1. 程式人生 > 程式設計 >C++ 獲取URL內容的例項

C++ 獲取URL內容的例項

我就廢話不多說了,大家還是直接看程式碼吧~

以下內容摘自StackOverFlow 連結

#ifndef HTTPUTIL_H
#define HTTPUTIL_H
#include <windows.h>
#include <string>
#include <stdio.h> 
using std::string; 
#pragma comment(lib,"ws2_32.lib") 
 
void mParseUrl(char *mUrl,string &serverName,string &filepath,string &filename);
SOCKET connectToServer(char *szServerName,WORD portNum);
int getHeaderLength(char *content);
char *readUrl2(char *szUrl,long &bytesReturnedOut,char **headerOut); 
 
char *sendRequest(char szUrl[]) {
 WSADATA wsaData;
 //char szUrl[] = "http://api.m.taobao.com/rest/api3.do?api=mtop.common.getTimestamp";
 long fileSize;
 char *memBuffer,*headerBuffer;
 
 memBuffer = headerBuffer = nullptr;
 
 if (WSAStartup(0x101,&wsaData) != 0)
  return nullptr;
 
 memBuffer = readUrl2(szUrl,fileSize,&headerBuffer);
 printf("returned from readUrl\n");
 printf("data returned:\n%s",memBuffer);
 if (fileSize != 0) {
  //delete (memBuffer);
  delete (headerBuffer);
 }
 WSACleanup();
 return memBuffer;
}
 
void mParseUrl(char *mUrl,string &filename) {
 string::size_type n;
 string url = mUrl;
 
 if (url.substr(0,7) == "http://")
  url.erase(0,7);
 
 if (url.substr(0,8) == "https://")
  url.erase(0,8);
 
 n = url.find('/');
 if (n != string::npos) {
  serverName = url.substr(0,n);
  filepath = url.substr(n);
  n = filepath.rfind('/');
  filename = filepath.substr(n + 1);
 }
 
 else {
  serverName = url;
  filepath = "/";
  filename = "";
 }
}
 
SOCKET connectToServer(char *szServerName,WORD portNum) {
 struct hostent *hp;
 unsigned int addr;
 struct sockaddr_in server;
 SOCKET conn;
 
 conn = socket(AF_INET,SOCK_STREAM,IPPROTO_TCP);
 if (conn == INVALID_SOCKET)
  return NULL;
 
 if (inet_addr(szServerName) == INADDR_NONE) {
  hp = gethostbyname(szServerName);
 } else {
  addr = inet_addr(szServerName);
  hp = gethostbyaddr((char *)&addr,sizeof(addr),AF_INET);
 }
 
 if (hp == nullptr) {
  closesocket(conn);
  return NULL;
 }
 
 server.sin_addr.s_addr = *((unsigned long *)hp->h_addr);
 server.sin_family = AF_INET;
 server.sin_port = htons(portNum);
 if (connect(conn,(struct sockaddr *)&server,sizeof(server))) {
  closesocket(conn);
  return NULL;
 }
 return conn;
}
 
int getHeaderLength(char *content) {
 const char *srchStr1 = "\r\n\r\n",*srchStr2 = "\n\r\n\r";
 char *findPos;
 int ofset = -1;
 
 findPos = strstr(content,srchStr1);
 if (findPos != nullptr) {
  ofset = findPos - content;
  ofset += strlen(srchStr1);
 }
 
 else {
  findPos = strstr(content,srchStr2);
  if (findPos != nullptr) {
   ofset = findPos - content;
   ofset += strlen(srchStr2);
  }
 }
 return ofset;
}
 
char *readUrl2(char *szUrl,char **headerOut) {
 const int bufSize = 512;
 char readBuffer[bufSize],sendBuffer[bufSize],tmpBuffer[bufSize];
 char *tmpResult = nullptr,*result;
 SOCKET conn;
 string server,filepath,filename;
 long totalBytesRead,thisReadSize,headerLen;
 
 mParseUrl(szUrl,server,filename);
 
 / step 1,connect //
 conn = connectToServer((char *)server.c_str(),80);
 
 / step 2,send GET request /
 sprintf(tmpBuffer,"GET %s HTTP/1.0",filepath.c_str());
 strcpy(sendBuffer,tmpBuffer);
 strcat(sendBuffer,"\r\n");
 sprintf(tmpBuffer,"Host: %s",server.c_str());
 strcat(sendBuffer,"\r\n");
 strcat(sendBuffer,"\r\n");
 send(conn,sendBuffer,strlen(sendBuffer),0);
 
 // SetWindowText(edit3Hwnd,sendBuffer);
 printf("Buffer being sent:\n%s",sendBuffer);
 
 / step 3 - get received bytes 
 // Receive until the peer closes the connection
 totalBytesRead = 0;
 while (1) {
  memset(readBuffer,bufSize);
  thisReadSize = recv (conn,readBuffer,bufSize,0);
 
  if ( thisReadSize <= 0 )
   break;
 
  tmpResult = (char *)realloc(tmpResult,thisReadSize + totalBytesRead);
 
  memcpy(tmpResult + totalBytesRead,thisReadSize);
  totalBytesRead += thisReadSize;
 }
 
 headerLen = getHeaderLength(tmpResult);
 long contenLen = totalBytesRead - headerLen;
 result = new char[contenLen + 1];
 memcpy(result,tmpResult + headerLen,contenLen);
 result[contenLen] = 0x0;
 char *myTmp;
 
 myTmp = new char[headerLen + 1];
 strncpy(myTmp,tmpResult,headerLen);
 myTmp[headerLen] = NULL;
 delete (tmpResult);
 *headerOut = myTmp;
 
 bytesReturnedOut = contenLen;
 closesocket(conn);
 return (result);
}
#endif // HTTPUTIL_H

測試程式碼:

#include <string>
#include <stdio.h>
#include "HttpUtil.h"
#include <iostream>
using std::string;
using namespace std; 
 
int main() {
 char *resData = sendRequest("http://api.m.taobao.com/rest/api3.do?api=mtop.common.getTimestamp");
 string str = resData;
 cout << endl << str << endl;
 delete resData;
 return 0;
}

補充知識:C++處理URL的方法,專案有用到,過程記錄如下

由於這塊需要轉換成unicode碼,也就是將字串傳換成unicode碼,因此需要對輸入的字串做處理,同時又分兩種情況,中文 非中文的處理,要區別對待,首先要對輸入的字串進行識別:

int 是不是中文(char *str)
{
char ch;
while (1)
{
ch = *str++;
if (ch == 0)
{
break;
} 
 
if (ch&0x80)
{
if (*str & 0x80)
{
return true;
}
}
else
{
return false;
}
}
return 0;
}

然後要進行相應轉換

//--------------------------------------------------------------------- 
//函式:W2C
//功能:將16位wchar_t轉換為 8位char[2]
//引數:w_cn為待轉換的16位字元,c_cn[]為轉換後的8位字元
//備註:wchar_t的高位位元組應該儲存在char陣列的低位位元組
//作者:xxxx
//---------------------------------------------------------------------
void W2C(wchar_t w_cn,char c_cn[]){c_cn[0] = w_cn >> 8 ;c_cn[1] = (char)w_cn ;}

然後主體轉換程式碼:

//-------------------------------------------------------------------
//函式:ToHex
//功能:將16位字串轉換為十六進位制字串
//引數:待轉換的字串,字串長度
//返回值:轉換後的字串
//作者:xxxx
//-------------------------------------------------------------------
CString ToHex(CString Data,long nDataLength)
{
CString sResult;
for (long nLoop=0; nLoop<nDataLength; nLoop++)
{
wchar_t ch = Data.GetAt(nLoop);
CHAR buff[MAX_PATH] = {0};
LPCWSTR str = &ch;
WideCharToMultiByte(CP_ACP,(LPCWSTR)str,-1,buff,MAX_PATH,0);
if (IncludeChinese(buff))
{
char c_cn[2]={'0'};
W2C(ch,c_cn);
static const char *hex = "0123456789ABCDEF";
for(int i=0;i<2;i++)
{
unsigned char chHexA = hex[((unsigned char)(c_cn[i]) >> 4) & 0x0f];
unsigned char chHexB = hex[(unsigned char)(c_cn[i]) & 0x0f];
sResult += (char)chHexA;
sResult += (char)chHexB;
}
}
else
{
sResult += ch;
} 
}
 
return sResult;
}

到這裡基本上結束了~也查看了一些資料,雖說這個功能簡單,但是過程有點曲折。但總算完成了,留個紀念吧~希望對其他人有幫助~希望大家多多支援我們。