C语言编写的简单网页抓取程序

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>

int main(int argc, char *argv[]) {
    CURL *curl;
    CURLcode res;
    FILE *fp;
    char *url = argv[1];
    char filename[256];

    // 检查参数是否正确
    if (argc != 2) {
        printf("Usage: %s url\n", argv[0]);
        return 1;
    }

    // 初始化curl
    curl = curl_easy_init();
    if (!curl) {
        printf("Error: Failed to initialize curl\n");
        return 1;
    }

    // 设置要访问的URL
    curl_easy_setopt(curl, CURLOPT_URL, url);

    // 设置要存储的文件名
    strcpy(filename, "result.html");
    fp = fopen(filename, "wb");
    if (!fp) {
        printf("Error: Failed to open file for writing\n");
        return 1;
    }

    // 设置文件写入回调函数
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, fwrite);
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, fp);

    // 执行curl操作
    res = curl_easy_perform(curl);
    if (res != CURLE_OK) {
        printf("Error: Failed to retrieve web page\n");
        return 1;
    }

    // 清理curl和文件句柄
    curl_easy_cleanup(curl);
    fclose(fp);

    printf("Web page saved to %s\n", filename);
    return 0;
}

Linux要先：
sudo apt-get install libcurl4-openssl-dev

编译方式：
gcc -o myprogram myprogram.c -I/usr/include/curl -lcurl

MACOS的方式：
gcc -o myprogram myprogram.c -lcurl