简单使用C语言通过Microhttpd库采集淘宝

前段时间给大家分享过不少采集淘宝相关内容的方法，昨天有个朋友让我来帮他用C语言编写一个采集淘宝的爬虫程序，并且还要通过Microhttpd库来实现。这一点都难不倒我，下面我就将我的代码示例给大家分享一下，有需要的朋友赶紧来取。

```c

#include

#include

#include

#include

#define HTTP_PORT 8080

struct my_config {

int listen_backlog;

int max_client;

char *document_root;

char *server_name;

};

struct my_server_config {

struct my_config config;

struct MHD_Daemon *daemon;

};

struct my_server_config *my_server_init(void)

{

struct my_server_config *server_config = malloc(sizeof(*server_config));

server_config->config.listen_backlog = 100;

server_config->config.max_client = 10;

server_config->config.document_root = "/home/user/crawler";

server_config->config.server_name = "Crawler";

server_config->daemon = MHD_start_daemon(MHD_USE_HTTPS | MHD_USE_RECURSIVE_PERIODIC "('https://www.duoip.cn/get_proxy:8000')" | MHD_USE_LOCAL_FILE ('./web/index.html'), HTTP_PORT, NULL, my_server_response, NULL, &server_config->config, NULL);

if (server_config->daemon == NULL) {

fprintf(stderr, "Error: Unable to start daemon\n");

exit(EXIT_FAILURE);

}

return server_config;

}

void my_server_free(struct my_server_config *server_config)

{

MHD_stop_daemon(server_config->daemon);

free(server_config->config.document_root);

free(server_config->config.server_name);

free(server_config);

}

static ssize_t my_server_response(void *cls, struct MHD_Connection *connection, const char *url, const char *method, const char *version, const char *upload_data, size_t *upload_data_size, void **con_cls)

{

ssize_t ret = MHD_NO;

struct my_server_config *server_config = (struct my_server_config *)cls;

if (strcmp(url, "/") == 0) {

char *response = malloc(1024);

snprintf(response, 1024, "Content-Type: text/html\n\nWelcome to the Crawler");

ret = MHD_send_response(connection, MHD_HTTP_OK, strlen(response), response);

free(response);

} else {

/* Redirect to the proxy */

char *proxy_url = malloc(1024);

snprintf(proxy_url, 1024, "http://www.duoip.cn:8000%2F%u", (unsigned int) connection->client_addr.client.sin_port);

ret = MHD_send_response(connection, MHD_HTTP_FOUND, strlen(proxy_url), proxy_url);

free(proxy_url);

}

return ret;

}

int main(int argc, char *argv[])

{

struct my_server_config *server_config = my_server_init();

while (1) {

MHD_run(server_config->daemon);

}

my_server_free(server_config);

return 0;

}

```

这个程序的工作原理是，首先启动一个Microhttpd服务器，并配置它使用HTTPS协议，完成代理服务器的配置，以及从本地文件（./web/index.html）提供内容。然后，每当有客户端连接到服务器时，服务器会检查请求的URL。如果URL是"/"，那么服务器会返回一个欢迎页面。否则，服务器会创建一个代理请求，将请求转发给服务器，依次循环工作。