Convert PDF to TXT to extract Chinese Characters

The following reading method may cause gibberish reading of some PDF files. If you have any other solutions, you can learn them together.

 

Winform code

First, download: product_box

By referencing two dll:
Ikvm. GNU. classpath. dll
PDFBox-0.7.3.dll

Put the two DLL files in the bin directory of the project:
FontBox-0.1.0-dev.dll
Ikvm. runtime. dll

// The referenced space, which can be used only after the dynamic DLL consumed by the Project
Using orgdomainbox. pdmodel;
Using orgdomainbox. util;

// Code in the button event
Private void button2_click (Object sender, system. eventargs E)
{

Pddocument txttmp = pddocument. Load (physical file path)
Extends textstripper extends stripper = new extends textstripper ();
Textbox1.text = javasstripper. gettext (txttmp );
Textbox1.text + = textbox1.text. length;

/* For future reference
Dialogresult DR = folderdialog. showdialog ();
If (Dr! = Dialogresult. OK)
{
Return;
}
// Select the file path
Folderpath = folderdialog. selectedpath;

Directoryinfo dirpdf = new directoryinfo (folderpath );
If (! Dirpdf. exists)
{
MessageBox. Show ("the file path you entered is incorrect. Please verify it! ");
Return;
}

Fileinfo [] fileoldsystem = dirpdf. getfiles ("*. pdf ");
If (fileoldsystem. Length = 0)
{
MessageBox. Show ("the file path you selected does not have a PDF file. Please verify it! ");
Return;
}

Foreach (fileinfo file in fileoldsystem)
{
Pddocument txttmp = pddocument. Load (file. fullname. tolower ());
Extends textstripper extends stripper = new extends textstripper ();
Textbox1.text = javasstripper. gettext (txttmp );
Textbox1.text + = textbox1.text. length;

Streamwriter Sw = file. appendtext (file. fullname. tolower (). Replace (". pdf", ". txt "));
Sw. Write (textbox1.text );
Sw. Flush ();
Sw. Close ();

}

*/

}