c program not writing same result as it is displaying - c

Question

My C program is not writing to a file the same data that it is displaying. how do i save what is outputted to the screen in a file. I am trying to save a webpage, the file name is defined by the third option, [site] [page] [path]
#include <stdio.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <stdlib.h>
#include <netdb.h>
#include <string.h>
int create_tcp_socket();
char *get_ip(char *host);
char *build_get_query(char *host, char *page);
void usage();
#define HOST "coding.debuntu.org"
#define PAGE "/"
#define PORT 80
#define USERAGENT "HTMLGET 1.0"
#define OS "mac osx"
int main(int argc, char **argv)
{
struct sockaddr_in *remote;
int sock;
int tmpres;
char *ip;
char *get;
char buf[BUFSIZ+1];
char *host;
char *page;
char *HTMLfile;
if(argc == 1){
usage();
exit(2);
}
host = argv[1];
if(argc > 2){
page = argv[2];
}else{
page = PAGE;
}
HTMLfile = argv[3];
sock = create_tcp_socket();
ip = get_ip(host);
fprintf(stderr, "<!--\nIP is %s\n", ip);
remote = (struct sockaddr_in *)malloc(sizeof(struct sockaddr_in *));
remote->sin_family = AF_INET;
tmpres = inet_pton(AF_INET, ip, (void *)(&(remote->sin_addr.s_addr)));
if( tmpres < 0)
{
perror("Can't set remote->sin_addr.s_addr");
exit(1);
}else if(tmpres == 0)
{
fprintf(stderr, "%s is not a valid IP address\n", ip);
exit(1);
}
remote->sin_port = htons(PORT);
if(connect(sock, (struct sockaddr *)remote, sizeof(struct sockaddr)) < 0){
perror("Could not connect");
exit(1);
}
get = build_get_query(host, page);
fprintf(stderr, "nQuery is:\n<<START>>\n%s<<END>>\n-->\n", get);
//Send the query to the server
int sent = 0;
while(sent < strlen(get))
{
tmpres = send(sock, get+sent, strlen(get)-sent, 0);
if(tmpres == -1){
perror("Can't send query");
exit(1);
}
sent += tmpres;
}
//now it is time to receive the page
memset(buf, 0, sizeof(buf));
int htmlstart = 0;
char * htmlcontent;
while((tmpres = recv(sock, buf, BUFSIZ, 0)) > 0){
if(htmlstart == 0)
{
/* Under certain conditions this will not work.
* If the \r\n\r\n part is splitted into two messages
* it will fail to detect the beginning of HTML content
*/
htmlcontent = strstr(buf, "\r\n\r\n");
if(htmlcontent != NULL){
htmlstart = 1;
htmlcontent += 4;
}
}else{
htmlcontent = buf;
}
if(htmlstart){
fprintf(stdout, "%s", htmlcontent);
}
FILE *f;
f = fopen(HTMLfile, "w");
fprintf(f, "%s", htmlcontent); //stderr, "%s"
fclose(f);
memset(buf, 0, tmpres);
}
if(tmpres < 0)
{
perror("Error receiving data");
}
free(get);
free(remote);
free(ip);
close(sock);
return 0;
}
void usage()
{
fprintf(stderr, "USAGE: htmlget host [page]\n\
\thost: the website hostname. ex: coding.debuntu.org\n\
\tpage: the page to retrieve. ex: index.html, default: /\n");
}
int create_tcp_socket()
{
int sock;
if((sock = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)) < 0){
perror("Can't create TCP socket");
exit(1);
}
return sock;
}
char *get_ip(char *host)
{
struct hostent *hent;
int iplen = 15; //XXX.XXX.XXX.XXX
char *ip = (char *)malloc(iplen+1);
memset(ip, 0, iplen+1);
if((hent = gethostbyname(host)) == NULL)
{
herror("Can't get IP");
exit(1);
}
if(inet_ntop(AF_INET, (void *)hent->h_addr_list[0], ip, iplen) == NULL)
{
perror("Can't resolve host");
exit(1);
}
return ip;
}
char *build_get_query(char *host, char *page)
{
char *query;
char *getpage = page;
char *tpl = "GET /%s HTTP/1.0\r\nHost: %s\r\nUser-Agent: %s\r\n\r\n";
if(getpage[0] == '/'){
getpage = getpage + 1;
fprintf(stderr,"Removing leading \"/\", converting %s to %s\n", page, getpage);
}
// -5 is to consider the %s %s %s in tpl and the ending \0
query = (char *)malloc(strlen(host)+strlen(getpage)+strlen(USERAGENT)+strlen(OS)+strlen(tpl)-5);
sprintf(query, tpl, getpage, host, USERAGENT);
return query;
// FILE *f;
// f = fopen(HTMLfile, "w");
// fprintf(f, htmlcontent);
// fclose(f);
}
Here is where i am saving the file:
FILE *f;
f = fopen(HTMLfile, "w");
fprintf(f, "%s", htmlcontent); //stderr, "%s"
fclose(f);
Here is the result that it saves for my question (This Page)
(['_setCustomVar', 1, 'tags', '|c|file|networking|']);
_gaq.push(['_trackPageview']);
var _qevents = _qevents || [];
(function () {
var ssl='https:'==document.location.protocol,
s=document.getElementsByTagName('script')[0],
ga=document.createElement('script');
ga.type='text/javascript';
ga.async=true;
ga.src=(ssl?'https://ssl':'http://www')+'.google-analytics.com/ga.js';
s.parentNode.insertBefore(ga,s);
var sc=document.createElement('script');
sc.type='text/javascript';
sc.async=true;
sc.src=(ssl?'https://secure':'http://edge')+'.quantserve.com/quant.js';
s.parentNode.insertBefore(sc,s);
})();
_qevents.push({ qacct: "p-c1rF4kxgLUzNc" });
</script>
</body>
</html>

Answer 1

FILE *f;
f = fopen(HTMLfile, "w");
fprintf(f, "%s", htmlcontent); //stderr, "%s"
fclose(f);
Rather than opening and closing the file each time through the loop, you should open
it once before the loop, keep it open while you're writing into it, then close it after
the loop.

Answer 2

Instead of opening the file with "w" use "a". Better yet, only open the file once.
f = fopen(HTMLfile, "a");
w" write: Create an empty file for output operations. If a file with the same name already exists, its contents are discarded and the file is treated as a new empty file.
"a" append: Open file for output at the end of a file. Output operations always write data at the end of the file, expanding it. Repositioning operations (fseek, fsetpos, rewind) are ignored. The file is created if it does not exist.