument.PDFBoxDocument.getDocumentCatalog();
PDDocumentOutline documentOutline = documentCatalog.getDocumentOutline();
if (documentOutline != null)
{
PDOutlineItem firstChild = documentOutline.getFirstChild();
PDPageTree pages = documentCatalog.getPages();
List <int> nums = new List <int>();
while (firstChild != null)
{
PDPage pDPage = firstChild.findDestinationPage(this.pdfDocument.PDFBoxDocument);
nums.Add(pages.indexOf(pDPage));
firstChild = firstChild.getNextSibling();
}
nums.Add(pages.getCount());
for (int i = 0; i < nums.Count - 1; i++)
{
int item = nums[i];
int num = nums[i + 1];
PDDocument pDDocument = new PDDocument();
for (int j = item; j < num; j++)
{
pDDocument.addPage(this.pdfDocument.PDFBoxDocument.getPage(j));
}
pDDocument = PDFHelper.AddTrialStampIfNecessary(pDDocument);
string str = string.Format("{0} [{1}].pdf", this.OutputFileName, i);
pDDocument.save(Path.Combine(this.OutputFilePath, str));
pDDocument.close();
}
}
else
{
Console.WriteLine("This document does not contain any bookmarks.");
}
}
catch (Exception exception1)
{
Exception exception = exception1;
throw new PDFToolkitException(exception.Message, exception.InnerException);
}
}
}
/// <summary>
/// Reads the contents from PDF file specified in the file path
/// </summary>
/// <param name="filePath">PDF file path to read the contents</param>
/// <returns>String text</returns>
private string ReadPDF(string filePath)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(filePath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
private static string parseUsingPDFBox(string input)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
private static string ExtractTextFromPdf(string path)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
/// <summary>
/// Returns the text content of the specified PDF
/// </summary>
/// <param name="pdfFilePath">The file path of the pdf</param>
public static string GetPDFText(string pdfFilePath)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(pdfFilePath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
private static string ParseUsingPDFBox(string input)//Strips the text from a pdf, given a filepath.
{
PDDocument doc = null;
try
{
doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
public string Parse(string fileName)
{
//Load in file. Using java.io because pdfbox is ported from java.
var pdfFile = new FileInputStream(fileName);
//Load file into the pdf parser
var pdfParser = new PDFParser(pdfFile);
//Parse the document, so that we can get it for the COSDocument
pdfParser.parse();
/*
COSDocument is the in-memory representation of the PDF.
see https://pdfbox.apache.org/docs/1.8.4/javadocs/org/apache/pdfbox/cos/COSDocument.html
*/
var cosDocument = pdfParser.getDocument();
var pdDocument = new PDDocument(cosDocument);
//Instantiate text stripper.
var pdfTextStripper = new PDFTextStripper();
/* Needed for only stripping specific pages
pdfTextStripper.setStartPage(0);
pdfTextStripper.setEndPage(pdDocument.getNumberOfPages());
*/
//Needed so that we can close the pdDocument before returning from this method
var strippedText = pdfTextStripper.getText(pdDocument);
//This closes all storage and delete the tmp files.
pdDocument.close();
cosDocument.close();
return strippedText;
}
