You can extract pages, text and Images from a PDF document and save them to a separate file. This tutorial guides you to extract pages, text and images from the PDF document. Follow these links to explore each one of them.
2. Extract Text
PDFtoolkit has the "ExtractPagesTo" function, which facilitates extracting pages from a currently loaded document into another document. The following example creates Output.pdf by extracting pages 1 to 10 from Doc1.pdf.
[VB]
gtPDFDocumentX1.LoadFromFile ("Doc1.pdf")
gtPDFDocumentX1.ExtractPagesTo "Output.pdf", "1-10"
[VC++]
m_PDF.LoadFromFile ("Doc1.pdf");
m_PDF.ExtractPagesTo( "Output.pdf", "1-10");
[VB]
' Load input file
PDFDoc.LoadFromFile (InputFile1)
Dim str() As String
Dim AllStr As String
Dim i As Integer
'Extract the formatted text from page 1.
str = PDFDoc.ExtractText("1")
AllStr = ""
For i = 0 To UBound(str) - 1
AllStr = AllStr + str(i)
Next i
MsgBox AllStr, , "Demo for ExtractText"
[VC++]
PDFDoc.LoadFromFile(InputFile1);
CString * str;
char * AllStr;
char Num[10];
unsigned Long N, size;
tagVARIANT myVar;
myVar = PDFDoc.ExtractText("1");
str = GetStringsFromVariant(myVar,N);
itoa(N,Num,10);
int i, j, k;
i=j=k=size = 0;
For (i=0 ; i< N; i++)
{
size = size + strlen(str[i]);
}
AllStr = New char [size];
For (i=0 ; i< N; i++)
{
For(int j= 0; j< strlen(str[i]);j++)
{
AllStr[k] = str[i][j];
k++;
}
}
MessageBox(AllStr);
[CS]
// Load Input file
PDFDoc.LoadFromFile(InputFile1);
String [] Str;
String AllStr;
//Extracting Text And storing into Str[].
Str = (String []) PDFDoc.ExtractText("1");
AllStr = "";
For(int i=0; i< Str.Length; i++)
AllStr = AllStr + Str[i];
MessageBox.Show(AllStr,"Demo for ExtractText");
PDFDoc.ResetDocument();
[VB]
' Load input file
PDFDoc.LoadFromFile (InputFile1)
Dim str() As String
Dim AllStr As String
Dim i As Integer
'Extract the formatted text from page 1.
str = PDFDoc.ExtractTextFormatted(1)
AllStr = ""
For i = 0 To UBound(str) - 1
AllStr = AllStr + str(i)
Next i
MsgBox AllStr, , "Demo for ExtractText"
PDFDoc.ResetDocument
[VC++]
PDFDoc.LoadFromFile(InputFile1);
CString * str;
char * AllStr;
char Num[10];
unsigned Long N, size;
tagVARIANT myVar;
myVar = PDFDoc.ExtractTextFormatted(1);
str = GetStringsFromVariant(myVar,N);
itoa(N,Num,10);
int i, j, k;
i=j=k=size = 0;
For (i=0 ; i< N; i++)
{
size = size + strlen(str[i]);
}
AllStr = New char [size];
For (i=0 ; i< N; i++)
{
For(int j= 0; j< strlen(str[i]);j++)
{
AllStr[k] = str[i][j];
k++;
}
}
MessageBox(AllStr);
[CS]
// Load Input file
PDFDoc.LoadFromFile(InputFile1);
String [] Str;
String AllStr;
//Extract the formatted Text from page 1.
Str = (String []) PDFDoc.ExtractText("1");
AllStr = "";
For(int i=0; i< Str.Length; i++)
AllStr = AllStr + Str[i];
MessageBox.Show(AllStr,"Demo for ExtractText");
PDFDoc.ResetDocument();
[VB]
'this code segment makes use of MSFlexGrid
Dim TXTELE As gtPDFTextElementX
Dim i, j As Integer
PDFDoc.LoadFromFile FileName
On Error Resume Next
j = 0
For i = 0 To PDFDoc.GetTotalPDFElementsInPage(1) - 1
If PDFDoc.GetPDFElementTypeAt(i, 1) = TxPDFElementType.etText Then
Set TXTELE = PDFDoc.GetPDFTextElementAt(i, 1)
MSFlexGrid1.TextMatrix(j + 1, 0) = i
MSFlexGrid1.TextMatrix(j + 1, 1) = "Text"
MSFlexGrid1.TextMatrix(j + 1, 2) = TXTELE.XCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 3) = TXTELE.YCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 4) = TXTELE.Text
j = j + 1
End If
If (j + 2) > MSFlexGrid1.Rows - 1 Then
MSFlexGrid1.Rows = MSFlexGrid1.Rows + 1
End If
Next
[VC++]
//this code segment makes use of MSFlexGrid
CgtPDFTextElementX TXTELE;
int i, j;
PDFDoc->LoadFromFile(InputFile);
j = 0;
for(i = 0; i < PDFDoc->GetTotalPDFElementsInPage(1); i++)
{
try
{
if(PDFDoc->GetPDFElementTypeAt(i, 1) == 0 /*etText*/ )
{
TXTELE = PDFDoc->GetPDFTextElementAt(i, 1);
msflxgrd.SetTextMatrix(j + 1, 0, I2S(i));
msflxgrd.SetTextMatrix(j + 1, 1, "Text");
msflxgrd.SetTextMatrix(j + 1, 2, D2S(TXTELE.GetXCordOrigin()));//see the function D2S below
msflxgrd.SetTextMatrix(j + 1, 3, D2S(TXTELE.GetYCordOrigin()));
msflxgrd.SetTextMatrix(j + 1, 4, TXTELE.GetText());
j = j + 1;
}
if((j + 2) > (msflxgrd.GetRows()- 1))
msflxgrd.SetRows(msflxgrd.GetRows() + 1);
}
catch (CException * E)
{
char Error[255];
E->GetErrorMessage(Error, 255);
AfxMessageBox(Error);
}
}
// the following function converts double value to string type
LPTSTR D2S(double d)
{
LPTSTR s;
s = new char[20];
gcvt( d, 10, s);
return s;
}
[CS]
//this code segment uses ListView
ListViewItem lstViewItem;
PDFDoc.LoadFromFile(InputFile);
gtPDFTextElementX TXTELE;
for(int i= 0; i< PDFDoc.GetTotalPDFElementsInPage(1) ;i++)
{
try
{
if(PDFDoc.GetPDFElementTypeAt(i,1)== TxPDFElementType.etText)
{
TXTELE = PDFDoc.GetPDFTextElementAt(i,1);
lstViewItem = ListView1.Items.Add(i.ToString());
lstViewItem.SubItems.Add("Text");
lstViewItem.SubItems.Add(TXTELE.XCordOrigin.ToString());
lstViewItem.SubItems.Add(TXTELE.YCordOrigin.ToString());
lstViewItem.SubItems.Add(TXTELE.Text);
}
}
catch (Exception E)
{
//continue;
MessageBox.Show(E.Message);
}
}
[VB]
Dim IMGELE As gtPDFImageElementX
Dim i As Integer
gtPDFDocumentX1.LoadFromFile("Input.pdf")
For i = 0 To gtPDFDocumentX1.GetTotalPDFElementsInPage(1) - 1
If gtPDFDocumentX1.GetPDFElementTypeAt(i, 1) = TxPDFElementType.etImage Then
Set IMGELE = gtPDFDocumentX1.GetPDFImageElementAt(i, 1)
If IMGELE.IsBMPImage Then
Picture1.Picture = IMGELE.Image
IMGELE.SaveToFile("Image.bmp")
ElseIf IMGELE.IsJPEGImage Then
Picture1.Picture = IMGELE.Image
IMGELE.SaveToFile("Image.jpeg")
End If
End If
Next
PDFDoc.LoadFromFile FileName
[VC++]
CgtPDFImageElementX IMGELE;
int i;
PDFDoc.LoadFromFile(InputFile);
For(i= 0; i< PDFDoc.GetTotalPDFElementsInPage(1) ;i++)
{
If(PDFDoc->GetPDFElementTypeAt(i,1)== etImage)
{
If(IMGELE.GetIsBMPImage())
IMGELE.SaveToFile("Image.bmp");
If(IMGELE.GetIsJPEGImage())
IMGELE.SaveToFile("Image.jpeg");
}
}
[CS]
gtPDFImageElementX IMGELE;
For(int i= 0; i< PDFDoc.GetTotalPDFElementsInPage(1) ;i++)
{
If(PDFDoc.GetPDFElementTypeAt(i,1)== TxPDFElementType.etImage)
{
IMGELE = PDFDoc.GetPDFImageElementAt(i,1);
If(IMGELE.IsJPEGImage)
IMGELE.SaveToFile("Image.jpeg");
If(IMGELE.IsBMPImage)
IMGELE.SaveToFile("Image.bmp");
}
}
[VB]
'This code segment uses MSFlexGrid
Dim FRMELE As gtPDFFormElementX
Dim i, j As Integer
PDFDoc.LoadFromFile FileName
On Error Resume Next
j = 0
For i = 0 To PDFDoc.GetTotalPDFElementsInPage(1) - 1
If PDFDoc.GetPDFElementTypeAt(i, 1) = TxPDFElementType.etForm Then
Set FRMELE = PDFDoc.GetPDFFormElementAt(i, 1)
MSFlexGrid1.TextMatrix(j + 1, 0) = i
MSFlexGrid1.TextMatrix(j + 1, 1) = "Form"
MSFlexGrid1.TextMatrix(j + 1, 2) = FRMELE.FormFieldBox.XCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 3) = FRMELE.FormFieldBox.YCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 4) = FRMELE.FieldName
MSFlexGrid1.TextMatrix(j + 1, 5) = FRMELE.Text.Text
MSFlexGrid1.TextMatrix(j + 1, 6) = FieldTypes(FRMELE.FieldType)
j = j + 1
End If
If (j + 2) > MSFlexGrid1.Rows - 1 Then
MSFlexGrid1.Rows = MSFlexGrid1.Rows + 1
End If
Next
[VC++]
//This code segment uses MSFlexGrid
int i, j;
PDFDoc->LoadFromFile(InputFile);
int Tot = PDFDoc->GetTotalPDFElementsInPage(1);
j = 0;
CgtPDFFormElementX FRMELE;
for(i = 0; i < Tot; i++)
{
try
{
if(PDFDoc->GetPDFElementTypeAt(i, 1) == 3 /*etForm*/ )
{
FRMELE = PDFDoc->GetPDFFormElementAt(i, 1);
msflxgrd.SetTextMatrix(j + 1, 0, I2S(i));
msflxgrd.SetTextMatrix(j + 1, 1, "Form");
msflxgrd.SetTextMatrix(j + 1, 2, D2S(FRMELE.GetXCordOrigin()));
msflxgrd.SetTextMatrix(j + 1, 3, D2S(FRMELE.GetYCordOrigin()));
msflxgrd.SetTextMatrix(j + 1, 4, FRMELE.GetFieldName());
msflxgrd.SetTextMatrix(j + 1, 5, FRMELE.GetText().GetText());
msflxgrd.SetTextMatrix(j + 1, 6, FieldTypes[FRMELE.GetFieldType()]);
j = j + 1;
}
if((j + 2) > (msflxgrd.GetRows()- 1))
msflxgrd.SetRows(msflxgrd.GetRows() + 1);
}
catch (CException * E)
{
char Error[255];
E->GetErrorMessage(Error, 255);
AfxMessageBox(Error);
}
}
[CS]
//This code segment uses ListView
ListViewItem lstViewItem;
PDFDoc.LoadFromFile(InputFile);
int Tot = PDFDoc.GetTotalPDFElementsInPage(1);
gtPDFFormElementX FRMELE;
for(int i = 0; i < Tot; i++)
{
try
{
if(PDFDoc.GetPDFElementTypeAt(i,1)== TxPDFElementType.etForm)
{
FRMELE = PDFDoc.GetPDFFormElementAt(i,1);
lstViewItem = ListView1.Items.Add(i.ToString());
lstViewItem.SubItems.Add("Form");
lstViewItem.SubItems.Add(FRMELE.FormFieldBox.XCordOrigin.ToString());
lstViewItem.SubItems.Add(FRMELE.FormFieldBox.YCordOrigin.ToString());
lstViewItem.SubItems.Add(FRMELE.FieldName);
lstViewItem.SubItems.Add(FRMELE.Text.Text);
lstViewItem.SubItems.Add(FieldTypes[(int)FRMELE.FieldType]);
}
}
catch (Exception E)
{
//continue;
MessageBox.Show(E.Message);
}
}
[VB]
'This code segment uses MS FlexGrid
Dim PATHELE As gtPDFPathElementX
Dim CURELE As gtPDFCurveElementX
Dim RECTELE As gtPDFRectangleElementX
Dim LNELE As gtPDFLineElementX
Dim i, j, k As Integer
PDFDoc.LoadFromFile FileName
On Error Resume Next
j = 0
For i = 0 To PDFDoc.GetTotalPDFElementsInPage(1) - 1
If PDFDoc.GetPDFElementTypeAt(i, 1) = TxPDFElementType.etPath Then
Set PATHELE = PDFDoc.GetPDFPathElementAt(i, 1)
For k = 0 To PATHELE.GetTotalPathElements() - 1
If PATHELE.GetPathElementTypeAt(k) = etLine Then
Set LNELE = PATHELE.GetLineElementAt(k)
If ElemType = etLine Then
MSFlexGrid1.TextMatrix(j + 1, 0) = i
MSFlexGrid1.TextMatrix(j + 1, 1) = "Line"
MSFlexGrid1.TextMatrix(j + 1, 2) = LNELE.XCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 3) = LNELE.YCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 4) = LNELE.XCordDestination
MSFlexGrid1.TextMatrix(j + 1, 5) = LNELE.YCordDestination
j = j + 1
End If
If (j + 2) > MSFlexGrid1.Rows - 1 Then
MSFlexGrid1.Rows = MSFlexGrid1.Rows + 1
End If
End If
If PATHELE.GetPathElementTypeAt(k) = TxPDFElementType.etCurve Then
Set CURELE = PATHELE.GetCurveElementAt(k)
Dim Points() As Integer
Points = CURELE.Points
Dim str As String
Dim m As Integer
For m = 0 To UBound(Points)
str = str + Conversion.CStr(Points(m)) + ", "
Next
If ElemType = etCurve Then
MSFlexGrid1.TextMatrix(j + 1, 0) = i
MSFlexGrid1.TextMatrix(j + 1, 1) = "Curve"
MSFlexGrid1.TextMatrix(j + 1, 2) = CURELE.XCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 3) = CURELE.YCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 4) = str
MSFlexGrid1.TextMatrix(j + 1, 5) = PATHELE.IsClosePath
j = j + 1
End If
End If
If PATHELE.GetPathElementTypeAt(k) = TxPDFElementType.etRectangle Then
Set RECTELE = PATHELE.GetRectangleElementAt(k)
If ElemType = etRectangle Then
MSFlexGrid1.TextMatrix(j + 1, 0) = i
MSFlexGrid1.TextMatrix(j + 1, 1) = "Rectangle"
MSFlexGrid1.TextMatrix(j + 1, 2) = RECTELE.XCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 3) = RECTELE.YCordOrigin
MSFlexGrid1.TextMatrix(j + 1, 4) = RECTELE.XCordDestination
MSFlexGrid1.TextMatrix(j + 1, 5) = RECTELE.YCordDestination
MSFlexGrid1.TextMatrix(j + 1, 6) = PATHELE.IsClosePath
j = j + 1
End If
End If
Next
End If
Next
[VC++]
//This code segment uses MS FlexGrid
CgtPDFPathElementX PATHELE;
CgtPDFCurveElementX CURELE;
CgtPDFRectangleElementX RECTELE;
CgtPDFLineElementX LNELE;
int i, j, k, Tot;
PDFDoc->LoadFromFile(InputFile);
Tot = PDFDoc->GetTotalPDFElementsInPage(1);
j = 0;
for(i= 0; i< PDFDoc->GetTotalPDFElementsInPage(1) ;i++)
{
try
{
if(PDFDoc->GetPDFElementTypeAt(i,1)== etPath) /*2*/
{
PATHELE = PDFDoc->GetPDFPathElementAt(i,1);
for(k=0; k< PATHELE.GetTotalPathElements(); k++)
{
if(PATHELE.GetPathElementTypeAt(k) == etLine) /*4*/
{
LNELE = PATHELE.GetLineElementAt(k);
if(ElemType == etLine) /*4*/
{
msflxgrd.SetTextMatrix(j + 1, 0, I2S(i));
msflxgrd.SetTextMatrix(j + 1, 1, "Line");
msflxgrd.SetTextMatrix(j + 1, 2, D2S(LNELE.GetXCordOrigin()));
msflxgrd.SetTextMatrix(j + 1, 3, D2S(LNELE.GetYCordOrigin()));
msflxgrd.SetTextMatrix(j + 1, 4, D2S(LNELE.GetXCordDestination()));
msflxgrd.SetTextMatrix(j + 1, 5, D2S(LNELE.GetYCordDestination()));
}
if((j + 2) > (msflxgrd.GetRows()- 1))
msflxgrd.SetRows(msflxgrd.GetRows() + 1);
}
if(PATHELE.GetPathElementTypeAt(k) == etCurve) /*6*/
{
CURELE = PATHELE.GetCurveElementAt(k);
unsigned long N;
tagVARIANT myVar2;
myVar2 = CURELE.GetPoints();
long * Points;
Points = GetIntArrayFromVariant(myVar2, N);
CString Str = ""