Question

我正在尝试通过制作一个简单的Web抓取器来学习C套接字，但我自己正在使用套接字库来执行套接字编程和HTTP请求。我编写了一个成功向http://mirror.vcu.edu发送非SSL请求的函数，并将输出存储在名为response的变量中。

char *noSSLRequest(REQUEST_HEADER_INFO *request_header_info) {
    struct sockaddr_in serverAddress;
    char *requestHeader;
    unsigned short serverPort;
    char serverIP[13];
    domainToIP(request_header_info->host, serverIP);
    char *response = calloc(0, 0);
    ssize_t bytesReceived = 0;


    int sockFD; //Only supporting IPV4 right now, returns file descriptor for socket

    if ((sockFD = socket(PF_INET, SOCK_STREAM, IPPROTO_TCP)) < -1) {
        freeRequestHeaderInfo(request_header_info);
        fprintf(stderr, "Error, could not open socket in http.c getHTMLBody(). Reason for error %s", strerror(errno));
        exit(-1);
    }
    printf(ANSI_COLOR_GREEN "LOG: Socket file descriptor is %d" ANSI_COLOR_RESET, sockFD);
    serverPort = 80;
    memset(&serverAddress, 0, sizeof(serverAddress));
    serverAddress.sin_family = AF_INET;
    serverAddress.sin_port = htons(80);
    inet_aton(serverIP, &serverAddress.sin_addr);

    if (connect(sockFD, (const struct sockaddr *) &serverAddress, sizeof(serverAddress)) < 0) {
        freeRequestHeaderInfo(request_header_info);
        fprintf(stderr, "Error, could not connect socket in http.c getHTMLBody(). Reason for error %s",
                strerror(errno));
        exit(-1);
    }

    printf(ANSI_COLOR_GREEN "\nLOG: Connected socket at descriptor %d to IP %s and port %d" ANSI_COLOR_RESET, sockFD,
           serverIP, serverPort);

    requestHeader = craftRequestHeader(request_header_info);

    if (send(sockFD, requestHeader, strlen(requestHeader), 0) < 0) {
        freeRequestHeaderInfo(request_header_info);
        fprintf(stderr, "Error, could not send request. Reason for error %s",
                strerror(errno));
        exit(-1);
    }

    printf(ANSI_COLOR_GREEN "\nLOG: Sent HTTP request from socket at descriptor %d to IP %s and port %d." ANSI_COLOR_RESET,
           sockFD,
           serverIP, serverPort);


    free(requestHeader);
    printf(ANSI_COLOR_GREEN "\nLOG: Starting receive operation" ANSI_COLOR_RESET);
    ssize_t bytesReceivedPrevious = -1;
    char buffer[RESPONSE_BUFFER_SIZE];


    while (bytesReceived < (RESPONSE_MAX_LEN * sizeof(char)) && bytesReceived > bytesReceivedPrevious) {
        bytesReceivedPrevious = bytesReceived;
        bytesReceived = recv(sockFD, buffer, RESPONSE_BUFFER_SIZE, 0);
        response = realloc(response, sizeof(*response) + RESPONSE_BUFFER_SIZE);
        strcat(response, buffer); //Append to the end, safe because recv takes care of limiting buffer size
    }
    response = realloc(response, sizeof(*response) + sizeof(char));
    response[strlen(response)] = '\0';
    printf(ANSI_COLOR_GREEN "\nLOG: Received HTTP response from socket at descriptor %d to IP %s and port %d.\n\n\n\n\n" ANSI_COLOR_RESET,
           sockFD,
           serverIP, serverPort);
    if (close(sockFD) < 0) {
        freeRequestHeaderInfo(request_header_info);
        fprintf(stderr, "Error, could not close socket in http.c getHTMLBody(). Reason for error %s", strerror(errno));
        exit(-1);
    }
    printf(ANSI_COLOR_GREEN "\nLOG: Closed socket at descriptor %d" ANSI_COLOR_RESET, sockFD);
    freeRequestHeaderInfo(request_header_info);

    return response;
}

一切正常，响应有一个空终止符，生活很好，除了在我的控制台中，由于某种原因，我打印出response的输出。我觉得某些东西正在泄漏，因为这个输出也是绿色的，即使在每个日志之后我将颜色重置为默认值。我知道有些标志和其他内容没有显示，我无法获取所有信息和代码，所以我有一个github repo和更详细的issue。

日志的图片在这里和问题上，虽然我无法获得完整的输出，因此非彩色文本版本就出现了问题。

Answer 1

此代码

response = realloc(response, sizeof(response) + RESPONSE_BUFFER_SIZE);

和此代码

response = realloc(response, sizeof(response) + sizeof(char));

都会导致未定义的行为。

response是char * - 指针。 sizeof()指针是指针的大小，而不是指向它的字符串的长度。

另请注意，根据定义，sizeof(char)是一个。

当没有明确命令时，C套接字HTTP请求异步打印响应

1 个答案: