VC实现访问网站，读取信息

今天更新 吸血鬼日记，为了最早发现人人影视的更新，而且不用麻烦地老是去刷网页，就想用C语言来做一个小程序来实现它。

需要用到libcurl库。思路是访问网页，把网页源码读到数组中，扫描该数组是否有需要的信息。

libcurl安装方法：http://www.2cto.com/kf/201006/51492.html

libcurl相关学习资料：http://bbs.chinaunix.net/thread-2070202-1-1.html

如果遇到报错“无法定位序数55于zlib1.dll”，可用的zlib1.dll下载地址：http://www.xiadll.com/info/zlib1.dll.html

读取到网页乱码的原因：http://linhs.blog.51cto.com/370259/124765 

网页乱码解决方法http://www.iteye.com/topic/604821

 

最后得到我的代码

  1 #include <stdio.h>
  2 #include <stdlib.h>
  3 #include <string.h>
  4 #include <windows.h>
  5 #include <iostream>
  6 using namespace std;
  7 
  8 #include <curl/curl.h>
  9 
 10 #pragma comment(lib, "libcurl.lib") 
 11 //#pragma comment(lib, "libcurl_imp.lib")
 12  
 13 struct MemoryStruct {
 14   char *memory;
 15   size_t size;
 16 };
 17  
 18  
 19 static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb, void *userp)
 20 {
 21   size_t realsize = size * nmemb;
 22   struct MemoryStruct *mem = (struct MemoryStruct *)userp;
 23  
 24   mem->memory = (char*)realloc(mem->memory, mem->size + realsize + 1);
 25   if (mem->memory == NULL) {
 26     /* out of memory! */ 
 27     printf("not enough memory (realloc returned NULL)\n");
 28     exit(EXIT_FAILURE);
 29   }
 30  
 31   memcpy(&(mem->memory[mem->size]), contents, realsize);
 32   mem->size += realsize;
 33   mem->memory[mem->size] = 0;
 34 
 35 
 36   return realsize;
 37 }
 38 
 39 
 40 int transfer(char * utf8str)
 41 {
 42   //UTF8转GBK
 43  int len_wchart = MultiByteToWideChar(CP_UTF8,0,utf8str,-1,NULL,0);   
 44  wchar_t * unicode_2 = new wchar_t[len_wchart] ;
 45  MultiByteToWideChar(CP_UTF8,0,utf8str,-1,unicode_2,len_wchart);
 46  int len_gbk = WideCharToMultiByte(CP_ACP,0,unicode_2,-1,NULL,0,NULL,NULL);  
 47  char * gbkstr = new char[len_gbk];
 48  WideCharToMultiByte(CP_ACP,0,unicode_2,-1,gbkstr,len_gbk,NULL,NULL);  
 49  
 50 // cout<< "-------- UTF8 => GBK --------" <<endl;
 51 // cout<<"GBK字符串长度:"<<strlen(gbkstr)<<endl<<"GBK串:"<<gbkstr<<endl;
 52 
 53  strcpy(utf8str,gbkstr);
 54  return 1;
 55 }
 56 
 57  
 58  
 59 int main(void)
 60 {
 61   CURL *curl_handle;
 62  
 63   struct MemoryStruct chunk;
 64   char *tmp;
 65   int i,j;
 66   char *object="S04E15";
 67  // FILE *fp;
 68 
 69   chunk.memory =(char*)malloc(1);  /* will be grown as needed by the realloc above */ 
 70   chunk.size = 0;    /* no data at this point */ 
 71  
 72   curl_global_init(CURL_GLOBAL_ALL);
 73  
 74   /* init the curl session */ 
 75   curl_handle = curl_easy_init();
 76  
 77   /* specify URL to get */ 
 78   curl_easy_setopt(curl_handle, CURLOPT_URL, "http://www.yyets.com/php/resource/10985");
 79  
 80   /* send all data to this function  */ 
 81   curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);
 82  
 83   /* we pass our 'chunk' struct to the callback function */ 
 84   curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);
 85  
 86   /* some servers don't like requests that are made without a user-agent
 87      field, so we provide one */ 
 88 //  curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "libcurl-agent/1.0");
 89  
 90 
 91  
 92   /* get it! */ 
 93   curl_easy_perform(curl_handle);
 94  
 95   /* cleanup curl stuff */ 
 96   curl_easy_cleanup(curl_handle);
 97  
 98   /*
 99    * Now, our chunk.memory points to a memory block that is chunk.size
100    * bytes big and contains the remote file.
101    *
102    * Do something nice with it!
103    *
104    * You should be aware of the fact that at this point we might have an
105    * allocated data block, and nothing has yet deallocated that data. So when
106    * you're done with it, you should free() it as a nice application.
107    */ 
108  
109 //  printf("%lu bytes retrieved\n", (long)chunk.size);
110 
111   transfer(chunk.memory);
112 
113   /* 
114    * This part of code can store the source code of the webpage to file
115    * Mainly used for debug
116    */
117 /*
118   if ((fp=fopen("webpage.txt","w")) == NULL) 
119   {
120       fprintf(stderr, "Cannot open output file.\n");
121       return 1;
122   }
123  // fwrite(chunk.memory,chunk.size,1,fp);
124   fprintf(fp,"%s",chunk.memory);
125 
126   fclose(fp);
127 */
128 
129 
130   /*
131    * Now, we are hunting for the desired resourses
132    * Have fun with it!
133    */
134 
135   for(i=0;i<chunk.size;i++)
136   {
137      for(j=0;j<strlen(object);j++)
138     {
139         if(*(chunk.memory+i+j)!=*(object+j))
140             break;
141     }
142      if(j==strlen(object))
143      {
144          printf("FIND %s !!!\n",object);
145          break;
146      }
147   }
148 
149   if(i==chunk.size)
150   {
151       printf("Failed in finding it...\n");
152   }
153 
154   if(chunk.memory)
155     free(chunk.memory);
156  
157   /* we're done with libcurl, so clean it up */ 
158   curl_global_cleanup();
159  
160   return 0;
161 }

 

posted @ 2013-02-22 16:46  菜鸟飞  阅读(3065)  评论(0)  编辑  收藏  举报