C++ 获取URL内容的实例

我就废话不多说了，大家还是直接看代码吧~

以下内容摘自StackOverFlow 链接

#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 &serverName, string &filepath, 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, long &bytesReturnedOut, 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, filepath, 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, tmpBuffer);
 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, 0, bufSize);
  thisReadSize = recv (conn, readBuffer, bufSize, 0);
 
  if ( thisReadSize <= 0 )
   break;
 
  tmpResult = (char *)realloc(tmpResult, thisReadSize + totalBytesRead);
 
  memcpy(tmpResult + totalBytesRead, readBuffer, 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

测试代码：

#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;
}

补充知识：C++处理URL的方法，项目有用到，过程记录如下

由于这块需要转换成unicode码，也就是将字符串传换成unicode码，因此需要对输入的字符串做处理，同时又分两种情况，中文 非中文的处理，要区别对待，首先要对输入的字符串进行识别：

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;
}

然后要进行相应转换

//--------------------------------------------------------------------- 
//函数：W2C
//功能：将16位wchar_t转换为 8位char[2]
//参数：w_cn为待转换的16位字符，c_cn[]为转换后的8位字符
//备注：wchar_t的高位字节应该存储在char数组的低位字节
//作者：xxxx
//---------------------------------------------------------------------
void W2C(wchar_t w_cn , char c_cn[]){c_cn[0] = w_cn >> 8 ;c_cn[1] = (char)w_cn ;}

然后主体转换代码：

//-------------------------------------------------------------------
//函数：ToHex
//功能：将16位字符串转换为十六进制字符串
//参数：待转换的字符串，字符串长度
//返回值：转换后的字符串
//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, 0, (LPCWSTR)str, -1, buff, MAX_PATH, 0, 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;
}

到这里基本上结束了~也查看了一些资料，虽说这个功能简单，但是过程有点曲折。但总算完成了，留个纪念吧~希望对其他人有帮助~希望大家多多支持自由互联。