Best ways of parsing a URL using C?

Question

I have a URL like this:

http://192.168.0.1:8080/servlet/rece

I want to parse the URL to get the values:

IP: 192.168.0.1
Por         


        

Answer 1

I wrote this

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
typedef struct
{
    const char* protocol = 0;
    const char* site = 0;
    const char* port = 0;
    const char* path = 0;
} URL_INFO;
URL_INFO* split_url(URL_INFO* info, const char* url)
{
    if (!info || !url)
        return NULL;
    info->protocol = strtok(strcpy((char*)malloc(strlen(url)+1), url), "://");
    info->site = strstr(url, "://");
    if (info->site)
    {
        info->site += 3;
        char* site_port_path = strcpy((char*)calloc(1, strlen(info->site) + 1), info->site);
        info->site = strtok(site_port_path, ":");
        info->site = strtok(site_port_path, "/");
    }
    else
    {
        char* site_port_path = strcpy((char*)calloc(1, strlen(url) + 1), url);
        info->site = strtok(site_port_path, ":");
        info->site = strtok(site_port_path, "/");
    }
    char* URL = strcpy((char*)malloc(strlen(url) + 1), url);
    info->port = strstr(URL + 6, ":");
    char* port_path = 0;
    char* port_path_copy = 0;
    if (info->port && isdigit(*(port_path = (char*)info->port + 1)))
    {
        port_path_copy = strcpy((char*)malloc(strlen(port_path) + 1), port_path);
        char * r = strtok(port_path, "/");
        if (r)
            info->port = r;
        else
            info->port = port_path;
    }
    else
        info->port = "80";
    if (port_path_copy)
        info->path = port_path_copy + strlen(info->port ? info->port : "");
    else 
    {
        char* path = strstr(URL + 8, "/");
        info->path = path ? path : "/";
    }
    int r = strcmp(info->protocol, info->site) == 0;
    if (r && info->port == "80")
        info->protocol = "http";
    else if (r)
        info->protocol = "tcp";
    return info;
}

Test

int main()
{
    URL_INFO info;
    split_url(&info, "ftp://192.168.0.1:8080/servlet/rece");
    printf("Protocol: %s\nSite: %s\nPort: %s\nPath: %s\n", info.protocol, info.site, info.port, info.path);
    return 0;
}

Out

Protocol: ftp
Site: 192.168.0.1
Port: 8080
Path: /servlet/rece

Answer 2

Write a custom parser or use one of the string replace functions to replace the separator ':' and then use sscanf().

Answer 3

I wrote a simple code using sscanf, which can parse very basic URLs.

#include <stdio.h>

int main(void)
{
    const char text[] = "http://192.168.0.2:8888/servlet/rece";
    char ip[100];
    int port = 80;
    char page[100];
    sscanf(text, "http://%99[^:]:%99d/%99[^\n]", ip, &port, page);
    printf("ip = \"%s\"\n", ip);
    printf("port = \"%d\"\n", port);
    printf("page = \"%s\"\n", page);
    return 0;
}

./urlparse
ip = "192.168.0.2"
port = "8888"
page = "servlet/rece"

Answer 4

Pure sscanf() based solution:

//Code
#include <stdio.h>

int
main (int argc, char *argv[])
{
    char *uri = "http://192.168.0.1:8080/servlet/rece"; 
    char ip_addr[12], path[100];
    int port;
    
    int uri_scan_status = sscanf(uri, "%*[^:]%*[:/]%[^:]:%d%s", ip_addr, &port, path);
    
    printf("[info] URI scan status : %d\n", uri_scan_status);
    if( uri_scan_status == 3 )
    {   
        printf("[info] IP Address : '%s'\n", ip_addr);
        printf("[info] Port: '%d'\n", port);
        printf("[info] Path : '%s'\n", path);
    }
    
    return 0;
}

However, keep in mind that this solution is tailor made for [protocol_name]://[ip_address]:[port][/path] type of URI's. For understanding more about the components present in the syntax of URI, you can head over to RFC 3986.

Now let's breakdown our tailor made format string : "%*[^:]%*[:/]%[^:]:%d%s"

• %*[^:] helps to ignore the protocol/scheme (eg. http, https, ftp, etc.)

  It basically captures the string from the beginning until it encounters the : character for the first time. And since we have used * right after the % character, therefore the captured string will be ignored.

• %*[:/] helps to ignore the separator that sits between the protocol and the IP address, i.e. ://

• %[^:] helps to capture the string present after the separator, until it encounters :. And this captured string is nothing but the IP address.

• :%d helps to capture the no. sitting right after the : character (the one which was encountered during the capturing of IP address). The no. captured over here is basically your port no.

• %s as you may know, will help you to capture the remaining string which is nothing but the path of the resource you are looking for.

Answer 5

Libcurl now has curl_url_get() function that can extract host, path, etc.

Example code: https://curl.haxx.se/libcurl/c/parseurl.html

/* extract host name from the parsed URL */ 
uc = curl_url_get(h, CURLUPART_HOST, &host, 0);
if(!uc) {
  printf("Host name: %s\n", host);
  curl_free(host);
}

Answer 6

May be late,... what I have used, is - the http_parser_parse_url() function and the required macros separated out from Joyent/HTTP parser lib - that worked well, ~600LOC.