获取网页编码问题和防止出现999错误

[huyidao21]

需要采集的是http://cn.biz.yahoo.com/iframe2/shl/zjlx/xarchives/600396.html
不过我试过了很多编码，都是乱码，有高手帮忙看看？始终没有发现他到底使用的什么编码
模拟访问，不过采集多了会出现999错误，被封掉IP。有好的解决办法吗？除了使用代理。

[huyidao21]

一天了，还没有高手可以指点一下吗？

[chehw]

text/html; charset=GBK
用的是GBK

[chehw]

解码结果:

<link href=../css-hq.css rel=stylesheet type=text/css>
<table class=12text cellSpacing=1 cellPadding=2 width=100% bgColor=#79b0e6 border=0><tr bgColor=#e5f2ff><td width=24%> </TD><td width=19% align=center>今日</TD><td width=19% align=center>5日</TD><td width=19% align=center>10日</TD><td width=19% align=center>20日</TD></TR><tr bgcolor=#ffffff><td>机构资金进出(万元)</td><td><font color=red>↑91.70</font></td><td><font color=red>↑1867.32</font></td><td><font color=red>↑9189.13</font></td><td><font color=red>↑29723.11</font></td></tr><tr bgcolor=#ffffff><td>资金进出（万元）</td><td><font color=green>↓-1265.44</font></td><td><font color=green>↓-5019.13</font></td><td><font color=green>↓-1877.42</font></td><td><font color=red>↑13660.59</font></td></tr><tr bgcolor=#ffffff><td>机构交易成本(元)</td><td>19.94</td><td>20.10</td><td>19.73</td><td>18.67</td></tr><tr bgcolor=#ffffff><td>机构交易额(万元)</td><td>1741.05</td><td>18006.71</td><td>44487.55</td><td>105532.90</td></tr><tr bgcolor=#ffffff><td>散户交易额(万元)</td><td>7295.79</td><td>42098.52</td><td>91521.27</td><td>164404.10</td></tr><tr bgcolor=#ffffff><td>散户资金进出(万元)</td><td><font color=green>↓-1357.14</font></td><td><font color=green>↓-6886.45</font></td><td><font color=green>↓-11066.54</font></td><td><font color=green>↓-16062.52</font></td></tr><tr bgcolor=#ffffff><td>机构、散户资金比</td><td>1：4.19</td><td>1：2.34</td><td>1：2.06</td><td>1：1.56</td></tr><tr bgcolor=#ffffff><td>机构换手率(%)</td><td>0.35</td><td>3.61</td><td>9.09</td><td>22.80</td></tr><tr bgcolor=#ffffff><td>总换手率(%)</td><td>1.83</td><td>12.06</td><td>27.77</td><td>58.09</td></tr></TABLE><!-- w5.biz.cnb.yahoo.com uncompressed/chunked Tue Jan  1 20:36:47 CST 2008 -->

[wsj1983920]

支持一下！！！！！！！

[bat800]

友情帮你顶一下！没有做过。

[huyidao21]

to chehw:
我也曾经试过GBK的，一样是乱码啊。能否SHOW一下你的代码？

[chehw]

int CMainWindow::NavigateTo(LPCTSTR lpszUrl)
{
	DWORD dwSize=0;
	DWORD dwRead;
	DWORD dwTotalRead=0;
	HINTERNET hSession=NULL,
		hConnect=NULL,
		hRequest=NULL;
	BOOL rc=FALSE;
	LPSTR buffer;
	LPWSTR wszText=NULL;

	TCHAR szDomain[MAX_PATH]=TEXT("");
	TCHAR szVirPath[1024]=TEXT("");

	TCHAR * pCursor=(TCHAR *)_tcschr(lpszUrl, TEXT('/'));
	if(NULL!=pCursor) 
	{
		lstrcpyn(szDomain, lpszUrl, pCursor-lpszUrl+1);
		lstrcpy(szVirPath, pCursor+1);
	}else
		lstrcpyn(szDomain, lpszUrl, MAX_PATH);

	hSession=WinHttpOpen(L"WinHttpTest - NavigateTo", WINHTTP_ACCESS_TYPE_NO_PROXY, WINHTTP_NO_PROXY_NAME, WINHTTP_NO_PROXY_BYPASS,0);
	if(NULL==hSession) goto Label_Exit;

	hConnect=WinHttpConnect(hSession, szDomain, INTERNET_DEFAULT_PORT, 0);
	if(NULL==hConnect) goto Label_Exit;

	hRequest=WinHttpOpenRequest(hConnect, L"GET", szVirPath, NULL, WINHTTP_NO_REFERER , WINHTTP_DEFAULT_ACCEPT_TYPES, 0);
	if(NULL==hRequest) goto Label_Exit;

	rc=WinHttpSendRequest(hRequest, WINHTTP_NO_ADDITIONAL_HEADERS, 0, WINHTTP_NO_REQUEST_DATA, 0, 0, 0);
	if(!rc) goto Label_Exit;

	rc=WinHttpReceiveResponse(hRequest, 0);
	if(!rc) goto Label_Exit;

	HANDLE hFile=INVALID_HANDLE_VALUE;
	
		
	int fUnicode=-1;
	UINT uCodePage=CP_ACP;

	DWORD dwBufferSize=16384;
	buffer=(LPSTR)LocalAlloc(LPTR, dwBufferSize);
	WinHttpQueryHeaders(hRequest, WINHTTP_QUERY_CONTENT_TYPE, WINHTTP_HEADER_NAME_BY_INDEX, 
		buffer, &dwBufferSize, WINHTTP_NO_HEADER_INDEX);

	SetWindowText(m_hEdit, (LPCWSTR)buffer);

	_tcsupr((wchar_t *)buffer);
	pCursor=(TCHAR *)_tcsstr((wchar_t *)buffer, TEXT("CHARSET="));
	if(NULL!=pCursor) 
	{
		pCursor+=8;
		if(lstrcmp(pCursor, TEXT("UTF-8"))==0) uCodePage=CP_UTF8;
	}

	LocalFree(buffer);
//	TCHAR szFileName[MAX_PATH]=TEXT("..\\files\\");

//	wsprintf(szFileName, TEXT("..\\files\\%s_%s.html"), szDomain, szVirPath);
	
//	hFile=CreateFile(szFileName, GENERIC_READ|GENERIC_WRITE, FILE_SHARE_READ, NULL,
//		CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL);
//	if(INVALID_HANDLE_VALUE==hFile) goto Label_Exit;
//	WriteFile(hFile, buffer, dwBufferSize, &dwBufferSize, NULL);


	do
	{
		dwSize=0;
		dwRead=0;
		rc=WinHttpQueryDataAvailable(hRequest, &dwSize);
		if(rc)
		{
			buffer=(LPSTR)LocalAlloc(LPTR, sizeof(CHAR)*(dwSize+1));
			
			rc=WinHttpReadData(hRequest, (LPVOID)buffer, dwSize, &dwRead);
			
			if(rc)
			{				
				
				{
					wszText=(LPWSTR)LocalAlloc(LPTR, sizeof(WCHAR)*(dwSize+100));
					MultiByteToWideChar(uCodePage, 0, buffer, dwRead, wszText, dwSize+100);
					SendMessage(m_hEdit, EM_REPLACESEL, -1, (LPARAM)wszText);
					LocalFree(wszText);
				}
				
			//	SendMessage(m_hEdit, EM_SETTEXTEX, (WPARAM)&ste, (LPARAM)buffer);
				if(INVALID_HANDLE_VALUE!=hFile)
					WriteFile(hFile, buffer, dwRead, &dwRead, NULL);
			//	SetDlgItemTextA(m_hWnd, 1000, buffer);
			}
			LocalFree(buffer);
		}
		dwTotalRead+=dwRead;
	}while(dwSize>0);
	
	CloseHandle(hFile);
Label_Exit:
	if(NULL!=hRequest)
	{
		WinHttpCloseHandle(hRequest);
	}
	if(NULL!=hConnect)
	{
		
		WinHttpCloseHandle(hConnect);
	}
	if(NULL!=hSession) 
	{		
		WinHttpCloseHandle(hSession);
	}

	return rc;
}

[huyidao21]

看不怎么懂楼上的代码。偶都用C#。还是结贴吧，谢谢楼上的。