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 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++;
}
}
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++;
}
}
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: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
}