来源于CU的一个帖子，问如何查看web服务器信息，忽然想起自己好像也比较想知道，遂google之
| [root@dbrg-2 ~]# curl -I www.baidu.com HTTP/1.1 200 OK Date: Wed, 29 Jul 2009 02:51:19 GMT Server: BWS/1.0 Content-Length: 3509 Content-Type: text/html Cache-Control: private Expires: Wed, 29 Jul 2009 02:51:19 GMT Set-Cookie: BAIDUID=0D5F54C0853B7C38D6BD3A3E5EA63C44:FG=1; expires=Wed, 29-Jul-39 02:51:19 GMT; path=/; domain=.baidu.com P3P: CP=" OTI DSP COR IVA OUR IND COM " [root@dbrg-2 ~]# wget -S --spider www.baidu.com --10:51:34-- http://www.baidu.com/ => `index.html |
那么工具是实现了，如何用c来实现呢... 其实也很简单，我刚开始还走了点弯路想的是去查看wget or curl的源码，奈何那种代码相互之间依赖性太强实在不易阅读，于是自己用wireshark抓包， so easy！！！！有兴趣的自己去抓下
| #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <sys/socket.h> #include <netinet/in.h> #include <netdb.h> #define HTTPPORT 80 char* head = "HEAD / HTTP/1.0\r\n" "Accept: */*\r\n" "User-Agent: Wget/1.10.2 (Red Hat modified)\r\n" "Host:127.0.0.1\r\n" "Connection: Keep-Alive\r\n\r\n"; int connect_URL(char *domain,int port) { int sock; struct hostent * host; struct sockaddr_in server; host = gethostbyname(domain); if (host == NULL) { printf("gethostbyname error\n"); return -2; } sock = socket(AF_INET,SOCK_STREAM,0); if (sock < 0) { printf("invalid socket\n"); return -1; } memset(&server,0,sizeof(struct sockaddr_in)); memcpy(&server.sin_addr,host->h_addr_list[0],host->h_length); server.sin_family = AF_INET; server.sin_port = htons(port); return (connect(sock,(struct sockaddr *)&server,sizeof(struct sockaddr)) <0) ? -1 : sock; } int main() { int sock; int ret; char buf[100]; char *domain = "127.0.0.1"; FILE* fp = fopen("test","w+"); if(NULL == fp){ printf("can't open stockcode file!\n"); return -1; } sock = connect_URL(domain,HTTPPORT); if (sock <0){ printf("connetc err\n"); return -1; } send(sock,head,strlen(head),0); while(1) { if((ret=recv(sock,buf,100-1,0))<1) break; buf[ret]='\0'; printf("%s", buf); fprintf(fp,"%s",buf); //save http data } fclose(fp); close(sock); //printf("bye!\n"); return 0; } |
