Article ID:qGEN008
Date Revised:May 02, 1998
Keywords:Web, Contents, URL, HTML
See Also:KB Article Q174524   Download ReadURL.PRG (3KB)   

Question: How can I get the contents of a web page as a text string?

Answer: Here is a more useful version of the code presented in the above KB article. It fixes a couple of bugs and returns the item as a string instead of dumping it into a memo field. If you use the function to grab a binary file like a JPG you can save it as a file with:

create cursor xtemp mtemp (m)
append blank
replace mtemp with ReadURL( "http://SomeSite.com/SomeJPG.jpg" )
copy memo mtemp to somejpg.jpg

The modified code follows:

* readurl.prg 06-Mar-98

* 06-Mar-98 pulled from Q174524 on March 98 Technet CD
* 06-Mar-98 bug fixed about the length of the sReadBuffer

*Any Internet or intranet URL can be passed as a parameter. Microsoft.com
*was chosen for this example.

*Note that Microsoft Internet Explorer must be installed on the computer.

* passed: URLName, in the form "http://www.microsoft.com"
*
* returns: the content of the URL
*
* usage:
*
*  uWebContent = ReadURL( "http://www.microsoft.com" )
*  uWebContent = ReadURL( "http://www.SomeSite.com/SomeJPG.jpg" )
*
* notes:
* 1 - IE does not need to be running to use this, but must be installed,
* as the program uses an option that gets information from the registry

LPARAMETERS pcUrlName

DECLARE INTEGER InternetOpen IN wininet.DLL STRING sAgent, ;
      INTEGER lAccessType, STRING sProxyName, ;
      STRING sProxyBypass, INTEGER lFlags

DECLARE INTEGER InternetOpenUrl IN wininet.DLL ;
   INTEGER hInternetSession, STRING sUrl, STRING sHeaders,;
   INTEGER lHeadersLength, INTEGER lFlags, INTEGER lContext

DECLARE INTEGER InternetReadFile IN wininet.DLL INTEGER hfile, ;
      STRING @sBuffer, INTEGER lNumberofBytesToRead, INTEGER @lBytesRead

DECLARE short InternetCloseHandle IN wininet.DLL INTEGER hInst

#DEFINE INTERNET_OPEN_TYPE_PRECONFIG 0
#DEFINE INTERNET_OPEN_TYPE_DIRECT 1
#DEFINE INTERNET_OPEN_TYPE_PROXY 3
#DEFINE SYNCHRONOUS 0
#DEFINE INTERNET_FLAG_RELOAD 2147483648
#DEFINE CR CHR(13)

local lsAgent, lhInternetSession, lhUrlFile, llOk, lnOk, lcRetVal, lcReadBuffer, lnBytesRead

* what application is using Internet services?
lsAgent = "VPF 5.0"

lhInternetSession = InternetOpen( lsAgent, INTERNET_OPEN_TYPE_PRECONFIG, ;
      '', '', SYNCHRONOUS)

* debugging line - uncomment to see session handle
* WAIT WINDOW "Internet session handle: " + LTRIM(STR(hInternetSession))

IF lhInternetSession = 0
   WAIT WINDOW "Internet session cannot be established" TIME 2
   RETURN .null.
ENDIF

lhUrlFile = InternetOpenUrl( lhInternetSession, pcUrlName, '', 0, ;
                             INTERNET_FLAG_RELOAD, 0)

* debugging line - uncomment to see URL handle
* WAIT WINDOW "URL Handle: " + LTRIM(STR(hUrlFile))

IF lhUrlFile = 0
   WAIT WINDOW "URL cannot be opened"
   RETURN .null.
ENDIF

lcRetVal = ""
llOk = .t.

DO WHILE llOK
   * set aside a big buffer
   lsReadBuffer = SPACE(32767)
   lnBytesRead = 0
   lnOK = InternetReadFile( lhUrlFile, @lsReadBuffer, LEN(lsReadBuffer), @lnBytesRead)

   if ( lnBytesRead > 0 )
      lcRetVal = lcRetVal + left( lsReadBuffer, lnBytesRead )
   endif

   * error trap - either a read failure or read past eof()
   llOk = ( lnOK = 1 ) and ( lnBytesRead > 0 )
ENDDO

* close all the handles we opened
InternetCloseHandle( lhUrlFile )
InternetCloseHandle( lhInternetSession )

* return the URL contents
RETURN lcRetVal


1