将 cURL 内容结果保存到 C++ 中的字符串中

Question

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

  curl = curl_easy_init();
  if(curl) {
    curl_easy_setopt(curl, CURLOPT_URL, "http://www.google.com");
    curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L);
    curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L);
    res = curl_easy_perform(curl);
    curl_easy_cleanup(curl);
  }
  _getch();
  return 0;
}

string contents = "";

我想将 curl html 内容的结果保存在一个字符串中，我该怎么做？ 这是一个愚蠢的问题，但不幸的是，我在 C++ 的 cURL 示例中找不到任何地方 谢谢！

Answer 1

我将 Joachim Isaksson 的答案与 CURLOPT_WRITEFUNCTION 的现代 C++ 改编一起使用。

编译器不会对 C 风格的转换进行唠叨。

static auto WriteCallback(char* ptr, size_t size, size_t nmemb, void* userdata) -> size_t {
  static_cast<string*>(userdata)->append(ptr, size * nmemb);
  return size * nmemb;
}

Answer 2

使用“新的”C++11 lambda 功能，只需几行代码即可完成。

#ifndef WIN32 #define __stdcall "" #endif //For compatibility with both Linux and Windows
std::string resultBody { };
curl_easy_setopt(curl, CURLOPT_WRITEDATA, &resultBody);
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, static_cast<size_t (__stdcall *)(char*, size_t, size_t, void*)>(
    [](char* ptr, size_t size, size_t nmemb, void* resultBody){
        *(static_cast<std::string*>(resultBody)) += std::string {ptr, size * nmemb};
        return size * nmemb;
    }
));

CURLcode curlResult = curl_easy_perform(curl);
std::cout << "RESULT BODY:\n" << resultBody << std::endl;
// Cleanup etc

注意 __stdcall 强制转换需要遵守 C 调用约定（cURL 是一个 C 库）

Answer 3

在我的博客上，我有 published 一个简单的包装类来执行此任务。

使用示例：

#include "HTTPDownloader.hpp"

int main(int argc, char** argv) {
    HTTPDownloader downloader;
    std::string content = downloader.download("https://stackoverflow.com");
    std::cout << content << std::endl;
}

这是头文件：

/**
 * HTTPDownloader.hpp
 *
 * A simple C++ wrapper for the libcurl easy API.
 *
 * Written by Uli Köhler (techoverflow.net)
 * Published under CC0 1.0 Universal (public domain)
 */
#ifndef HTTPDOWNLOADER_HPP
#define HTTPDOWNLOADER_HPP

#include <string>

/**
 * A non-threadsafe simple libcURL-easy based HTTP downloader
 */
class HTTPDownloader {
public:
    HTTPDownloader();
    ~HTTPDownloader();
    /**
     * Download a file using HTTP GET and store in in a std::string
     * @param url The URL to download
     * @return The download result
     */
    std::string download(const std::string& url);
private:
    void* curl;
};

#endif  /* HTTPDOWNLOADER_HPP */

这里是源代码：

/**
 * HTTPDownloader.cpp
 *
 * A simple C++ wrapper for the libcurl easy API.
 *
 * Written by Uli Köhler (techoverflow.net)
 * Published under CC0 1.0 Universal (public domain)
 */
#include "HTTPDownloader.hpp"
#include <curl/curl.h>
#include <curl/easy.h>
#include <curl/curlbuild.h>
#include <sstream>
#include <iostream>
using namespace std;

size_t write_data(void *ptr, size_t size, size_t nmemb, void *stream) {
    string data((const char*) ptr, (size_t) size * nmemb);
    *((stringstream*) stream) << data;
    return size * nmemb;
}

HTTPDownloader::HTTPDownloader() {
    curl = curl_easy_init();
}

HTTPDownloader::~HTTPDownloader() {
    curl_easy_cleanup(curl);
}

string HTTPDownloader::download(const std::string& url) {
    curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
    /* example.com is redirected, so we tell libcurl to follow redirection */
    curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
    curl_easy_setopt(curl, CURLOPT_NOSIGNAL, 1); //Prevent "longjmp causes uninitialized stack frame" bug
    curl_easy_setopt(curl, CURLOPT_ACCEPT_ENCODING, "deflate");
    std::stringstream out;
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_data);
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, &out);
    /* Perform the request, res will get the return code */
    CURLcode res = curl_easy_perform(curl);
    /* Check for errors */
    if (res != CURLE_OK) {
        fprintf(stderr, "curl_easy_perform() failed: %s\n",
                curl_easy_strerror(res));
    }
    return out.str();
}

Answer 4

提出了有用但简单的解决方案，它重载了 std::ostream::operator

#include <ostream>

#include <curl/curl.h>

size_t curlCbToStream (
    char * buffer,
    size_t nitems,
    size_t size,
    std::ostream * sout
)
{
    *sout << buffer;

    return nitems * size;
}

std::ostream & operator<< (
    std::ostream & sout,
    CURL * request
)
{
    ::curl_easy_setopt(request, CURLOPT_WRITEDATA, & sout);
    ::curl_easy_setopt(request, CURLOPT_WRITEFUNCTION, curlCbToStream);
    ::curl_easy_perform(request);

    return sout;
}

采取的方法的可能缺点是：

typedef void CURL;

这意味着它涵盖了所有已知的指针类型。

Answer 5

基于@JoachimIsaksson 的回答，这里有一个更详细的输出，它处理内存不足并且对 curl 的最大输出有限制（因为 CURLOPT_MAXFILESIZE 限制仅基于标头信息，而不是基于传输的实际大小)。

#DEFINE MAX_FILE_SIZE = 10485760 //10 MiB

size_t curl_to_string(void *ptr, size_t size, size_t count, void *stream)
{
    if(((string*)stream)->size() + (size * count) > MAX_FILE_SIZE)
    {
        cerr<<endl<<"Could not allocate curl to string, output size (current_size:"<<((string*)stream)->size()<<"bytes + buffer:"<<(size * count) << "bytes) would exceed the MAX_FILE_SIZE ("<<MAX_FILE_SIZE<<"bytes)";
        return 0;
    }
    int retry=0;
    while(true)
    {
        try{
            ((string*)stream)->append((char*)ptr, 0, size*count);
            break;// successful
        }catch (const std::bad_alloc&) {
            retry++;
            if(retry>100)
            {
                cerr<<endl<<"Could not allocate curl to string, probably not enough memory, aborting after : "<<retry<<" tries at 10s apart";
                return 0;
            }
            cerr<<endl<<"Could not allocate curl to string, probably not enough memory, sleeping 10s, try:"<<retry;
            sleep(10);
        }
    }
  return size*count;
}

Answer 6

您必须使用CURLOPT_WRITEFUNCTION 设置回调以进行写入。我现在无法测试编译它，但函数看起来应该很接近；

static std::string readBuffer;

static size_t WriteCallback(void *contents, size_t size, size_t nmemb, void *userp)
{ 
    size_t realsize = size * nmemb;
    readBuffer.append(contents, realsize);
    return realsize;
}

然后通过doing调用它；

readBuffer.clear();
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteCallback);
// ...other curl options
res = curl_easy_perform(curl);

通话结束后，readBuffer应该有你的内容了。

编辑：您可以使用CURLOPT_WRITEDATA 传递缓冲区字符串，而不是使其成为静态。在这种情况下，为了简单起见，我只是将其设为静态。一个不错的页面（除了上面的链接示例）是here，用于解释选项。

Edit2：根据要求，这是一个没有静态字符串缓冲区的完整工作示例；

#include <iostream>
#include <string>
#include <curl/curl.h>


static size_t WriteCallback(void *contents, size_t size, size_t nmemb, void *userp)
{
    ((std::string*)userp)->append((char*)contents, size * nmemb);
    return size * nmemb;
}

int main(void)
{
  CURL *curl;
  CURLcode res;
  std::string readBuffer;

  curl = curl_easy_init();
  if(curl) {
    curl_easy_setopt(curl, CURLOPT_URL, "http://www.google.com");
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteCallback);
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, &readBuffer);
    res = curl_easy_perform(curl);
    curl_easy_cleanup(curl);

    std::cout << readBuffer << std::endl;
  }
  return 0;
}

Answer 7

这可能不会马上起作用，但应该会给你一个想法：

#include <string>
#include <curl.h>
#include <stdio.h>
size_t write_data(void *ptr, size_t size, size_t nmemb, FILE *stream) {
    size_t written;
    written = fwrite(ptr, size, nmemb, stream);
    return written;
}

int main() {
    std::string tempname = "temp";
    CURL *curl;
    CURLcode res;
    curl = curl_easy_init();
    if(curl) {
      FILE *fp = fopen(tempname.c_str(),"wb");
      curl_easy_setopt(curl, CURLOPT_URL, "http://www.google.com");
      curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_data); 
      curl_easy_setopt(curl, CURLOPT_WRITEDATA, fp);
      res = curl_easy_perform(curl);
      curl_easy_cleanup(curl);
      fclose(fp);
      fp = fopen(tempname.c_str(),"rb");
      fseek (fp , 0 , SEEK_END);
      long lSize = ftell (fp);
      rewind(fp);
      char *buffer = new char[lSize+1];
      fread (buffer, 1, lSize, fp);
      buffer[lSize] = 0;
      fclose(fp);
      std::string content(buffer);
      delete [] buffer;
    }
}