// GETURL.C -- Win32 console app -- rename gethttp, allow w/o http://
// Andrew Schulman, February 1997
// andrew@ora.com
// cl geturl.c wsock32.lib
// geturl [-head] [-split] [-input file] [-post data] <http://whatever or -stdin>
// also handles URLs of form <A HREF="http://xxxx">, converts to http://xxxx

// TODO:
// -- accept filename on cmdline to save to (e.g., for GIF)
// -- after have filename, provide option to show in browser (via ShellExecute ddeexec)
// -- doesn't work for ftp:// yet!
// -- https:// doesn't really work, obviously!
// -- support mailto: to show SMTP vs. MAPI?
// -- make non-Windows version (no WSAStartup, winsock.h, etc.)
// -- support Connection: Keep-Alive
// -- add -links, -tag name,name,name options
// -- improve -split option: tags on single line, no extra blank line
// -- support :port, e.g., http://www.eb.com:195

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <io.h>
#include "winsock.h"

void fail(const char *s) { puts(s); exit(1); }

#define msg(s)  { printf("FAIL: %s\n", s); return 0; }

char *nomem = "insufficient memory";

#define BUFFER_SIZE  20480
#define WINSOCK_VERSION 0x0101
#define NO_FLAGS 0
#define HTTP_PORT 80
#define HTTPS_PORT 443
#define FTP_PORT 21

// options
int do_head = 0, do_manual_input = 0, do_post = 0, do_split = 0, do_base = 0;
int do_loc = 1, do_verbose = 1;
char *input_file, *post_data, *base;

SOCKET ConnectWebServerSocket(char *host, int port)
{
    static int did_startup = 0;
    static WSADATA wsaData;
    LPHOSTENT pHostEnt;
    SOCKADDR_IN sockAddr;
    struct in_addr *addr;
    u_char b[4];
    SOCKET sock = INVALID_SOCKET;

    if (! did_startup)
    {
        if (WSAStartup(WINSOCK_VERSION, &wsaData))
            msg("WSAStartup");
        did_startup = 1;
    }
    
    sockAddr.sin_family = AF_INET;
    sockAddr.sin_port = htons(port);
    if (isdigit(*host))
    {
        // already have IP address; don't need DNS lookup
        sscanf(host, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]);
        sockAddr.sin_addr.s_addr = *((u_long *) b);
    }
    else
    {
        if (!(pHostEnt = gethostbyname(host)))
            msg("gethostbyname");
        sockAddr.sin_addr = *((LPIN_ADDR)*pHostEnt->h_addr_list);
    }

    // TODO:since gethostbyname is expensive? (DNS), see if same as last time?
    
    // TODO: SO_USELOOPBACK for http://localhost, "local CGI", etc.
    // TODO: maybe use SO_KEEPALIVE?
    if ((sock = socket(PF_INET, SOCK_STREAM, IPPROTO_TCP)) == INVALID_SOCKET)
        msg("socket");
    
    if (do_verbose)
    {
        addr = (struct in_addr *) &sockAddr.sin_addr;
        memcpy(b, (u_char *) &addr->S_un.S_un_b, sizeof(unsigned long));
        printf("Connecting to %u.%u.%u.%u\n", b[0], b[1], b[2], b[3]);
    }

    if (connect(sock, (LPSOCKADDR)&sockAddr, sizeof(sockAddr)) != 0)
        msg("connect");
    
    return sock;
}

int SendWebQuery(SOCKET sock, char * szQuery)
{
    char *request;

    if (! (request = malloc(2048)))
        msg(nomem);
    if (do_manual_input)
    {
        char line[80];
        FILE *f = fopen(input_file, "r");
        if (f == (FILE *) -1)
            msg("Can't open input file");
        request[0] = 0;
        while (fgets(line, 80, f))
        {
            if (strlen(request)+strlen(line) >= 2048)
                msg("Sorry, 2k limit");
            strcat(request, line[0] ? line : "\n");
        }
        fclose(f);
    }
    else if (do_post)
    {
        sprintf(request, 
            "POST %s HTTP/1.0\n"
            "Content-type: application/x-www-form-urlencoded\n"
            "Content-length: %u\n\n"
            "%s\n",
            szQuery, strlen(post_data), post_data);
    }
    else
    {
        sprintf(request, "%s %s HTTP/1.0\n\n", 
            (do_head ? "HEAD" : "GET"), szQuery);
    }
    if (send(sock, request, strlen(request), NO_FLAGS) == 
        SOCKET_ERROR)
        msg("send");
    free(request);
    return 0;
}

int get_url(char *url);

static char *location_str = "Location:" ;
static int location_len = 0;

// should first check for "302 Redirection"!!
// should only do inside header, before first "\n\n"!!
int look_for_reloc(char *buf, int len)
{
    char *s, *s2;
    if (! location_len) location_len = strlen(location_str);

    if (s = strstr(buf, location_str))
    {
        char *url;
        if (! (url = malloc(512)))
            msg(nomem);
        if (s2 = strchr(s, '\r'))
            *s2 = '\0'; // seal off line
        if (s2 = strchr(s, '\n'))
            *s2 = '\0'; // seal off line
        strncpy(url, s, 512);
        puts(url);
        // if url doesn't contain "//" or "/" then is relative URL!!
        // e.g., www.truevalue.com -> index.cgi
        if (get_url(url))
        {
            free(url);
            return 1;
        }
        else
            puts("--- Couldn't get redirected URL ---");
        free(url);
    }
    return 0;
}
                                        
UINT RecvWebFile(SOCKET sock, char *buf)
{
    int len;
    if ((len = recv(sock, buf, BUFFER_SIZE, NO_FLAGS)) == SOCKET_ERROR)
        msg("recv");
    if (do_loc && look_for_reloc(buf, len))
        return 0;
    return len;
}

int get_file(SOCKET sock, char *pathname);

// confusing name, because also have -split option!
int split(char *url, char *hostname, char *pathname)
{
    char *buf, *h, *f, *s;
    int protocol = HTTP_PORT;

    if (! location_len) location_len = strlen(location_str);

    if (! (buf = malloc(2048)))
        msg(nomem);

    // can do redirection for now with geturl | grep Location: | geturl -stdin
    if (strncmp(url, location_str, location_len) == 0)
        url += location_len;
    
    // if quotes in URL, then yank out stuff within quotes
    // to handle <A HREF="xxxx"> lines gracefully
    if (strchr(url, '\"'))
    {
        strcpy(buf, url);
        url = buf;
        while (*url != '\"') url++; url++;
        if (s = strchr(url, '\"')) 
            *s = '\0';   // block off any close quote
    }
    
    while (isspace(*url))
        url++;
    
    if (do_base && (! strstr(url, "//")))
    {
        static char *buf = (char *) 0;
        if (! buf)
            if (! (buf = malloc(2048)))
                msg(nomem);
        strcpy(buf, base);
        strcat(buf, url);
        url = buf;
    }

    if (strstr(url, "//"))
    {
        if (strncmp(url, "http://", 7) == 0)
            { url += 7; protocol = HTTP_PORT; }
        else if (strncmp(url, "https://", 8) == 0)
            { url += 8; protocol = HTTPS_PORT; }
        else if (strncmp(url, "ftp://", 6) == 0)
            { url += 6; protocol = FTP_PORT; }
        else
            { protocol = 0; msg("protocol"); }
    }
    
    h = url;
    f = url;
    while (*f && (*f != '/')) 
        f++;
    strcpy(pathname, *f ? f : "/");
    *f = 0;
    strcpy(hostname, h);
    free(buf);
    return protocol;
}

void display(char *buf, int recv)
{
    static int in_tag = 0;  // make static so carries over multiple buffers
    static int got_nl = 0;
    if (do_split)
    {
        char *s;
        int i;
        for (i=recv, s=buf; i--; s++)
            switch (*s)
            {
                case '\n' :
                case '\r' :
                    if (in_tag)
                        putchar(' ');
                    else
                    {
                        if (! got_nl)
                            putchar(*s);
                        got_nl = 1;
                    }
                    break;
                case '<' : if (! got_nl) putchar('\n'); putchar('<'); in_tag++; break;
                case '>' : putchar('>'); putchar('\n'); got_nl = 1; in_tag--; break;
                default :  putchar(*s); got_nl = 0; break;
            }
    }
    else
        fwrite(buf, recv, 1, stdout);
}

int get_file(SOCKET sock, char *pathname)
{
    char *buf;
    UINT recv;
    char *s;

    if (! (buf = malloc(BUFFER_SIZE)))
        msg(nomem);
    if (SendWebQuery(sock, pathname) != 0)
        msg("SendWebQuery");
    while (((recv = RecvWebFile(sock, buf)) != 0))
        display(buf, recv);
    free(buf);
    putchar('\n');
    return 1;
}

int get_url(char *url)
{
    char hostname[256], pathname[512];
    SOCKET sock;
    int protocol;

    if (! (protocol = split(url, hostname, pathname)))
        return 0;

    // printf("get_url: [%u,%s,%s]\n", protocol, hostname, pathname);

    if ((sock = ConnectWebServerSocket(hostname, protocol)) == 
        INVALID_SOCKET)
        msg("ConnectWebServerSocket");
    get_file(sock, pathname);
    closesocket(sock);
    
    return 1;
}

char *usage = "usage: geturl [options] <http://whatever or -stdin>\n"
    "  options:\n"
    "  -noloc : don't do HTTP relocations (default on)\n"
    "  -base <addr> : use addr as base for all relative URLs\n"
    "  -head : do HTTP HEAD (default GET)\n"
    "  -post <data> : do HTTP POST of data\n"
    "  -input <file> : get all HTTP headers from file\n"
    "  -stdin : get URLs from stdin\n"
    "  -split : break HTML output into lines on tags\n";
        
int main(int argc, char *argv[])
{
    int i;
    int do_stdin = 0;
    if (argc < 2)
        fail(usage);
    for (i=1; i<argc; i++)
    {
        if ((argv[i][0] == '-') || (argv[i][0] == '/'))
        {
            char *option = strupr(&argv[i][1]);
            #define OPTION(x) (strcmp(option, x) == 0)
            if (OPTION("SPLIT"))        do_split = 1;
            else if (OPTION("STDIN"))   do_stdin = 1;
            else if (OPTION("HEAD"))    do_head = 1;
            else if (OPTION("NOLOC"))   do_loc = 0;
            else if (OPTION("INPUT")) { do_manual_input = 1; 
                                        input_file = argv[++i]; }
            else if (OPTION("POST"))  { do_post = 1;
                                        post_data = argv[++i]; }
            else if (OPTION("BASE"))  { do_base = 1;
                                        base = argv[++i]; }
            else                        fail(usage);
        }
        else
        {
            puts(argv[i]);
            if (! get_url(argv[i]))
                puts("--- Couldn't get URL ---");
        }
    }
    
    if (do_stdin)
    {
        char buf[1024];
        while (gets(buf))
        {
            puts(buf);
            if (! get_url(buf))
                puts("--- Couldn't get URL ---");
        }
    }
}