Follow <source>/<track> as embedded near-links (#451) (#457)

src/srcset are already extracted from any element via hts_detect[], so
<source>/<track> URLs were captured. But hts_detect_embed only listed
<img src>, so at the recursion-depth boundary under --near these media
were treated as plain links and dropped, unlike <img>. Add a separate
HTML5 media table (keeping the legacy one clang-format-stable) and chain
the embed lookup through both.

Signed-off-by: Xavier Roche <roche@httrack.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

src/htsbasenet.h

@@ -129,6 +129,8 @@ typedef enum HTTPStatusCode {
   HTTP_UNSUPPORTED_MEDIA_TYPE = 415,
   HTTP_REQUESTED_RANGE_NOT_SATISFIABLE = 416,
   HTTP_EXPECTATION_FAILED = 417,
+  HTTP_TOO_MANY_REQUESTS = 429,
+  HTTP_UNAVAILABLE_FOR_LEGAL_REASONS = 451,
   HTTP_INTERNAL_SERVER_ERROR = 500,
   HTTP_NOT_IMPLEMENTED = 501,
   HTTP_BAD_GATEWAY = 502,

src/htscatchurl.c

@@ -64,7 +64,7 @@ Please visit our Website: http://www.httrack.com
 // catch_url_init(&port,&return_host);
 HTSEXT_API T_SOC catch_url_init_std(int *port_prox, char *adr_prox) {
   T_SOC soc;
-  int try_to_listen_to[] = { 8080, 3128, 80, 81, 82, 8081, 3129, 31337, 0, -1 };
+  int try_to_listen_to[] = {8080, 3128, 80, 81, 82, 8081, 3129, 0, -1};
   int i = 0;
 
   do {

src/htslib.c

@@ -1951,6 +1951,10 @@ HTSEXT_API const char *infostatuscode_const(int statuscode) {
     return "Requested Range Not Satisfiable";
   case 417:
     return "Expectation Failed";
+  case 429:
+    return "Too Many Requests";
+  case 451:
+    return "Unavailable For Legal Reasons";
   case 500:
     return "Internal Server Error";
   case 501:
@@ -5797,6 +5801,13 @@ HTSEXT_API int hts_init(void) {
       abortLog("unable to initialize TLS: SSL_CTX_new()");
       assertf("unable to initialize TLS" == NULL);
     }
+    /* Pin a TLS floor (no SSLv3/TLS1.0/1.1); no cert verify, by design. */
+#if OPENSSL_VERSION_NUMBER >= 0x10100000L
+    SSL_CTX_set_min_proto_version(openssl_ctx, TLS1_2_VERSION);
+#else
+    SSL_CTX_set_options(openssl_ctx, SSL_OP_NO_SSLv2 | SSL_OP_NO_SSLv3 |
+                                         SSL_OP_NO_TLSv1 | SSL_OP_NO_TLSv1_1);
+#endif
   }
 #endif
 

src/htsselftest.c

@@ -1318,6 +1318,24 @@ static int st_useragent(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* HTTP status code -> reason phrase, including the modern 429/451. */
+static int st_status(httrackp *opt, int argc, char **argv) {
+  const char *s;
+  (void) opt;
+  (void) argc;
+  (void) argv;
+  s = infostatuscode_const(429);
+  assertf(s != NULL && strcmp(s, "Too Many Requests") == 0);
+  s = infostatuscode_const(451);
+  assertf(s != NULL && strcmp(s, "Unavailable For Legal Reasons") == 0);
+  /* A spot-check of a long-standing code, and an unknown one. */
+  s = infostatuscode_const(404);
+  assertf(s != NULL && strcmp(s, "Not Found") == 0);
+  assertf(infostatuscode_const(799) == NULL);
+  printf("status self-test OK\n");
+  return 0;
+}
+
 /* ------------------------------------------------------------ */
 /* Registry: name -> handler, with a usage hint and a one-line description. */
 /* ------------------------------------------------------------ */
@@ -1365,6 +1383,7 @@ static const struct selftest_entry {
     {"dns", "", "DNS resolver/cache self-test", st_dns},
     {"cookies", "", "cookie request-header self-test", st_cookies},
     {"useragent", "", "default User-Agent self-test", st_useragent},
+    {"status", "", "HTTP status code -> reason phrase self-test", st_status},
 };
 
 static void list_selftests(void) {

src/proxy/proxytrack.c

@@ -497,6 +497,12 @@ static const char *GetHttpMessage(int statuscode) {
   case 417:
     return "Expectation Failed";
     break;
+  case 429:
+    return "Too Many Requests";
+    break;
+  case 451:
+    return "Unavailable For Legal Reasons";
+    break;
   case 500:
     return "Internal Server Error";
     break;

tests/01_engine-status.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# HTTP status -> reason phrase, including the modern 429/451 (#453).
+httrack -O /dev/null -#test=status run | grep -q "status self-test OK"

tests/Makefile.am

@@ -47,6 +47,7 @@ TESTS = \
 	01_engine-savename.test \
 	01_engine-selftest-dispatch.test \
 	01_engine-simplify.test \
+	01_engine-status.test \
 	01_engine-stripquery.test \
 	01_engine-strsafe.test \
 	01_engine-urlhack.test \