Checking text in a PDF file with LoadRunner

My solution uses the popen() function to call a command-line program from LoadRunner which converts the PDF to text. The text can then be verified using simple string comparison functions. The command line program I used is pdftotext, which is part of the open-source Xpdf project. I have mirrored the file, so you can download pdftotext (from Xpdf v3.03) directly from my website.

Here is the example code:

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

char *strstr( const char *string1, const char *string2); // Explicit declaration required for C functions that do not return integers. #define BUFFER_SIZE 16384 // 16 KB. If this gets too big, use malloc() instead to avoid "too many local variables" compilation error.   Action() { int pdf_size; // size of the downloaded PDF (determined at runtime) int fp_save; // file pointer for saving the PDF int fp_popen; // file/stream pointer for the output from popen() int count; // number of characters that have been read from the popen() stream char buffer[BUFFER_SIZE]; // allocate memory for the output of popen()   lr_start_transaction("download_pdf");   // Save entire HTTP response body // Note that the PDF download must be in a step by itself in order to save the contents. It cannot be an EXTRARES. web_reg_save_param_ex( "ParamName=PdfContents", "LB/BIN=", "RB/BIN=", SEARCH_FILTERS, "Scope=Body", LAST);   web_reg_find("Text=PDF", LAST); // Basic check web_url("Download PDF", "URL=http://www.myloadtest.com/resources/hp-discover-2012-tb2337-moncrieff.pdf", "Resource=0", // Not a resource "RecContentType=application/pdf", LAST);   pdf_size = web_get_int_property(HTTP_INFO_DOWNLOAD_SIZE); if (pdf_size < 100000){ lr_error_message("Downloaded PDF is smaller than expected."); // By itself, this is not a very good check. lr_exit(LR_EXIT_ACTION_AND_CONTINUE, LR_FAIL); }   lr_end_transaction("download_pdf", LR_AUTO); lr_think_time(10); lr_start_transaction("check_pdf");   // Save file. lr_save_string(lr_eval_string("C:\\LoadRunner\\Data\\{TimeStamp}{VuserId}.pdf"), "FileName"); // Ensure that the file name is unique to avoid overwriting the contents fp_save = fopen(lr_eval_string("{FileName}"), "wb"); // open file in "write, binary" mode. fwrite(lr_eval_string("{PdfContents}"), pdf_size, 1, fp_save); fclose(fp_save);   // Run "C:\LoadRunner\Lib\pdftotext {FileName} -" and save the output to a parameter. fp_popen = popen(lr_eval_string("C:\\LoadRunner\\Lib\\pdftotext {FileName} -"), "r"); count = fread(buffer, sizeof(char), BUFFER_SIZE, fp_popen); if (feof(fp_popen) == 0) { lr_error_message("Did not reach the end of the input stream when reading. Try increasing BUFFER_SIZE."); return -1; } buffer[count] = NULL; // Make sure the string in the buffer is null-terminated. lr_save_string(buffer, "PdfText"); lr_output_message("The Windows version is: %s", buffer); pclose(fp_popen);   // Check that the PDF parameter contains the expected text ("LoadRunner"). if (strstr(lr_eval_string("{PdfText}"), "LoadRunner") == NULL) { lr_error_message("PDF file does not contain the expected string."); lr_exit(LR_EXIT_ACTION_AND_CONTINUE, LR_FAIL); }   // Cleanup. Delete the file. system(lr_eval_string("del /q {FileName}"));   lr_end_transaction("check_pdf", LR_AUTO);   return 0; }