public static void Run()
{
// ExStart:ExtractText
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_Text();
// Open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir + "ExtractText.pdf");
// Use parameterless ExtractText method
pdfExtractor.ExtractText();
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetText(tempMemoryStream);
string text = "";
// Specify Unicode encoding type in StreamReader constructor
using (StreamReader streamReader = new StreamReader(tempMemoryStream, Encoding.Unicode))
{
streamReader.BaseStream.Seek(0, SeekOrigin.Begin);
text = streamReader.ReadToEnd();
}
File.WriteAllText(dataDir + "output_out.txt", text);
// ExEnd:ExtractText
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_Text();
//open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir+ "ExtractText-PageRange.pdf");
//specify start and end pages
pdfExtractor.StartPage = 1;
pdfExtractor.EndPage = 1;
//use parameterless ExtractText method
pdfExtractor.ExtractText();
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetText(tempMemoryStream);
string text = "";
//specify Unicode encoding type in StreamReader constructor
using (StreamReader sr = new StreamReader(tempMemoryStream,Encoding.Unicode))
{
sr.BaseStream.Seek(0, SeekOrigin.Begin);
text = sr.ReadToEnd();
}
File.WriteAllText(dataDir+ "output.txt", text);
}
public static void Main()
{
// The path to the documents directory.
string dataDir = Path.GetFullPath("../../../Data/");
//open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir+ "input.pdf");
//use parameterless ExtractText method
pdfExtractor.ExtractText();
int pageNumber = 1;
while (pdfExtractor.HasNextPageText())
{
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetNextPageText(tempMemoryStream);
string text = "";
//specify Unicode encoding type in StreamReader constructor
using (StreamReader streamReader = new
StreamReader(tempMemoryStream, Encoding.Unicode))
{
streamReader.BaseStream.Seek(0, SeekOrigin.Begin);
text = streamReader.ReadToEnd();
}
File.WriteAllText(dataDir+ "output" + pageNumber + ".txt", text);
pageNumber++;
}
}
private void ParsePDF(ref FileObject fo, string filePath)
{
Aspose.Pdf.Document pdfDocument = new Aspose.Pdf.Document(filePath);
PdfFileInfo pi = new PdfFileInfo(pdfDocument);
PdfExtractor pe = new PdfExtractor(pdfDocument);
ImagePlacementAbsorber abs = new ImagePlacementAbsorber();
fo.pageCount = pi.NumberOfPages;
fo.embeddedDocsCount = pdfDocument.EmbeddedFiles.Count;
pdfDocument.Pages.Accept(abs);
fo.imageCount = abs.ImagePlacements.Count;
fo.hasPassword = pi.HasOpenPassword;
pe.ExtractText(Encoding.ASCII);
string tmpFolderToExtract = tmpFolder + "\\" + Guid.NewGuid();
Directory.CreateDirectory(tmpFolderToExtract);
string tmpTextFile = tmpFolderToExtract + "\\" + "tmpTextexport.txt";
pe.GetText(tmpTextFile);
fo.wordCount = GetWordCount(tmpTextFile);
fo.characterCount = GetCharCount(tmpTextFile);
if (File.Exists(tmpTextFile))
{
File.Delete(tmpTextFile);
}
if (Directory.Exists(tmpFolderToExtract))
{
Directory.Delete(tmpFolderToExtract);
}
}
public static void Main()
{
// The path to the documents directory.
string dataDir = Path.GetFullPath("../../../Data/");
//open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir + "input.pdf");
//specify start and end pages
pdfExtractor.StartPage = 1;
pdfExtractor.EndPage = 1;
//use parameterless ExtractText method
pdfExtractor.ExtractText();
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetText(tempMemoryStream);
string text = "";
//specify Unicode encoding type in StreamReader constructor
using (StreamReader sr = new StreamReader(tempMemoryStream, Encoding.Unicode))
{
sr.BaseStream.Seek(0, SeekOrigin.Begin);
text = sr.ReadToEnd();
}
File.WriteAllText(dataDir + "output.txt", text);
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_Text();
//open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir + "ExtractText-Page.pdf");
//use parameterless ExtractText method
pdfExtractor.ExtractText();
int pageNumber = 1;
while (pdfExtractor.HasNextPageText())
{
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetNextPageText(tempMemoryStream);
string text = "";
//specify Unicode encoding type in StreamReader constructor
using (StreamReader streamReader = new
StreamReader(tempMemoryStream, Encoding.Unicode))
{
streamReader.BaseStream.Seek(0, SeekOrigin.Begin);
text = streamReader.ReadToEnd();
}
File.WriteAllText(dataDir + "output" + pageNumber + ".txt", text);
pageNumber++;
}
}
public static void Run()
{
// ExStart:ExtractTextPage
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_Text();
// Open input PDF
PdfExtractor pdfExtractor = new PdfExtractor();
pdfExtractor.BindPdf(dataDir+ "ExtractText-Page.pdf");
// Use parameterless ExtractText method
pdfExtractor.ExtractText();
int pageNumber = 1;
while (pdfExtractor.HasNextPageText())
{
MemoryStream tempMemoryStream = new MemoryStream();
pdfExtractor.GetNextPageText(tempMemoryStream);
string text = "";
// Specify Unicode encoding type in StreamReader constructor
using (StreamReader streamReader = new
StreamReader(tempMemoryStream, Encoding.Unicode))
{
streamReader.BaseStream.Seek(0, SeekOrigin.Begin);
text = streamReader.ReadToEnd();
}
File.WriteAllText(dataDir+ "output" + pageNumber + "_out.txt", text);
pageNumber++;
}
// ExEnd:ExtractTextPage
}
public static void Run()
{
// ExStart:PdfContainsTextOrImages
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_TechnicalArticles();
// Instantiate a memoryStream object to hold the extracted text from Document
MemoryStream ms = new MemoryStream();
// Instantiate PdfExtractor object
PdfExtractor extractor = new PdfExtractor();
// Bind the input PDF document to extractor
extractor.BindPdf(dataDir + "FilledForm.pdf");
// Extract text from the input PDF document
extractor.ExtractText();
bool containsText = false;
bool containsImage = false;
// Save the extracted text to a text file
extractor.GetText(ms);
// Check if the MemoryStream length is greater than or equal to 1
if (ms.Length >= 1)
{
containsText = true;
}
// Extract images from the input PDF document
extractor.ExtractImage();
// Calling HasNextImage method in while loop. When images will finish, loop will exit
if (extractor.HasNextImage())
{
containsImage = true;
}
// Now find out whether this PDF is text only or image only
if (containsText == true && containsImage == false)
{
Console.WriteLine("PDF contains text only");
}
else if (containsText == false && containsImage == true)
{
Console.WriteLine("PDF contains image only");
}
else if (containsText == true && containsImage == true)
{
Console.WriteLine("PDF contains both text and image");
}
else if (containsText == false && containsImage == false)
{
Console.WriteLine("PDF contains neither text or nor image");
}
// ExEnd:PdfContainsTextOrImages
}
public void PdfExtractTextRpdTest(string path, string plus, string code)
{
var pdfExtractor = new PdfExtractor(new ContentImageExtractor());
var rdpExtractor = new RpdContentExtractor(new RpdExtractorConfig(new List <string> {
plus
}, new List <string>(), @"(?<code>\d\d\.0\d\.\d\d)($|\D)"));
var bytes = File.ReadAllBytes(path);
var content = pdfExtractor.ExtractText(bytes, ".pdf");
var extract = rdpExtractor.Extract(content.Content);
Assert.True(extract.Codes.Count > 0);
Assert.AreEqual(code, extract.Codes.First());
Assert.AreEqual(DocumentType.Rpd, extract.DocumentType);
}
public static void Run()
{
// ExStart:PdfContainsTextOrImages
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_TechnicalArticles();
// Instantiate a memoryStream object to hold the extracted text from Document
MemoryStream ms = new MemoryStream();
// Instantiate PdfExtractor object
PdfExtractor extractor = new PdfExtractor();
// Bind the input PDF document to extractor
extractor.BindPdf(dataDir + "FilledForm.pdf");
// Extract text from the input PDF document
extractor.ExtractText();
bool containsText = false;
bool containsImage = false;
// Save the extracted text to a text file
extractor.GetText(ms);
// Check if the MemoryStream length is greater than or equal to 1
if (ms.Length >= 1)
containsText = true;
// Extract images from the input PDF document
extractor.ExtractImage();
// Calling HasNextImage method in while loop. When images will finish, loop will exit
if (extractor.HasNextImage())
containsImage = true;
// Now find out whether this PDF is text only or image only
if (containsText == true && containsImage == false)
Console.WriteLine("PDF contains text only");
else if (containsText == false && containsImage == true)
Console.WriteLine("PDF contains image only");
else if (containsText == true && containsImage == true)
Console.WriteLine("PDF contains both text and image");
else if (containsText == false && containsImage == false)
Console.WriteLine("PDF contains neither text or nor image");
// ExEnd:PdfContainsTextOrImages
}
public static void Run()
{
// ExStart:PdfExtractorFeatures
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_TechnicalArticles();
// Create an instance of PdfExtractor class
PdfExtractor extractor = new PdfExtractor();
// Set PDF file password
extractor.Password = "";
// Specify start and end pages of the PDF
extractor.StartPage = 1;
extractor.EndPage = 10;
// Bind PDF file with the extractor object
extractor.BindPdf(dataDir + "inFile.pdf");
// Extract all text from the PDF
extractor.ExtractText();
// Save extracted text in a text file
extractor.GetText(dataDir + "PdfExtractorFeatures_text_out_.txt");
// Text of individual pages can also be saved individually in single text files
if (extractor.HasNextPageText())
{
extractor.GetNextPageText(dataDir + DateTime.Now.Ticks.ToString() + "_out_.txt");
}
// Extract images from PDF file
extractor.ExtractImage();
// Save each individual image in an image file
if (extractor.HasNextImage())
{
extractor.GetNextImage(dataDir + DateTime.Now.Ticks.ToString() + "_out_.jpg", System.Drawing.Imaging.ImageFormat.Jpeg);
}
// Extract attachments
extractor.ExtractAttachment();
extractor.GetAttachment(dataDir);
// ExEnd:PdfExtractorFeatures
}
public static void Run()
{
// ExStart:PdfExtractorFeatures
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdfFacades_TechnicalArticles();
// Create an instance of PdfExtractor class
PdfExtractor extractor = new PdfExtractor();
// Set PDF file password
extractor.Password = "";
// Specify start and end pages of the PDF
extractor.StartPage = 1;
extractor.EndPage = 10;
// Bind PDF file with the extractor object
extractor.BindPdf( dataDir + "inFile.pdf");
// Extract all text from the PDF
extractor.ExtractText();
// Save extracted text in a text file
extractor.GetText(dataDir + "PdfExtractorFeatures_text_out.txt");
// Text of individual pages can also be saved individually in single text files
if (extractor.HasNextPageText())
{
extractor.GetNextPageText(dataDir + DateTime.Now.Ticks.ToString() + "_out.txt");
}
// Extract images from PDF file
extractor.ExtractImage();
// Save each individual image in an image file
if (extractor.HasNextImage())
{
extractor.GetNextImage(dataDir + DateTime.Now.Ticks.ToString() + "_out.jpg", System.Drawing.Imaging.ImageFormat.Jpeg);
}
// Extract attachments
extractor.ExtractAttachment();
extractor.GetAttachment(dataDir);
// ExEnd:PdfExtractorFeatures
}
private void pdf_to_txt(save_progress progress, System.Windows.Forms.Form dlg, string fileType)
{
try
{
Aspose.Pdf.Document document = null;
int num = 0;
if (fileType == ".pdf")
{
document = this.pdf_doc;
num = 0;
}
else if ((fileType == ".doc") || (fileType == ".docx"))
{
document = this.doc_to_pdf(progress, dlg, 0);
num = 50;
}
else if ((fileType == ".xls") || (fileType == ".xlsx"))
{
document = this.xls_to_pdf(progress, dlg, 0);
num = 50;
}
else if ((fileType == ".ppt") || (fileType == ".pptx"))
{
document = this.ppt_to_pdf(progress, dlg, 0);
num = 50;
}
PdfExtractor extractor = new PdfExtractor(document);
FileStream outputStream = new FileStream(this.global_config.target_dic + Path.GetFileNameWithoutExtension(this.file_path) + this.get_suffix(), FileMode.Create);
extractor.ExtractTextMode = 0;
if (progress != null)
{
dlg.Invoke(progress, new object[] { num });
}
for (int i = 1; i <= document.Pages.Count; i++)
{
extractor.StartPage = i;
extractor.EndPage = i;
extractor.ExtractText(Encoding.UTF8);
extractor.GetText(outputStream);
if (progress != null)
{
if (num == 50)
{
dlg.Invoke(progress, new object[] { ((i * 50) / document.Pages.Count) + 50 });
}
else
{
dlg.Invoke(progress, new object[] { (i * 100) / document.Pages.Count });
}
}
}
outputStream.Close();
}
catch (Exception)
{
return;
}
if (progress != null)
{
dlg.Invoke(progress, new object[] { 100 });
}
}