大家都很熟悉HTTP協(xié)議的應(yīng)用，因?yàn)槊刻於荚诰W(wǎng)絡(luò)上瀏覽著不少東西，也都知道是HTTP協(xié)議是相當(dāng)簡(jiǎn)單的。每次用 thunder之類的下載軟件下載網(wǎng)頁(yè)，當(dāng)用到那個(gè)“用thunder下載全部鏈接”時(shí)總覺(jué)得很神奇。
后來(lái)想想，其實(shí)要實(shí)現(xiàn)這些下載功能也并不難，只要按照HTTP協(xié)議發(fā)送request，然后對(duì)接收到的數(shù)據(jù)進(jìn)行分析，如果頁(yè)面上還有href之類的鏈接指 向標(biāo)志就可以進(jìn)行深一層的下載了。HTTP協(xié)議目前用的最多的是1.1 版本，要全面透徹地搞懂它就參考RFC2616文檔吧。我是怕rfc文檔了的,要看自己去看吧^_^
源代碼如下：
/******* http客戶端程序 httpclient.c ************/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <errno.h>
#include <unistd.h>
#include <netinet/in.h>
#include <limits.h>
#include <netdb.h>
#include <arpa/inet.h>
#include <ctype.h>

//////////////////////////////httpclient.c 開(kāi)始///////////////////////////////////////////


/********************************************
功能：搜索字符串右邊起的第一個(gè)匹配字符
********************************************/
char * Rstrchr(char * s, char x) {
  int i = strlen(s);
  if(!(*s)) return 0;
  while(s[i-1]) if(strchr(s + (i - 1), x)) return (s + (i - 1)); else i--;
  return 0;
}

/********************************************
功能：把字符串轉(zhuǎn)換為全小寫
********************************************/
void ToLowerCase(char * s) {
  while(s && *s) {*s=tolower(*s);s++;}
}

/**************************************************************
功能：從字符串src中分析出網(wǎng)站地址和端口，并得到用戶要下載的文件
***************************************************************/
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("http://"))) pA = src+strlen("http://");
  else if(!strncmp(pA, "https://", strlen("https://"))) pA = src+strlen("https://");
  pB = strchr(pA, '/');
  if(pB) {
    memcpy(web, pA, strlen(pA) - strlen(pB));
    if(pB+1) {
      memcpy(file, pB + 1, strlen(pB) - 1);
      file[strlen(pB) - 1] = 0;
    }
  }
  else memcpy(web, pA, strlen(pA));
  if(pB) web[strlen(pA) - strlen(pB)] = 0;
  else web[strlen(pA)] = 0;
  pA = strchr(web, ':');
  if(pA) *port = atoi(pA + 1);
  else *port = 80;
}


int main(int argc, char *argv[])
{
  int sockfd;
  char buffer[1024];
  struct sockaddr_in server_addr;
  struct hostent *host;
  int portnumber,nbytes;
  char host_addr[256];
  char host_file[1024];
  char local_file[256];
  FILE * fp;
  char request[1024];
  int send, totalsend;
  int i;
  char * pt;

  if(argc!=2)
  {
    fprintf(stderr,"Usage:%s web-address\a\n",argv[0]);
    exit(1);
  }
  printf("parameter.1 is: %s\n", argv[1]);
  ToLowerCase(argv[1]);/*將參數(shù)轉(zhuǎn)換為全小寫*/
  printf("lowercase parameter.1 is: %s\n", argv[1]);

  GetHost(argv[1], host_addr, host_file, &portnumber);/*分析網(wǎng)址、端口、文件名等*/
  printf("webhost:%s\n", host_addr);
  printf("hostfile:%s\n", host_file);
  printf("portnumber:%d\n\n", portnumber);

  if((host=gethostbyname(host_addr))==NULL)/*取得主機(jī)IP地址*/
  {
    fprintf(stderr,"Gethostname error, %s\n", strerror(errno));
    exit(1);
  }

  /* 客戶程序開(kāi)始建立 sockfd描述符 */
  if((sockfd=socket(AF_INET,SOCK_STREAM,0))==-1)/*建立SOCKET連接*/
  {
    fprintf(stderr,"Socket Error:%s\a\n",strerror(errno));
    exit(1);
  }

  /* 客戶程序填充服務(wù)端的資料 */
  bzero(&server_addr,sizeof(server_addr));
  server_addr.sin_family=AF_INET;
  server_addr.sin_port=htons(portnumber);
  server_addr.sin_addr=*((struct in_addr *)host->h_addr);

  /* 客戶程序發(fā)起連接請(qǐng)求 */
  if(connect(sockfd,(struct sockaddr *)(&server_addr),sizeof(struct sockaddr))==-1)/*連接網(wǎng)站*/
  {
    fprintf(stderr,"Connect Error:%s\a\n",strerror(errno));
    exit(1);
  }

  sprintf(request, "GET /%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);/*準(zhǔn)備request，將要發(fā)送給主機(jī)*/

  /*取得真實(shí)的文件名*/
  if(host_file && *host_file) pt = Rstrchr(host_file, '/');
  else pt = 0;

  memset(local_file, 0, sizeof(local_file));
  if(pt && *pt) {
    if((pt + 1) && *(pt+1)) strcpy(local_file, pt + 1);
    else memcpy(local_file, host_file, strlen(host_file) - 1);
  }
  else if(host_file && *host_file) strcpy(local_file, host_file);
  else strcpy(local_file, "index.html");
  printf("local filename to write:%s\n\n", local_file);

  /*發(fā)送http請(qǐng)求request*/
  send = 0;totalsend = 0;
  nbytes=strlen(request);
  while(totalsend < nbytes) {
    send = write(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 response header:\n");
  i=0;
  /* 連接成功了，接收http響應(yīng)，response */
  while((nbytes=read(sockfd,buffer,1))==1)
  {
    if(i < 4) {
      if(buffer[0] == '\r' || buffer[0] == '\n') i++;
      else i = 0;
      printf("%c", buffer[0]);/*把http頭信息打印在屏幕上*/
    }
    else {
      fwrite(buffer, 1, 1, fp);/*將http主體信息寫入文件*/
      i++;
      if(i%1024 == 0) fflush(fp);/*每1K時(shí)存盤一次*/
    }
  }
  fclose(fp);
  /* 結(jié)束通訊 */
  close(sockfd);
  exit(0);
}

zj@zj:~/C_pram/practice/http_client$ ls
httpclient  httpclient.c
zj@zj:~/C_pram/practice/http_client$ ./httpclient http://www.baidu.com/
parameter.1 is: http://www.baidu.com/
lowercase parameter.1 is: http://www.baidu.com/
webhost:www.baidu.com
hostfile:
portnumber:80

GET / HTTP/1.1
Accept: */*
Accept-Language: zh-cn
User-Agent: Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)
Host: www.baidu.com:80
Connection: Close

local filename to write:index.html

163 bytes send OK!

The following is the response header:
HTTP/1.1 200 OK
Date: Wed, 29 Oct 2008 10:41:40 GMT
Server: 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=.baidu.com
P3P: CP=" OTI DSP COR IVA OUR IND COM "

zj@zj:~/C_pram/practice/http_client$ ls
httpclient  httpclient.c  index.html