From 6f5eaccd75960719d6d94ca5c4c6bfb8a57c90ff Mon Sep 17 00:00:00 2001
From: Jarno Mäkipää <jmakip87@gmail.com>
Date: Sat, 19 Oct 2019 08:37:09 +0300
Subject: wget: Added support for HTTP 301 and 302 redirects

Added: parsing of redirectation responses, will now follow redirectation
path until maximum of 10 jumps. This will probably lead to server
advertising user the https url.
---
 toys/pending/wget.c | 67 ++++++++++++++++++++++++++++++++---------------------
 1 file changed, 41 insertions(+), 26 deletions(-)

(limited to 'toys/pending/wget.c')

diff --git a/toys/pending/wget.c b/toys/pending/wget.c
index eb496da2..405ed942 100644
--- a/toys/pending/wget.c
+++ b/toys/pending/wget.c
@@ -100,7 +100,7 @@ static int conn_svr(const char *hostname, const char *port) {
       continue;
     }
     if (connect(sock, rp->ai_addr, rp->ai_addrlen) != -1)
-      break; // succeed in connecting to any server IP 
+      break; // succeed in connecting to any server IP
     else perror_msg("connect error");
     close(sock);
   }
@@ -131,10 +131,10 @@ static char *get_body(ssize_t len, ssize_t *body_len) {
 
 void wget_main(void)
 {
-  int sock;
+  int sock, redirects = 10;
   FILE *fp;
   ssize_t len, body_len;
-  char *body, *result, *rc, *r_str;
+  char *body, *result, *rc, *r_str, *redir_loc = 0;
   char ua[18] = "toybox wget", ver[6], hostname[1024], port[6], path[1024];
 
   // TODO extract filename to be saved from URL
@@ -144,34 +144,49 @@ void wget_main(void)
   if(!toys.optargs[0]) help_exit("no URL");
   get_info(toys.optargs[0], hostname, port, path);
 
-  sock = conn_svr(hostname, port);
 
-  // compose HTTP request
-  sprintf(toybuf, "GET %s HTTP/1.1\r\n", path);
-  mk_fld("Host", hostname);
 #ifdef TOYBOX_VERSION
   strcat(ua, "/"), strncpy(ver, TOYBOX_VERSION, 5), strcat(ua, ver);
 #endif
-  mk_fld("User-Agent", ua); 
-  mk_fld("Connection", "close");
-  strcat(toybuf, "\r\n");
+  for (;; redirects--) {
+    sock = conn_svr(hostname, port);
+    // compose HTTP request
+    sprintf(toybuf, "GET %s HTTP/1.1\r\n", path);
+    mk_fld("Host", hostname);
+    mk_fld("User-Agent", ua);
+    mk_fld("Connection", "close");
+    strcat(toybuf, "\r\n");
+
+    // send the HTTP request
+    len = strlen(toybuf);
+    if (write(sock, toybuf, len) != len) perror_exit("write error");
+
+    // read HTTP response
+    if ((len = read(sock, toybuf, 4096)) == -1) perror_exit("read error");
+    if (!strstr(toybuf, "\r\n\r\n")) error_exit("too long HTTP response");
+    body = get_body(len, &body_len);
+    redir_loc = strstr(toybuf, "Location: ");
+    result = strtok(toybuf, "\r");
+    strtok(result, " ");
+    rc = strtok(NULL, " ");
+    r_str = strtok(NULL, " ");
+
+    // HTTP res code check
+    if (!strcmp(rc, "301") || !strcmp(rc, "302")) {
+      char* eol = 0;
+      if ((eol = strchr(redir_loc, '\r')) > 0) *eol = 0;
+      else if (redir_loc) error_exit("Could not parse redirect URL");
+      if (redirects < 0) error_exit("Too many redirects");
+
+      printf("Redirection: %s %s \n", rc, r_str);
+      printf("%s \n", redir_loc);
+      redir_loc = redir_loc+strlen("Location: ");
+      close(sock);
+      get_info(redir_loc, hostname, port, path);
+    } else if (!strcmp(rc, "200")) break;
+    else error_exit("res: %s(%s)", rc, r_str);
+  }
 
-  // send the HTTP request
-  len = strlen(toybuf);
-  if (write(sock, toybuf, len) != len) perror_exit("write error");
-
-  // read HTTP response
-  if ((len = read(sock, toybuf, 4096)) == -1) perror_exit("read error");
-  if (!strstr(toybuf, "\r\n\r\n")) error_exit("too long HTTP response");
-  body = get_body(len, &body_len);
-  result = strtok(toybuf, "\r");
-  strtok(result, " ");
-  rc = strtok(NULL, " ");
-  r_str = strtok(NULL, " ");
-
-  // HTTP res code check
-  // TODO handle HTTP 302 Found(Redirection)
-  if (strcmp(rc, "200")) error_exit("res: %s(%s)", rc, r_str);
 
   if (!(fp = fopen(TT.filename, "w"))) perror_exit("fopen error");
   if (fwrite(body, 1, body_len, fp) != body_len)
-- 
cgit v1.2.3