《http解析》由会员分享，可在线阅读，更多相关《http解析（6页珍藏版）》请在金锄头文库上搜索。
1、大家都很熟悉 HTTP 协议的应用，因为每天都在网络上浏览着不少东西，也都 知道是 HTTP 协议是相当简单的。每次用 thunder 之类的下载软件下载网页， 当用到那个“用 thunder 下载全部链接”时总觉得很神奇。 后来想想，其实要实现这些下载功能也并不难，只要按照 HTTP 协议发送 request，然后对接收到的数据进行分析，如果页面上还有 href 之类的链接 指向标志就可以进行深一层的下载了。HTTP 协议目前用的最多的是 1.1 版本， 要全面透彻地搞懂它就参考 RFC2616 文档吧。源代码如下： /* http 客户端程序 httpclient.c */ #includ
2、e #include #include #include #include #include #include #include #include #include #include #include /httpclient.c 开始 /* 功能：搜索字符串右边起的第一个匹配字符 */ char * Rstrchr(char * s, char x) int i = strlen(s);if(!(*s) return 0;while(si-1) if(strchr(s + (i - 1), x) return (s + (i -1); else i-;return 0; /* 功能：把字符串转
3、换为全小写 */ void ToLowerCase(char * s) while(s s+; /* 功能：从字符串 src 中分析出网站地址和端口，并得到用户要下载的文件 */ void GetHost(char * src, char * web, char * file, int * port) char * pA;char * pB;memset(web, 0, sizeof(web);memset(file, 0, sizeof(file);*port = 0;if(!(*src) return;pA = src;if(!strncmp(pA, “http:/“, strlen(“h
4、ttp:/“) pA = src+strlen(“h ttp:/“);else if(!strncmp(pA, “https:/“, strlen(“https:/“) pA = src+st rlen(“https:/“);pB = strchr(pA, /);if(pB) memcpy(web, pA, strlen(pA) - strlen(pB);if(pB+1) memcpy(file, pB + 1, strlen(pB) - 1);filestrlen(pB) - 1 = 0;else memcpy(web, pA, strlen(pA);if(pB) webstrlen(pA)
5、 - strlen(pB) = 0;else webstrlen(pA) = 0;pA = strchr(web, :);if(pA) *port = atoi(pA + 1);else *port = 80; int main(int argc, char *argv) int sockfd;char buffer1024;struct sockaddr_in server_addr;struct hostent *host;int portnumber,nbytes;char host_addr256;char host_file1024;char local_file256;FILE *
6、 fp;char request1024;int send, totalsend;int i;char * pt;if(argc!=2)fprintf(stderr,“Usage:%s web-address/a/n“,argv0);exit(1);printf(“parameter.1 is: %s/n“, argv1);ToLowerCase(argv1);/*将参数转换为全小写*/printf(“lowercase parameter.1 is: %s/n“, argv1);GetHost(argv1, host_addr, host_file, /*分析网址、 端口、文件名等*/pri
7、ntf(“webhost:%s/n“, host_addr);printf(“hostfile:%s/n“, host_file);printf(“portnumber:%d/n/n“, portnumber);if(host=gethostbyname(host_addr)=NULL)/*取得主机 IP 地址*/fprintf(stderr,“Gethostname error, %s/n“, strerror(errno);exit(1);/* 客户程序开始建立 sockfd 描述符 */if(sockfd=socket(AF_INET,SOCK_STREAM,0)=-1)/*建立 SOC
8、KET 连接*/fprintf(stderr,“Socket Error:%s/a/n“,strerror(errno);exit(1);/* 客户程序填充服务端的资料 */bzero(server_addr.sin_family=AF_INET;server_addr.sin_port=htons(portnumber);server_addr.sin_addr=*(struct in_addr *)host-h_addr);/* 客户程序发起连接请求 */if(connect(sockfd,(struct sockaddr *)(exit(1);sprintf(request, “GET
9、/%s HTTP/1.1/r/nAccept: */*/r/nAccept- Language: zh-cn/r/n/ User-Agent: Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)/r/n/ Host: %s:%d/r/nConnection: Close/r/n/r/n“, host_file, host_addr, portnumber);printf(“%s“, request);/*准备 request，将要发送给主机*/*取得真实的文件名*/if(host_file else pt = 0;memset(local_f
10、ile, 0, sizeof(local_file);if(pt else memcpy(local_file, host_file, strlen(host_file) - 1);else if(host_file else strcpy(local_file, “index.html“);printf(“local filename to write:%s/n/n“, local_file);/*发送 http 请求 request*/send = 0;totalsend = 0;nbytes=strlen(request);while(totalsend nbytes) send = w
11、rite(sockfd, request + totalsend, nbytes - totalsend);if(send=-1) printf(“send error!%s/n“, strerror(errno);exit(0);totalsend+=send;printf(“%d bytes send OK!/n“, totalsend);fp = fopen(local_file, “a“);if(!fp) printf(“create file error! %s/n“, strerror(errno);return 0;printf(“/nThe following is the r
12、esponse header:/n“);i=0;/* 连接成功了，接收 http 响应，response */while(nbytes=read(sockfd,buffer,1)=1)if(i 4) if(buffer0 = /r | buffer0 = /n) i+;else i = 0;printf(“%c“, buffer0);/*把 http 头信息打印在屏幕上*/else fwrite(buffer, 1, 1, fp);/*将 http 主体信息写入文件*/i+;if(i%1024 = 0) fflush(fp);/*每 1K 时存盘一次*/fclose(fp);/* 结束通讯 *
13、/close(sockfd);exit(0); zjzj:/C_pram/practice/http_client$ ls httpclient httpclient.c zjzj:/C_pram/practice/http_client$ ./httpclient http:/ parameter.1 is: http:/ lowercase parameter.1 is: http:/ webhost: hostfile: portnumber:80GET / HTTP/1.1 Accept: */* Accept-Language: zh-cn User-Agent: Mozilla/4
14、.0 (compatible; MSIE 5.01; Windows NT 5.0) Host: :80 Connection: Closelocal filename to write:index.html163 bytes send OK!The following is the response header: HTTP/1.1 200 OK Date: Wed, 29 Oct 2008 10:41:40 GMTServer: BWS/1.0 Content-Length: 4216 Content-Type: text/html Cache-Control: private Expires: Wed, 29 Oct 2008 10:41:40 GMT Set-Cookie: BAIDUID=A93059C8DDF7F1BC47C10CAF9779030E:FG=1; expires=Wed, 29-Oct-38 10:41:40 GMT; path=/; domain= P3P: CP=“ OTI DSP COR IVA OUR IND COM “zjz
