问题
I spent the last days trying to figure out how to download a file from an URL. This is my first challenge with socket and I'm using it to have an understanding of protocols so I would like to do it without cURL libraries and only in C language!! I searched a lot....now I'm able to printf the source code of a page but I think it's different with a file, I don't have only to put the received data from a buffer to a file, right? any tips?
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <netdb.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <errno.h>
#include <arpa/inet.h>
int main(void)
{
char domain[] = "www.sstatic.net", path[]="stackexchange/img/logos/so/so-logo-med.png"; //example
int sock, bytes_received;
char send_data[1024],recv_data[9999], *p;
struct sockaddr_in server_addr;
struct hostent *he;
FILE *fp;
he = gethostbyname(domain);
if (he == NULL){
herror("gethostbyname");
exit(1);
}
if ((sock = socket(AF_INET, SOCK_STREAM, 0))== -1){
perror("Socket");
exit(1);
}
server_addr.sin_family = AF_INET;
server_addr.sin_port = htons(80);
server_addr.sin_addr = *((struct in_addr *)he->h_addr);
bzero(&(server_addr.sin_zero),8);
if (connect(sock, (struct sockaddr *)&server_addr,sizeof(struct sockaddr)) == -1){
perror("Connect");
exit(1);
}
snprintf(send_data, sizeof(send_data), "GET /%s HTTP/1.1\r\nHost: /%s\r\n\r\n", path, domain);
//printf("%s\n", send_data);
send(sock, send_data, strlen(send_data), 0);
printf("Data sended.\n");
fp=fopen("received_file","wb");
bytes_received = recv(sock, recv_data, 9999, 0);
recv_data[bytes_received] = '\0';
printf("Data receieved.\n");
printf("%s\n", recv_data);
p = strstr(recv_data, "\r\n\r\n"); //to find "\r\n\r\n" sequence and put the pointer p after that
p=p+4;
fwrite(p,strlen(p),1,fp);
close(sock);
fclose(fp);
return 0;
}
UPDATE 1 thanks to milevyo for some improvements! It works good with a txt file but it doesn't with other kinds of file (png in this case)
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <netdb.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <errno.h>
#include <arpa/inet.h>
int main(void){
//char domain[] = "www.gnu.org", path[]="/licenses/gpl.txt"; //example
char domain[] = "sstatic.net", path[]="stackexchange/img/logos/so/so-logo-med.png"; //example
int sock, bytes_received;
char send_data[1024],recv_data[9999];
struct sockaddr_in server_addr;
struct hostent *he;
FILE *fp;
he = gethostbyname(domain);
if (he == NULL){
herror("gethostbyname");
exit(1);
}
if ((sock = socket(AF_INET, SOCK_STREAM, 0))== -1){
perror("Socket");
exit(1);
}
server_addr.sin_family = AF_INET;
server_addr.sin_port = htons(80);
server_addr.sin_addr = *((struct in_addr *)he->h_addr);
bzero(&(server_addr.sin_zero),8);
printf("Connecting ...\n");
if (connect(sock, (struct sockaddr *)&server_addr,sizeof(struct sockaddr)) == -1){
perror("Connect");
exit(1);
}
printf("Sending data ...\n");
snprintf(send_data, sizeof(send_data), "GET /%s HTTP/1.1\r\nHost: /%s\r\n\r\n", path, domain);
if(send(sock, send_data, strlen(send_data), 0)==-1){
perror("send");
exit(2);
}
printf("Data sent.\n");
fp=fopen("received_file","wb");
printf("Recieving data...\n\n");
while((bytes_received = recv(sock, recv_data, 9999, 0))>0){
if(bytes_received==-1){
perror("recieve");
exit(3);
}
recv_data[bytes_received] = '\0';
fwrite(recv_data,bytes_received,1,fp);
printf("%s", recv_data);
}
close(sock);
fclose(fp);
printf("\n\nDone.\n\n");
return 0;
}
this code produce a 334 bytes file (instead of 12,4kb of the original file) with this inside:
HTTP/1.1 400 Bad Request
Date: Sat, 28 Nov 2015 16:20:45 GMT
Content-Type: text/html
Content-Length: 177
Connection: close
Server: -nginx
CF-RAY: -
<html>
<head><title>400 Bad Request</title></head>
<body bgcolor="white">
<center><h1>400 Bad Request</h1></center>
<hr><center>cloudflare-nginx</center>
</body>
</html>
somebody knows how to fix this "400 Bad Request"?
回答1:
This is an update for the previous posted code. The http protocol is far to be implementation in just a small example.
reformatting the code , or giving a modification to it is more than welcome.
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <netdb.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <errno.h>
#include <arpa/inet.h>
#include <string.h>
int ReadHttpStatus(int sock){
char c;
char buff[1024]="",*ptr=buff+1;
int bytes_received, status;
printf("Begin Response ..\n");
while(bytes_received = recv(sock, ptr, 1, 0)){
if(bytes_received==-1){
perror("ReadHttpStatus");
exit(1);
}
if((ptr[-1]=='\r') && (*ptr=='\n' )) break;
ptr++;
}
*ptr=0;
ptr=buff+1;
sscanf(ptr,"%*s %d ", &status);
printf("%s\n",ptr);
printf("status=%d\n",status);
printf("End Response ..\n");
return (bytes_received>0)?status:0;
}
//the only filed that it parsed is 'Content-Length'
int ParseHeader(int sock){
char c;
char buff[1024]="",*ptr=buff+4;
int bytes_received, status;
printf("Begin HEADER ..\n");
while(bytes_received = recv(sock, ptr, 1, 0)){
if(bytes_received==-1){
perror("Parse Header");
exit(1);
}
if(
(ptr[-3]=='\r') && (ptr[-2]=='\n' ) &&
(ptr[-1]=='\r') && (*ptr=='\n' )
) break;
ptr++;
}
*ptr=0;
ptr=buff+4;
//printf("%s",ptr);
if(bytes_received){
ptr=strstr(ptr,"Content-Length:");
if(ptr){
sscanf(ptr,"%*s %d",&bytes_received);
}else
bytes_received=-1; //unknown size
printf("Content-Length: %d\n",bytes_received);
}
printf("End HEADER ..\n");
return bytes_received ;
}
int main(void){
char domain[] = "sstatic.net", path[]="stackexchange/img/logos/so/so-logo-med.png";
int sock, bytes_received;
char send_data[1024],recv_data[1024], *p;
struct sockaddr_in server_addr;
struct hostent *he;
he = gethostbyname(domain);
if (he == NULL){
herror("gethostbyname");
exit(1);
}
if ((sock = socket(AF_INET, SOCK_STREAM, 0))== -1){
perror("Socket");
exit(1);
}
server_addr.sin_family = AF_INET;
server_addr.sin_port = htons(80);
server_addr.sin_addr = *((struct in_addr *)he->h_addr);
bzero(&(server_addr.sin_zero),8);
printf("Connecting ...\n");
if (connect(sock, (struct sockaddr *)&server_addr,sizeof(struct sockaddr)) == -1){
perror("Connect");
exit(1);
}
printf("Sending data ...\n");
snprintf(send_data, sizeof(send_data), "GET /%s HTTP/1.1\r\nHost: %s\r\n\r\n", path, domain);
if(send(sock, send_data, strlen(send_data), 0)==-1){
perror("send");
exit(2);
}
printf("Data sent.\n");
//fp=fopen("received_file","wb");
printf("Recieving data...\n\n");
int contentlengh;
if(ReadHttpStatus(sock) && (contentlengh=ParseHeader(sock))){
int bytes=0;
FILE* fd=fopen("test.png","wb");
printf("Saving data...\n\n");
while(bytes_received = recv(sock, recv_data, 1024, 0)){
if(bytes_received==-1){
perror("recieve");
exit(3);
}
fwrite(recv_data,1,bytes_received,fd);
bytes+=bytes_received;
printf("Bytes recieved: %d from %d\n",bytes,contentlengh);
if(bytes==contentlengh)
break;
}
fclose(fd);
}
close(sock);
printf("\n\nDone.\n\n");
return 0;
}
来源：https://stackoverflow.com/questions/33960385/how-to-download-a-file-from-http-using-c