Examples of interface functions:

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK(string lpPDFFile, string lpOutFile, string lpOptions);

//Directly analyze PDF with this function

lpPDFFile is the input PDF, e.g., C:\test.pdf

lpOutFile is an output file, e.g., D:\out.png

lpOptions supports following arguments:

-f <int>           : specify the first page to process.

-l <int>           : specify the last page to process.

-r <int>           : set resolution in DPI (default is 150).

-opw <string>: give owner password (for encrypted PDF).

-upw <string>:give user password (for encrypted PDF).

-html              : output text information in HTML instead of CSV format.

 

[DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDKFromMemory(ref byte lpPDFData, int nDataLen, string lpOutFile, string lpOptions);

//Analyze PDF in memory; options and arguments are the same as those of VeryPDF_PDFParserSDK.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetHandle(string lpPDFFile, string lpOptions);

//Load PDF into memory and return the handle. lpOptions arguments are the same as those of VeryPDF_PDFParserSDK.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetCount(int hPDFParserData);

/*Get the page count of handle of loaded PDF. Note that the page count is the number of loaded pages but not the total page count of the PDF. For example, if lpOptions uses “-f 2 -l 4”, this function will return 3, the valid page count (2, 3, and 4) of handle. If you need the total page count, please use function VeryPDF_PDFParserSDK_GetAllPagesCount(). */

 

[DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetImageLength(int hPDFParserData, int nIndex);

//Get image length of the handle. The application will allocate memory by the image length value.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetImageData(int hPDFParserData, int nIndex, [MarshalAs(UnmanagedType.LPArray)] byte[] lpData, int nBufLen);

//Get image data in specified page of PDF handle.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetTextInfoLength(int hPDFParserData, int nIndex);

//Get the text data length of specified page of PDF handle. The application will allocate memory by the length value.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetTextInfoData(int hPDFParserData, int nIndex, [MarshalAs(UnmanagedType.LPArray)] byte[] lpData, int nBufLen);

//Return text data of specified page in PDF handle.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetPageCount(string lpPDFFile);

//Get page count of the PDF file.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_GetAllPagesCount(int hPDFParserData);

//Get the total page count of the PDF handle.

 

 [DllImport("pdfparsersdk2.dll")]

private static extern int VeryPDF_PDFParserSDK_Free(int hPDFParserData);

//Release the PDF handle.

The followings are some function code which can be directly used in your C# code.

        private void DiskFile_Click(object sender, EventArgs e)

        {

            string appPath = Path.GetDirectoryName(Application.ExecutablePath);

            int nRet;

            string strOptions;

            string strInPDFFile;

            string strOutFile;

            string strLogMsg;

            strInPDFFile = (appPath + "\\example1.pdf");

            strOutFile = (appPath + "\\out.png");

            strOptions = "-$ XXXXXXXXXXXXXXXXXXXX";

            nRet = VeryPDF_PDFParserSDK(strInPDFFile, strOutFile, strOptions);

            strLogMsg = (strInPDFFile + ("\r\n"

                        + (strOutFile + ("\r\n"

                        + (strOptions + ("\r\n" + ("nRet = " + (nRet.ToString()))))))));

            MessageBox.Show(strLogMsg);

        }

 

        private void Memory_Click(object sender, EventArgs e)

        {

            int nRet;

            string strOptions;

            string strInPDFFile;

            string strOutFile;

            int nPDFSDKLib;

            int nCount;

            int nItem;

            byte[] vecImgData = null;

            byte[] vecTxtData = null;

            int nImageDataLen;

            int nTextInfoLen;

            string strLogMsg;

            string appPath = Path.GetDirectoryName(Application.ExecutablePath);

            strInPDFFile = (appPath + "\\example1.pdf");

            strOptions = "-$ XXXXXXXXXXXXXXXXXXXX";

            nPDFSDKLib = VeryPDF_PDFParserSDK_GetHandle(strInPDFFile, strOptions);

            nCount = VeryPDF_PDFParserSDK_GetCount(nPDFSDKLib);

            for (nItem = 0; (nItem <= (nCount - 1)); nItem++)

            {

                nImageDataLen = VeryPDF_PDFParserSDK_GetImageLength(nPDFSDKLib, nItem);

                nTextInfoLen = VeryPDF_PDFParserSDK_GetTextInfoLength(nPDFSDKLib, nItem);

                vecImgData = new byte[nImageDataLen];

                vecTxtData = new byte[nTextInfoLen];

                VeryPDF_PDFParserSDK_GetImageData(nPDFSDKLib, nItem, vecImgData, nImageDataLen);

                VeryPDF_PDFParserSDK_GetTextInfoData(nPDFSDKLib, nItem, vecTxtData, nTextInfoLen);

                strLogMsg = System.Text.Encoding.ASCII.GetString(vecTxtData);

                MessageBox.Show(strLogMsg.Substring(0, 300));

            }

            VeryPDF_PDFParserSDK_Free(nPDFSDKLib);

            nPDFSDKLib = 0;

        }

 

        private void PageByPage_Click(object sender, EventArgs e)

        {

            int nRet;

            string strOptions;

            string strInPDFFile;

            string strOutFile;

            int nPDFSDKLib;

            int nCount;

            int nItem;

            byte[] vecImgData = null;

            byte[] vecTxtData = null;

            int nImageDataLen;

            int nTextInfoLen;

            string strLogMsg;

            int nPageCount;

            int page;

            string appPath = Path.GetDirectoryName(Application.ExecutablePath);

            strInPDFFile = (appPath + "\\example2.pdf");

            nPageCount = VeryPDF_PDFParserSDK_GetPageCount(strInPDFFile);

            for (page = 1; (page <= nPageCount); page++)

            {

                strOptions = ("-$ XXXXXXXXXXXXXXXXXXXX -f "

                            + ((page.ToString()) + (" -l " + (page.ToString()))));

                nPDFSDKLib = VeryPDF_PDFParserSDK_GetHandle(strInPDFFile, strOptions);

                nCount = VeryPDF_PDFParserSDK_GetCount(nPDFSDKLib);

                for (nItem = 0; (nItem <= (nCount - 1)); nItem++)

                {

                    nImageDataLen = VeryPDF_PDFParserSDK_GetImageLength(nPDFSDKLib, nItem);

                    nTextInfoLen = VeryPDF_PDFParserSDK_GetTextInfoLength(nPDFSDKLib, nItem);

                    vecImgData = new byte[nImageDataLen];

                    vecTxtData = new byte[nTextInfoLen];

                    VeryPDF_PDFParserSDK_GetImageData(nPDFSDKLib, nItem, vecImgData, nImageDataLen);

                    VeryPDF_PDFParserSDK_GetTextInfoData(nPDFSDKLib, nItem, vecTxtData, nTextInfoLen);

                    strLogMsg = System.Text.Encoding.ASCII.GetString(vecTxtData);

                    if ((nTextInfoLen == 0))

                    {

                        strLogMsg = "This page hasn\'t text contents.";

                    }

                    if ((strLogMsg.Length > 300))

                    {

                        strLogMsg = strLogMsg.Substring(0, 300);

                    }

                    MessageBox.Show(strLogMsg, ("Text contents of Page " + (page.ToString())));

                }

                VeryPDF_PDFParserSDK_Free(nPDFSDKLib);

                nPDFSDKLib = 0;

            }

        }

4. Compile the C# project and created an executable file

"CSharp_WindowsFormsApplication1.exe". Run the executable file, and then you will see its interface as displayed in Fig. 2.

Fig. 2 Interface of compiled C# demonstration project

5. In the interface shown in Fig. 2, click the first button, and then you will get the following files:

• out_pg_0001.htm is a plain text file which contains data in format below:

Before each word (string), the four numbers give the position (Left, Top, Width, and Height) of the word. Data blocks are separated by semicolon ";".

If you want to output the data in XML, please use argument "-html" in option "strOptions",

for example, do as in the following code.

 private void DiskFile_Click(object sender, EventArgs e)

        {

            string appPath = Path.GetDirectoryName(Application.ExecutablePath);

            int nRet;

            string strOptions;

            string strInPDFFile;

            string strOutFile;

            string strLogMsg;

            strInPDFFile = (appPath + "\\example1.pdf");

            strOutFile = (appPath + "\\out.png");

            strOptions = "-$ XXXXXXXXXXXXXXXXXXXX -html";

            nRet = VeryPDF_PDFParserSDK(strInPDFFile, strOutFile, strOptions);

            strLogMsg = (strInPDFFile + ("\r\n"

                        + (strOutFile + ("\r\n"

                        + (strOptions + ("\r\n" + ("nRet = " + (nRet.ToString()))))))));

            MessageBox.Show(strLogMsg);

        }

Recompile the project, and run the generated "CSharp_WindowsFormsApplication1.exe", you will get a new "out_pg_0001.htm" which stores data in formats like the below.

Strings and the positions are stored in the HTML file.

<div style="position: absolute;top:2;left:-1"><img width="1275" height="1650" src="out_pg_0001.png"></img></div>

<div style="position:absolute;left:666;top:78;width:84;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">MORGAN</span></div>

<div style="position:absolute;left:761;top:78;width:90;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">STANLEY</span></div>

<div style="position:absolute;left:862;top:78;width:57;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">FIXED</span></div>

<div style="position:absolute;left:930;top:78;width:76;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">INCOME</span></div>

<div style="position:absolute;left:1017;top:78;width:107;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">RESEARCH</span></div>

<div style="position:absolute;left:666;top:118;width:76;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">September</span></div>

<div style="position:absolute;left:746;top:118;width:20;height:14"><span style="font-style:normal;font-weight:700;font-size:13px;font-family:Arial;color:#000000;">20,</span></div>

• out_pg_0001.png is an image rendered from the PDF page.

Each string in out_pg_0001.png has the same position as stored in out_pg_0001.htm. If you view out_pg_0001.htm by a web browser, you will see that strings in the PNG image and HTML file are precisely overlapped as shown in Fig. 3.

Fig. 3 View the created HTML file in a web browser

6. To modify the text in a PDF, please use the demonstration project "D:\temp\pdfparsersdk\VB.NET_ModifyTextInPDF\WindowsApplication1\WindowsApplication1.sln". Compile the project, and then you will get the demonstration executable file "VB_NET_ModifyTextInPDF.exe". Run the executable file and load a test PDF. You will see the interface as shown in Fig. 4.

Fig. 4 Modify a PDF with compiled demo application

If you want to replace MORGAN with VeryPDF, input the position information (Left, Top, Width, and Height), the original text "MORGAN" in Old Text, and the target text "VeryPDF" in New Text, as displayed in Fig. 5.

Fig. 5 Replace text in PDF with demo application

Click the button Replace Text in PDF, and then the text "MORGAN" will be replaced with "VeryPDF" as shown in Fig. 6.

Fig. 6 Result of text replacement

The replacement operation can also be performed by VB.NET codes as follows:

    Private Declare Function VeryPDF_PDFParserSDK Lib "pdfparsersdk2.dll" (ByVal lpPDFFile As String, ByVal lpOutFile As String, ByVal lpOptions As String) As Integer

    Private Declare Function VeryPDF_PDFParserSDKFromMemory Lib "pdfparsersdk2.dll" (ByRef lpPDFData As Byte, ByVal nDataLen As Integer, ByVal lpOutFile As String, ByVal lpOptions As String) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetHandle Lib "pdfparsersdk2.dll" (ByVal lpPDFFile As String, ByVal lpOptions As String) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetCount Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetImageLength Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer, ByVal nIndex As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetImageData Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer, ByVal nIndex As Integer, ByRef lpData As Byte, ByVal nBufLen As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetTextInfoLength Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer, ByVal nIndex As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetTextInfoData Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer, ByVal nIndex As Integer, ByRef lpData As Byte, ByVal nBufLen As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_Free Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetPageCount Lib "pdfparsersdk2.dll" (ByVal lpPDFFile As String) As Integer

    Private Declare Function VeryPDF_PDFParserSDK_GetAllPagesCount Lib "pdfparsersdk2.dll" (ByVal hPDFParserData As Integer) As Integer

    Private Declare Function VeryPDF_ModifyPDF_OpenFile Lib "pdfparsersdk2.dll" (ByVal lpInPDFFile As String, ByVal lpOutPDFFile As String) As Integer

    Private Declare Function VeryPDF_ModifyPDF_CloseFile Lib "pdfparsersdk2.dll" (ByVal hPDF As Integer) As Integer

    Private Declare Function VeryPDF_ModifyPDF_ModifyText Lib "pdfparsersdk2.dll" (ByVal hPDF As Integer, ByVal nPage As Integer, ByVal x As Integer, ByVal y As Integer, ByVal nWidth As Integer, ByVal nHeight As Integer, ByVal lpOldText As String, ByVal lpNewText As String) As Integer

    Private Declare Sub VeryPDF_ModifyPDF_SetCode Lib "pdfparsersdk2.dll" (ByVal lpCode As String)

    Private Sub Replace_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Replace.Click

        'default DPI is 72DPI in PDF file, so you need calculate position by 72DPI,

        'you can read the text contents and position from output HTML file

        Dim x, y, w, h, hPDF, bRet, nPage As Integer

        Dim strOldText, strNewText As String

 

        VeryPDF_ModifyPDF_SetCode("Your License Key for ModifyPDF SDK")

        Dim strInPDFFile As String = PDFFileName.Text

        If strInPDFFile = "" Then

            MsgBox("Please select a PDF file first")

            Return

        End If

        Dim strOutFile As String = Application.StartupPath() & "\modified.pdf"

        Dim nDPI As Integer = 72

        If LeftBox.Text = "" Then

            MsgBox("Please input a correct 'Left' value for text which you want to replace")

            Return

        End If

        If TopBox.Text = "" Then

            MsgBox("Please input a correct 'Top' value for text which you want to replace")

            Return

        End If

        If WidthBox.Text = "" Then

            MsgBox("Please input a correct 'Width' value for text which you want to replace")

            Return

        End If

        If HeightBox.Text = "" Then

            MsgBox("Please input a correct 'Height' value for text which you want to replace")

            Return

        End If

 

        Dim left As Integer = CInt(LeftBox.Text)

        Dim top As Integer = CInt(TopBox.Text)

        Dim width As Integer = CInt(WidthBox.Text)

        Dim height As Integer = CInt(HeightBox.Text)

        Dim oldText As String = OldTextBox.Text

        If oldText = "" Then

            MsgBox("Please input a correct 'Old Text' value for text which you want to replace")

           Return

        End If

        Dim newText As String = NewTextBox.Text

        If newText = "" Then

            MsgBox("Please input a correct 'New Text' value for text which you want to replace")

            Return

        End If

 

        hPDF = VeryPDF_ModifyPDF_OpenFile(strInPDFFile, strOutFile)

        'Replace horizontal text contents

        nPage = 1

        x = left * 72.0 / nDPI

        y = top * 72.0 / nDPI

        w = width * 72.0 / nDPI

        h = height * 72.0 / nDPI

        strOldText = oldText

        strNewText = newText

        bRet = VeryPDF_ModifyPDF_ModifyText(hPDF, nPage, x, y, w, h, strOldText, strNewText)

 

        VeryPDF_ModifyPDF_CloseFile(hPDF)

        MsgBox("Replace Text in PDF file completed." & vbCrLf & "VeryPDF_ModifyPDF_ModifyText() return: " & CStr(bRet))

 

    End Sub