Convert PDF to Text Sample code

ConvertSpot.com	*PDF to text Component, PDF to Text DLL, PDF to text Converter, Convert PDF to Text*
	*PDF to XML, Excel to XML, Excel to CSV, Word to Text, PowerPoint to Text, Excel to Text*

Product->Convert PDF to Text(DLL Edition)->Tech Document

Check the methods exposed from the DLL here

Examples:

Download Now FAQ'S Buy It Now

Example in VC:

1. Copy P2TDLL.DLL to the system folder or the folder of your project.

2. Include P2TProcessor.h in your project.

/**
* This is the callback function. you will get the stream data here.
* Add your own process logic in the function body.
* The type of this function is DATACALLBACKFUNC, please check
* P2TProcessor.h for detail information.
*/
void ContentCallBackFunc(char* i_szStr, int i_size)
{
     char tmp[800]={0};
     _snprintf(tmp,i_size,"%s",i_szStr);
     printf("Content: %s\n",tmp);
}

HINSTANCE hDLL; // Handle to DLL
CREATEPROCESSOR lpCreateProcessor; // Function pointer
RELEASEPROCESSOR lpReleaseProcessor;

hDLL = LoadLibrary("P2TDLL.dll");
if (hDLL != NULL)
{
     lpCreateProcessor = (CREATEPROCESSOR)GetProcAddress(hDLL,
                          "CreateProcessor");
     lpReleaseProcessor = (RELEASEPROCESSOR)GetProcAddress(hDLL,
                          "ReleaseProcessor");

     if (!lpCreateProcessor || !lpReleaseProcessor)
     {
        // handle the error
        MessageBox("Can't locate the function pointer.");
     }
     else
     {
        P2TProcessor* pP2TProcessor = lpCreateProcessor();

        pP2TProcessor->VerifyLicense("Test Me Please", "683690765A89C345B87135F");
        pP2TProcessor->EngagePDFProcessor(0,0,"","");
        pP2TProcessor->ParsePDF("C:\\test\\test.pdf", "C:\\test\\test.txt");
        pP2TProcessor->ParsePDF("C:\\test\\111.pdf",ContentCallBackFunc, 200);
        MessageBox("done!");

                 //The processor must be released before you unload the DLL
        lpReleaseProcessor(pP2TProcessor);
     }

    FreeLibrary(hDLL);
}

Go back to top

There's only two method exposed from the DLL.

/**
* This method get a instance of the processor
* @return P2TProcessor* The pointer of the new instance of the processor
*/
P2TProcessor* CreateProcessor();

/**
* This method release the instance created by CreateProcessor
* @param P2TProcessor* i_pP2TP The pointer created by CreateProcessor.
*
*/
void ReleaseProcessor(P2TProcessor* i_pP2TP);

Go back to top

=========>>P2TProcessor.h<<===============
////////////////////////////////////////////////////
#ifndef __P2TPROCESSOR_H_
#define __P2TPROCESSOR_H_

class P2TProcessor;

/**
* This is the log infromation callback function. if you wanna the real time
* log/output information, you need hook this function.
* @param char* i_szStr The input log information.
*
*/
typedef void(*LOGCALLBACKFUNC)(char* i_szStr);

/**
* This is the data stream callback function. you will get the stream data here.
* Add your own process logic here to process the output data stream.
* @param const char* i_szStr The buffer pointer of the output string
* @param int i_size The size of the data(in byte)
*/
typedef void(*DATACALLBACKFUNC)(const char* i_szStr, int i_size);

/**
* This is the one of two methods exposed from the DLL
* Use this method to create a new instance of P2TProcessor
* and return the pointer of the processor, The pointer must
* be released use RleaseProcessor after converting.
*/
typedef P2TProcessor* (*CREATEPROCESSOR)();

/**
* This is the one of the two methods exposed from the DLL
* Use this method to release the processor instance created
* by CreateProcessor
*
*/
typedef void (*RELEASEPROCESSOR)(P2TProcessor* pProcessor);

/**
* P2TProcessor is the class that encapsulates all the functions related
* to PDF converting. You can get the instance of this class through
* CreateProcessor exposed from the DLL
*
*/
class P2TProcessor {
public:

/**
* This is the function that should be called first before you try to call
* any other functions, It verifies the run time license information.
* @param char* UserName The register username.
* @param char* Key       The register keycode.
* @return int   zero:    Success. In trial version, always return zero.
*           not zero:    Something wrong with username/key
*/
virtual int VerifyLicense(char* UserName, char* Key) = 0;

/**
* This function pass in control information into P2TProcessor
* before it does the converting job.
* @param LOGCALLBACKFUNC pf   The log info callback function.
* @param int i_nCntrlFlg      The control flag pass into the processor.
* @param char* i_szPageRange The output page range collection, pass in empty
*                             string if you don't want to output page range.
* @param char* i_szPageBreaker   The breaker string of the page breaker.
*                                passin empty string if don't need page breaker
*/
virtual void EngagePDFProcessor(LOGCALLBACKFUNC pf, int i_nCntrlFlg, char* i_szPageRange, char* i_szPageBreaker) = 0;

/**
* This function parse pdf file and output the data into a file
* @param char* i_pdfFile   The input pdf file's path and name.
* @param char* i_txtFile   The output text file's path and name.
* @return int    0   Success.
*               -1   Something wrong during converting, check log callback func
*/
virtual int ParsePDF(char* i_pdfFile, char* i_txtFile) = 0;

/**
* This function parse pdf file and output the data stream into the callback
* function
* @param char* i_szPDFName:           The input pdf file's path and name.
* @param DATACALLBACKFUNC i_pFunc:    The pointer of the callback function
* @param int i_nBufSize:              The max buffer size that will pass to the
*                                     callback function.
* @return int    0 Success.
*               -1 Something wrong during converting, check log callback func
*/
virtual int ParsePDF(const char* i_szPDFName, DATACALLBACKFUNC i_pFunc, int i_nBufSize) = 0;

};

#endif

Go back to top