Simple example of libcurl accessing url saved as file

备注：本文是libcurl easy interfaceThe download file simple example,非prod-ready的代码, 没有提供keep-Alive、超时设置等. 只是一个简单示例.

libcurl是网络工具curl的底层核心.It is very reliable and stable network dependent libraries. 分为easy和multiTwo series of interface. 其中easy是同步调用,相对简单, multi是异步调用, 比较复杂. 本文是easy接口调用示例.
官网链接： https://curl.se/libcurl/
In the website has a lot of sample,Can choose according to need reference code islibcurl的api说明：https://curl.se/libcurl/c/libcurl-tutorial.html

代码

// Copyright (c) 2022 by yqbjtu
//
// sudo apt-get remove libcurl4
// 确保机器已经安装了libcurl库
// sudo apt-get install libcurl4-openssl-dev
// Build command line, Because this article is very simple,A sample file,一条命令搞定
// g++ curl_file.cpp -std=c++11 -lcurl -o libcurdemo.out;
// 执行./libcurdemo.out

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

//判断url是否存在
int checkUrlIsExist(const char * URL) {
    

    CURL * curl_fd = curl_easy_init();
    CURLcode code;
    CURLINFO response_code = CURLINFO_NONE;
    curl_easy_setopt(curl_fd, CURLOPT_NOBODY, 1);
    curl_easy_setopt(curl_fd, CURLOPT_TIMEOUT, 3);
    curl_easy_setopt(curl_fd, CURLOPT_URL, URL);
    code = curl_easy_perform(curl_fd);

    if (code == CURLE_OK) {
    
        curl_easy_getinfo(curl_fd, CURLINFO_RESPONSE_CODE, &response_code);
    }

    curl_easy_cleanup(curl_fd);

    return response_code;
}


size_t write_data(void *ptr, size_t size, size_t nmemb, FILE *stream) {
    
    size_t written = fwrite(ptr, size, nmemb, stream);
    // prints as unsigned decimal
    printf("file writen byte:%zu\n", written);
    return written;
}

int main()
{
    
    CURLcode res;
    /* 调用curl_global_init()初始化libcurl */
    res = curl_global_init(CURL_GLOBAL_ALL);
    if (CURLE_OK != res)
    {
    
        std::cout <<"init libcurl failed."<< std::endl;
        curl_global_cleanup();
        return -1;
    }

    std::cout << "curl version:" << curl_version() << std::endl;
    std::cout << "libcurl download file demo" << std::endl;

    std::string url = "https://www.baidu.com";
    const char *cUrl = url.c_str();
    int statusCode = checkUrlIsExist(cUrl);
    if (statusCode == 404) {
    
        std::cout << "page not found, http status 404"<< std::endl;
        return -1;
    } else {
    
        std::cout << "statusCode:" << statusCode<< std::endl;
    }

    CURL *curl;
    FILE *fp;
    CURLcode resultCode;

    char outFileName[FILENAME_MAX] = "./index.html";
    curl = curl_easy_init();
    if (curl) {
    
        fp = fopen(outFileName,"wb");
        if (fp == NULL) {
    
            std::cout << "fail to open file " << outFileName << std::endl;
            curl_easy_cleanup(curl);
            return -1;
        }
        // Set the header fields、Add request body all throughcurl_easy_setopt完成
        curl_easy_setopt(curl, CURLOPT_URL, cUrl);
        // 如果没有通过CURLOPT_WRITEFUNCTION属性给easy handle设置回调函数,libcurl会提供一个默认的回调函数,它只是简单的将接收到的数据打印到标准输出.
        // 可以通过CURLOPT_WRITEDATA属性给默认回调函数传递一个已经打开的文件指针,用于将数据输出到文件里.
        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_data);
        curl_easy_setopt(curl, CURLOPT_WRITEDATA, fp);
        /* Switch on full protocol/debug output , Need to look at some intermediate information can open*/
        curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L);

        resultCode = curl_easy_perform(curl);
        std::cout <<"curl resultCode:" << resultCode << std::endl;
        if (resultCode != CURLE_OK)
        {
    
            std::cout << "fail to access url " << url << std::endl;
            return -1;
        }
        /* always cleanup */
        curl_easy_cleanup(curl);
        fclose(fp);
    }

    std::cout << "write data to file " << outFileName << " done" << std::endl;
    // 对应开始的curl_global_init
    curl_global_cleanup();
    return 0;
}

效果

xxx-MacBook-Pro ch5 % g++ curl_file.cpp -std=c++11 -lcurl -o libcurdemo.out;./libcurdemo.out
curl version:libcurl/7.77.0 (SecureTransport) LibreSSL/2.8.3 zlib/1.2.11 nghttp2/1.42.0
libcurl download file demo
statusCode:200
*   Trying 110.242.68.3:443...
* Connected to www.baidu.com (110.242.68.3) port 443 (#0)
* ALPN, offering h2
* ALPN, offering http/1.1
* successfully set certificate verify locations:
*  CAfile: /etc/ssl/cert.pem
*  CApath: none
* SSL connection using TLSv1.2 / ECDHE-RSA-AES128-GCM-SHA256
* ALPN, server accepted to use http/1.1
* Server certificate:
*  subject: C=CN; ST=beijing; L=beijing; OU=service operation department; O=Beijing Baidu Netcom Science Technology Co., Ltd; CN=baidu.com
*  start date: Jul  5 05:16:02 2022 GMT
*  expire date: Aug  6 05:16:01 2023 GMT
*  subjectAltName: host "www.baidu.com" matched cert's "*.baidu.com"
*  issuer: C=BE; O=GlobalSign nv-sa; CN=GlobalSign RSA OV SSL CA 2018
*  SSL certificate verify ok.
> GET / HTTP/1.1
Host: www.baidu.com
Accept: */*

* Mark bundle as not supporting multiuse
< HTTP/1.1 200 OK
< Accept-Ranges: bytes
< Cache-Control: no-cache
< Connection: keep-alive
< Content-Length: 9508
< Content-Type: text/html
< Date: Sat, 30 Jul 2022 03:34:06 GMT
< P3p: CP=" OTI DSP COR IVA OUR IND COM "
< P3p: CP=" OTI DSP COR IVA OUR IND COM "
< Pragma: no-cache
< Server: BWS/1.1
< Set-Cookie: BAIDUID=BAF6D7E5ACD702EEA47AB9528ACECA23:FG=1; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
< Set-Cookie: BIDUPSID=BAF6D7E5ACD702EEA47AB9528ACECA23; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
< Set-Cookie: PSTM=1659152046; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
< Set-Cookie: BAIDUID=BAF6D7E5ACD702EED7F6FFB8A23F97DF:FG=1; max-age=31536000; expires=Sun, 30-Jul-23 03:34:06 GMT; domain=.baidu.com; path=/; version=1; comment=bd
< Traceid: 165915204602586155627623073953155317249
< Vary: Accept-Encoding
< X-Frame-Options: sameorigin
< X-Ua-Compatible: IE=Edge,chrome=1
< 
file writen byte:192
file writen byte:2358
file writen byte:559
file writen byte:4716
file writen byte:1683
* Connection #0 to host www.baidu.com left intact
curl resultCode:0
write data to file ./index.html done