C++ 获取URL内容的实例

2023-07-08 12:19:05 80

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

#ifndefHTTPUTIL_H
#defineHTTPUTIL_H
#include
#include
#include
usingstd::string;
#pragmacomment(lib,"ws2_32.lib")

voidmParseUrl(char*mUrl,string&serverName,string&filepath,string&filename);
SOCKETconnectToServer(char*szServerName,WORDportNum);
intgetHeaderLength(char*content);
char*readUrl2(char*szUrl,long&bytesReturnedOut,char**headerOut);

char*sendRequest(charszUrl[]){
WSADATAwsaData;
//charszUrl[]="http://api.m.taobao.com/rest/api3.do?api=mtop.common.getTimestamp";
longfileSize;
char*memBuffer,*headerBuffer;

memBuffer=headerBuffer=nullptr;

if(WSAStartup(0x101,&wsaData)!=0)
returnnullptr;

memBuffer=readUrl2(szUrl,fileSize,&headerBuffer);
printf("returnedfromreadUrl\n");
printf("datareturned:\n%s",memBuffer);
if(fileSize!=0){
//delete(memBuffer);
delete(headerBuffer);
}
WSACleanup();
returnmemBuffer;
}

voidmParseUrl(char*mUrl,string&serverName,string&filepath,string&filename){
string::size_typen;
stringurl=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="";
}
}

SOCKETconnectToServer(char*szServerName,WORDportNum){
structhostent*hp;
unsignedintaddr;
structsockaddr_inserver;
SOCKETconn;

conn=socket(AF_INET,SOCK_STREAM,IPPROTO_TCP);
if(conn==INVALID_SOCKET)
returnNULL;

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);
returnNULL;
}

server.sin_addr.s_addr=*((unsignedlong*)hp->h_addr);
server.sin_family=AF_INET;
server.sin_port=htons(portNum);
if(connect(conn,(structsockaddr*)&server,sizeof(server))){
closesocket(conn);
returnNULL;
}
returnconn;
}

intgetHeaderLength(char*content){
constchar*srchStr1="\r\n\r\n",*srchStr2="\n\r\n\r";
char*findPos;
intofset=-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);
}
}
returnofset;
}

char*readUrl2(char*szUrl,long&bytesReturnedOut,char**headerOut){
constintbufSize=512;
charreadBuffer[bufSize],sendBuffer[bufSize],tmpBuffer[bufSize];
char*tmpResult=nullptr,*result;
SOCKETconn;
stringserver,filepath,filename;
longtotalBytesRead,thisReadSize,headerLen;

mParseUrl(szUrl,server,filepath,filename);

/step1,connect//
conn=connectToServer((char*)server.c_str(),80);

/step2,sendGETrequest/
sprintf(tmpBuffer,"GET%sHTTP/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("Bufferbeingsent:\n%s",sendBuffer);

/step3-getreceivedbytes
//Receiveuntilthepeerclosestheconnection
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);
longcontenLen=totalBytesRead-headerLen;
result=newchar[contenLen+1];
memcpy(result,tmpResult+headerLen,contenLen);
result[contenLen]=0x0;
char*myTmp;

myTmp=newchar[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
#include
#include"HttpUtil.h"
#include
usingstd::string;
usingnamespacestd;

intmain(){
char*resData=sendRequest("http://api.m.taobao.com/rest/api3.do?api=mtop.common.getTimestamp");
stringstr=resData;
cout<
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)
{
charch;
while(1)
{
ch=*str++;
if(ch==0)
{
break;
}

if(ch&0x80)
{
if(*str&0x80)
{
returntrue;
}
}
else
{
returnfalse;
}
}
return0;
}
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
//---------------------------------------------------------------------
voidW2C(wchar_tw_cn,charc_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
//-------------------------------------------------------------------
CStringToHex(CStringData,longnDataLength)
{
CStringsResult;
for(longnLoop=0;nLoop>4)&0x0f];
unsignedcharchHexB=hex[(unsignedchar)(c_cn[i])&0x0f];
sResult+=(char)chHexA;
sResult+=(char)chHexB;
}
}
else
{
sResult+=ch;
}
}

returnsResult;
}
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~希望大家多多支持毛票票。

C++ 获取URL内容的实例

热门推荐

随机推荐