关于使用curl下载网页源码中文乱码问题!

最新推荐文章于 2024-08-06 10:59:58 发布

吾王Excalibur

最新推荐文章于 2024-08-06 10:59:58 发布

阅读量1.3k

点赞数

分类专栏： C++ libcurl 文章标签： curl

C++ 同时被 2 个专栏收录

43 篇文章 3 订阅

订阅专栏

libcurl

3 篇文章 0 订阅

订阅专栏

关于使用libcurl下载网页源码中文乱码问题!

参考了这位兄弟的：http://blog.csdn.net/malihong1/article/details/50480420，可能他没继续找到方法。

借用了http://www.cnblogs.com/iRoad/p/4105172.html的函数

直接改官网的demo https://curl.haxx.se/libcurl/c/example.html，https.c 代码如下：

[cpp] view plain copy

print ?

/***************************************************************************
* _ _ ____ _
* Project ___| | | | _ \| |
* / __| | | | |_) | |
* | (__| |_| | _ <| |___
* \___|\___/|_| \_\_____|
*
* Copyright (C) 1998 - 2015, Daniel Stenberg, <daniel@haxx.se>, et al.
*
* This software is licensed as described in the file COPYING, which
* you should have received as part of this distribution. The terms
* are also available at https://curl.haxx.se/docs/copyright.html.
*
* You may opt to use, copy, modify, merge, publish, distribute and/or sell
* copies of the Software, and permit persons to whom the Software is
* furnished to do so, under the terms of the COPYING file.
*
* This software is distributed on an “AS IS” basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
***************************************************************************/
/* <DESC>
* Simple HTTPS GET
* </DESC>
*/
// C 运行时头文件
#include <atlstr.h>
#include <WinINet.h>
#include <string>
#include <stdio.h>
#include <curl/curl.h>
using namespace std;
string UTF8ToGBK(const std::string& strUTF8)
{
int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);
WCHAR* wszGBK = new WCHAR[len+1];
memset(wszGBK, 0, len * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)(LPCTSTR)strUTF8.c_str(), -1, wszGBK, len);
len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);
char *szGBK = new char[len + 1];
memset(szGBK, 0, len + 1);
WideCharToMultiByte(CP_ACP,0, wszGBK, -1, szGBK, len, NULL, NULL);
std::string strTemp(szGBK);
delete[]szGBK;
delete[]wszGBK;
return strTemp;
}
/**
@brief char*数据接收回调函数，仅适用stream实际类型是std::string
*/
static size_t DataReceiveCallback(void *ptr, size_t size, size_t nmemb, void *stream) {
size_t len = size * nmemb;
std::string* buffer = reinterpret_cast<std::string*>(stream);
if (buffer)
buffer->append((char*)ptr, len);
return len;
}
int main(void)
{
CURL *curl;
CURLcode res;
std::string data;
curl_global_init(CURL_GLOBAL_DEFAULT);
curl = curl_easy_init();
if(curl) {
curl_easy_setopt(curl, CURLOPT_URL, ”https://v.qq.com/x/cover/jwplwx9ootoigud.html”);
#ifdef SKIP_PEER_VERIFICATION
/*
* If you want to connect to a site who isn’t using a certificate that is
* signed by one of the certs in the CA bundle you have, you can skip the
* verification of the server’s certificate. This makes the connection
* A LOT LESS SECURE.
*
* If you have a CA cert for the server stored someplace else than in the
* default bundle, then the CURLOPT_CAPATH option might come handy for
* you.
*/
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L);
#endif
#ifdef SKIP_HOSTNAME_VERIFICATION
/*
* If the site you’re connecting to uses a different host name that what
* they have mentioned in their server certificate’s commonName (or
* subjectAltName) fields, libcurl will refuse to connect. You can skip
* this check, but this will make the connection less secure.
*/
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L);
#endif
// 响应数据回调
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, DataReceiveCallback);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, &data);
/* Perform the request, res will get the return code */
res = curl_easy_perform(curl);
/* Check for errors */
if(res != CURLE_OK)
fprintf(stderr, ”curl_easy_perform() failed: %s\n”,
curl_easy_strerror(res));
string strGBK = UTF8ToGBK(data);
/* always cleanup */
curl_easy_cleanup(curl);
}
curl_global_cleanup();
return 0;
}

/***************************************************************************
 *                                  _   _ ____  _
 *  Project                     ___| | | |  _ \| |
 *                             / __| | | | |_) | |
 *                            | (__| |_| |  _ <| |___
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) 1998 - 2015, Daniel Stenberg, <daniel@haxx.se>, et al.
 *
 * This software is licensed as described in the file COPYING, which
 * you should have received as part of this distribution. The terms
 * are also available at https://curl.haxx.se/docs/copyright.html.
 *
 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
 * copies of the Software, and permit persons to whom the Software is
 * furnished to do so, under the terms of the COPYING file.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 ***************************************************************************/
/* <DESC>
 * Simple HTTPS GET
 * </DESC>
 */
// C 运行时头文件

include <atlstr.h>

include <WinINet.h>

include <string>

include <stdio.h>

include <curl/curl.h>

using namespace std;

string UTF8ToGBK(const std::string& strUTF8)
{
int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);
WCHAR* wszGBK = new WCHAR[len+1];
memset(wszGBK, 0, len * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)(LPCTSTR)strUTF8.c_str(), -1, wszGBK, len);

len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);  
char *szGBK = new char[len + 1];  
memset(szGBK, 0, len + 1);  
WideCharToMultiByte(CP_ACP,0, wszGBK, -1, szGBK, len, NULL, NULL);   
std::string strTemp(szGBK);  
delete[]szGBK;  
delete[]wszGBK;  
return strTemp;

}

/**
@brief char*数据接收回调函数，仅适用stream实际类型是std::string
*/
static size_t DataReceiveCallback(void *ptr, size_t size, size_t nmemb, void *stream) {
size_t len = size * nmemb;

std::string* buffer = reinterpret_cast&lt;std::string*&gt;(stream);
if (buffer)
    buffer-&gt;append((char*)ptr, len);

return len;

}

int main(void)
{
CURL *curl;
CURLcode res;

std::string data;
curl_global_init(CURL_GLOBAL_DEFAULT);

curl = curl_easy_init();
if(curl) {
curl_easy_setopt(curl, CURLOPT_URL, “https://v.qq.com/x/cover/jwplwx9ootoigud.html“);

ifdef SKIP_PEER_VERIFICATION

/*
 * If you want to connect to a site who isn't using a certificate that is
 * signed by one of the certs in the CA bundle you have, you can skip the
 * verification of the server's certificate. This makes the connection
 * A LOT LESS SECURE.
 *
 * If you have a CA cert for the server stored someplace else than in the
 * default bundle, then the CURLOPT_CAPATH option might come handy for
 * you.
 */
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L);

endif

ifdef SKIP_HOSTNAME_VERIFICATION

/*
 * If the site you're connecting to uses a different host name that what
 * they have mentioned in their server certificate's commonName (or
 * subjectAltName) fields, libcurl will refuse to connect. You can skip
 * this check, but this will make the connection less secure.
 */
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L);

endif

// 响应数据回调
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, DataReceiveCallback);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, &amp;data);


/* Perform the request, res will get the return code */
res = curl_easy_perform(curl);
/* Check for errors */
if(res != CURLE_OK)
  fprintf(stderr, "curl_easy_perform() failed: %s\n",
          curl_easy_strerror(res));

string strGBK = UTF8ToGBK(data);
/* always cleanup */
curl_easy_cleanup(curl);

}

curl_global_cleanup();

return 0;
}