httpreqparse.cpp

对HTTP消息进行解析

		//table->RespServiceBuffer=...
		//table->ResponseCode=...
		if(stricmp((char *)(table->ResponseCode),"500")
			&&stricmp((char *)(table->ResponseCode),"501"))//判断响应码
		//if(table->Content_Length!=0&&(!stricmp((char *)(table->Content_Type),"text/html")))
		if(table->Content_Length!=0)
		{
			if(func_HTTP_ParseHTTPInfoData2(HTTPData, &MsgHead, &MsgBody))//HTTP数据解析处理
			{
				//printf("MsgHead----->%s\n",MsgHead);
				//printf("MsgBody----->%s\n",MsgBody);
				//printf("MsgBody2----->%s\n",MsgBody2);
				if(func_HTTP_ParseHTTPHtmlStart(MsgBody,&befHtml,&behHtml))
				{
					printf("查到html\n");
					table->HtmStart=1;
					strcpy(filename,"unknown");
					printf("behHtml----->%s\n",behHtml);
					
					if(func_HTTP_ParseHTTPStytleStart(behHtml,&befStytle,&behStytle))
					{
							printf("behStytle----->%s\n",behStytle);
							if(func_HTTP_ParseHTTPStytleEnd(behStytle,&bef_Stytle,&beh_Stytle))
							{
								printf("bef_Stytle----->%s\n",bef_Stytle);
								printf("beh_Stytle----->%s\n",beh_Stytle);
								strcpy(filename,bef_Stytle+7);
								
								printf("filename----->%s\n",filename);
											
								htmfilename=CString("e:\\outdata\\")+CString(filename)+CString(".htm");
								
								table->HtmFileName=htmfilename;

								fpHtm1=fopen(htmfilename,"w");
								fprintf(fpHtm1,"%s",behHtml);
								fprintf(fpHtm1,"%s","<");
								fprintf(fpHtm1,"%s",beh_Stytle);
								fclose(fpHtm1);
							
							}//func_HTTP_ParseHTTPStytleEnd
					}//func_HTTP_ParseHTTPStytleStart
					else
					{
								printf("filename----->%s\n",filename);
				
								htmfilename=CString("e:\\outdata\\")+CString(filename)+CString(".htm");
								
								table->HtmFileName=htmfilename;

								fpHtm1=fopen(htmfilename,"w");
								fprintf(fpHtm1,"%s",behHtml);
								fclose(fpHtm1);
					}
					
					
				}//func_HTTP_ParseHTTPHtmlStart
				//找到</HTML>则此轮结束，释放工作区
				if(func_HTTP_ParseHTTPHtmlEnd(HTTPData,&bef_Html,&beh_Html))
				{
						func_ReleaseWorkTable(ReqRespSeq);
				}
				
		
			}//func_HTTP_ParseHTTPInfoData2
		}//Content_Length!=0

	}//HTTP/1.1
	else//完全消息体
	{
		if(table==NULL)
		{
			for(i=0;i<MaxRequestNum;i++)
			{
				if(HTTPRequestSeqFlag[i]==0)
				{
					ReqRespSeq=i;
					HTTPRequestSeqFlag[i]=1;
					break;
				}
			}

			if(i>=MaxRequestNum)
			{printf("工作区满!\n");return(0);}
	
			table=&HTTPWorkTable[ReqRespSeq];
		}


		printf("此IP包是完全消息体内容！\n");
		if(table->HTTPState==HTTP_Request_State)
		{
			table->HTTPState=HTTP_RequestBody_State;
		}
		else if(table->HTTPState==HTTP_Response_State||table->HTTPState==HTTP_ResponseBody_State)
		{
			table->HTTPState=HTTP_ResponseBody_State;

			htmfilename=table->HtmFileName;
			printf("是响应消息消息体！\n");

			/*if(table->GzipState==1)
			{
				func_GzipDecode(HTTPData,&HTTPData2);//有解码函数吗？
				HTTPData=HTTPData2;
			}*/


			if(func_HTTP_ParseHTTPHtmlEnd(HTTPData,&bef_Html,&beh_Html))
			{
				printf("bef_Html----->%s\n",bef_Html);

				fpHtm1=fopen(htmfilename,"a");
				fprintf(fpHtm1,"%s",bef_Html);
				fprintf(fpHtm1,"%s","</HTML>");
				fclose(fpHtm1);
				func_ReleaseWorkTable(ReqRespSeq);

				//if(table->Content_Length!=0)
				//{

				//}
			}
			else
			{
				if(table->HtmStart==1)
				{
					fpHtm1=fopen(htmfilename,"a");
					fprintf(fpHtm1,"%s",HTTPData);
					
					fclose(fpHtm1);
				}


			}

		}
		else
			printf("state error\n");


	}
	


	return(1);
}
//func_HTTP_ParseHTTPHtmlStart
BOOL func_HTTP_ParseHTTPHtmlStart(char* pStr, char** ppToken1, char** ppToken2)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "<html");
	if(pch) //找到匹配字符第一个' '
	{
		*ppToken2=pch;//ppToken2字符串从此开始
		return TRUE;
	}
	else
	{
		pch=strstr(pStr, "<HTML");
		if(pch) //找到匹配字符第一个' '
		{
			*ppToken2=pch;//ppToken2字符串从此开始
			return TRUE;
		}
	}
	return FALSE;
}
//func_HTTP_ParseHTTPStytleStart
BOOL func_HTTP_ParseHTTPStytleStart(char* pStr, char** ppToken1, char** ppToken2)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "<TITLE>");
	if(pch) //找到匹配字符第一个' '
	{
		//*pch='\0';//ppToken1字符串至此结束
		//pch++;
		*ppToken2=pch;//ppToken2字符串从此开始
		
		return TRUE;
	}
	else
	{
		pch=strstr(pStr, "<title>");
		if(pch) //找到匹配字符第一个' '
		{
			//*pch='\0';//ppToken1字符串至此结束
			//pch++;
			*ppToken2=pch;//ppToken2字符串从此开始
		
			return TRUE;
		}

	}
	return FALSE;
}
//func_HTTP_ParseHTTPStytleEnd
BOOL func_HTTP_ParseHTTPStytleEnd(char* pStr, char** ppToken1, char** ppToken2)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "</TITLE>");
	if(pch) //找到匹配字符第一个' '
	{
		*pch='\0';//ppToken1字符串至此结束
		pch++;	
		*ppToken2=pch;//ppToken2字符串从此开始
		
	
		return TRUE;
	}
	else
	{
		pch=strstr(pStr, "</title>");
		if(pch) //找到匹配字符第一个' '
		{
			*pch='\0';//ppToken1字符串至此结束
			pch++;	
			*ppToken2=pch;//ppToken2字符串从此开始
		
	
			return TRUE;
		}
	}
	return FALSE;
}
//func_HTTP_ParseHTTPHtmlEnd
BOOL func_HTTP_ParseHTTPHtmlEnd(char* pStr, char** ppToken1, char** ppToken2)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "</html>");
	if(pch) //找到匹配字符串第一个
	{
		*pch='\0';//ppToken1字符串至此结束
		pch++;
		*ppToken2=pch;//ppToken2字符串从此开始
	
		return TRUE;
	}
	else
	{
		pch=strstr(pStr, "</HTML>");
		if(pch) //找到匹配字符串第一个
		{
		*pch='\0';//ppToken1字符串至此结束
		pch++;
		*ppToken2=pch;//ppToken2字符串从此开始
	
		return TRUE;
		}
	}
	return FALSE;
}
int func_HTTP_Init()
{
	int ii;
	struct HTTPWorkTable_STRU *table=NULL;


	
	for(ii=0;ii<MaxRequestNum;ii++)
	{
		table=&HTTPWorkTable[ii];
		table->HTTPState=0;
		strcpy(table->ResponseCode,"\0");
		strcpy(table->Content_Type,"\0");
		strcpy(table->Content_Coding,"\0");
		table->HtmFileName="\0";
		table->Content_Length=1;
		table->ReqServiceBuffer=NULL;
		table->RespServiceBuffer=NULL;
		table->HtmStart=0;
		table->GETStart=0;
		table->GzipState=0;

		HTTPRequestSeqFlag[ii]=0;
	}

	return(1);

}
int func_ReleaseWorkTable(int seq)
{
		struct HTTPWorkTable_STRU *table=NULL;

		table=&HTTPWorkTable[seq];
		table->HTTPState=0;
		strcpy(table->ResponseCode,"\0");
		strcpy(table->Content_Type,"\0");
		strcpy(table->Content_Coding,"\0");
		table->HtmFileName="\0";
		table->Content_Length=1;
		table->ReqServiceBuffer=NULL;
		table->RespServiceBuffer=NULL;
		table->HtmStart=0;
		table->GETStart=0;
		table->GzipState=0;

		//HTTPRequestSeqFlag[seq]=0;
		return(1);
}


/*int func_ParseHeadFieldsLoc(char *MsgHead,char *str1,char *str2,char *str3,char *str4)
{
	
	char *pch1=strstr(MsgHead, str1);
	char *pch2=strstr(MsgHead, str2);
	char *pch3=strstr(MsgHead, str3);
	char *pch4=strstr(MsgHead, str4);

    //排序......

	if(pch) //找到匹配字符串
	{
		//*pch='\0';//ppToken1字符串至此结束
		//pch++;
		*ppToken2=pch;//ppToken2字符串从此开始
		pch=strstr(ppToken2, "\r\n");
		if(pch)
		{
			*pch='\0';//ppToken1字符串至此结束
			//pch++;
			//*ppToken2=pch;//ppToken2字符串从此开始
			return TRUE;
		}
	}
	return FALSE;
	do
	{
			if((*(pToken3+len)=='H')&&(*(pToken3+len+1)=='o')&&(*(pToken3+len+2)=='s')
				&&(*(pToken3+len+3)=='t')&&(*(pToken3+len+4)==':'))
			{
					yes=0;
					temp2=pToken3;
					Parse2(temp2+len+5, &pToken4);
					printf("解析host--->%s\n",pToken4);
			}
			len++;
	 }while(yes);			
	 
}*/

int func_ParseAcceptEncodingGZIP(char* pStr, char** ppToken1, char** ppToken3)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "Accept-Encoding: gzip");
	if(pch) //找到匹配字符第一个' '
	{
		*pch='\0';//ppToken1字符串至此结束
		pch++;
		*ppToken3=pch;
		return TRUE;
	}
	return FALSE;
}
int func_ParseContentEncodingGZIP(char* pStr, char** ppToken1, char** ppToken3)
{
	*ppToken1=pStr;
	char* pch=strstr(pStr, "Content-Encoding: gzip");
	if(pch) //找到匹配字符第一个' '
	{
		*pch='\0';//ppToken1字符串至此结束
		pch++;
		*ppToken3=pch;
		return TRUE;
	}
	return FALSE;
}
int func_GzipDecode(char* pStr, char** ppToken1)
{
	return(1);
}