Re: simple function to get URL

Al Globus (globus@nas.nasa.gov)
Wed, 8 Mar 1995 18:26:05 -0800

Thanx for all the responses. Most suggested libWWW -- but I
failed to mention I wanted something small (say one file).
In any case, David Yip and I implemented it. Thought you
might like to see. There's some missing error checking
and no timeout, but it seems to work ok on simple tests.
The main() is just for testing

======================= cut here ============================
#include <assert.h>
#include <string.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <stdio.h>
#include <netinet/in.h>
#include <netdb.h>
#include <unistd.h>

#define ERROR 0
/*
Get the data at a URL and return it.
Called is responsible for calling 'free' on
returned *data.
Returns 0 is something wrong.

BUG: no timeouts and doesn't check all error returns
*/
#define BUF_SIZE 4096
size_t getURLbyParts( void** data, char* machine, int port, char* file )
{
struct hostent *he;
struct servent *se;
struct sockaddr_in sin;
int sock;
int bytes;
char buf[BUF_SIZE];
char* results = 0;
size_t size;
char getString[2048]; /* BUG: use malloc, but freeing after error is a problem */

data = 0;
he = gethostbyname( machine );

sock = socket(he->h_addrtype, SOCK_STREAM, 0);

bzero((caddr_t)&sin, sizeof(sin));
sin.sin_family = he->h_addrtype;
if (bind(sock, &sin, sizeof(sin)) < 0)
return ERROR;
bcopy(he->h_addr, &sin.sin_addr, he->h_length);
se = getservbyname("telnet", "tcp");

sin.sin_port = port;
if (connect(sock, &sin, sizeof(sin)) < 0)
return ERROR;

/* send GET message to http */
sprintf(getString,"GET %s\n", file);
if ( write( sock, getString, strlen(getString) != strlen(getString) ) )
return ERROR;

/* get data */
size = 0;
results = 0;
while( (bytes = read(sock,buf,BUF_SIZE)) > 0) {
int newSize = size + bytes;
results = realloc( results, newSize );
assert( results );
bcopy( buf, results + size, bytes );
size += bytes;
}
*data = (void*)results;
return size;
}

/*
Get the data at a URL and return it.
Called is responsible for calling 'free' on
returned *data.
url must be of the form http://machine-name[:port]/file-name
Returns 0 is something wrong.
*/
size_t getURL( void** data, char* url )
{
char* s;
size_t size;
char* machine;
int machineLen; /* length of machine name */
int port;
char* file = 0;

char* http = "http://";
int httpLen = strlen( http );
if ( !url ) return ERROR;
if ( strncmp( http, url, httpLen) ) return 0;

/* get the machine name */
for( s = url + strlen(http) + 1; *s && (*s != ':') && (*s != '/'); s++ )
;
machineLen = s - url;
machineLen -= httpLen;
machine = (char*)malloc( machineLen + 1 ); assert( machine );
strncpy( machine, url + httpLen, machineLen );

/* get port number */
if ( *s == ':' ) {
port = atoi( ++s );
while( *s && (*s != '/') )
s++;
} else {
port = 80;
}

/* get the file name */
if ( *s == '/' )
file = s;
else
file = "/";

size = getURLbyParts( data, machine, port, file );
free( machine );
return size;
}

void main( int argc, char** argv )
{
char* url = argv[1];
void* data;
size_t size = getURL( &data, url );
}