X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Fhtml-url.c;h=11789e59f017561f966b989a2a1d731b76d12c55;hp=73425c05913b8ebd4c2ee372ff9cdef8dcf3aaca;hb=8f93191f2656768dee6f9f700b9653421df55e1c;hpb=390adeea93dd76e8a9c818e996067670009023d3

diff --git a/src/html-url.c b/src/html-url.c
index 73425c05..11789e59 100644
--- a/src/html-url.c
+++ b/src/html-url.c
@@ -48,6 +48,7 @@ typedef void (*tag_handler_t) PARAMS ((int, struct taginfo *,
 
 DECLARE_TAG_HANDLER (tag_find_urls);
 DECLARE_TAG_HANDLER (tag_handle_base);
+DECLARE_TAG_HANDLER (tag_handle_form);
 DECLARE_TAG_HANDLER (tag_handle_link);
 DECLARE_TAG_HANDLER (tag_handle_meta);
 
@@ -73,29 +74,31 @@ static struct {
   { "embed",	tag_find_urls },
 #define TAG_FIG		7
   { "fig",	tag_find_urls },
-#define TAG_FRAME	8
+#define TAG_FORM	8
+  { "form",	tag_handle_form },
+#define TAG_FRAME	9
   { "frame",	tag_find_urls },
-#define TAG_IFRAME	9
+#define TAG_IFRAME	10
   { "iframe",	tag_find_urls },
-#define TAG_IMG		10
+#define TAG_IMG		11
   { "img",	tag_find_urls },
-#define TAG_INPUT	11
+#define TAG_INPUT	12
   { "input",	tag_find_urls },
-#define TAG_LAYER	12
+#define TAG_LAYER	13
   { "layer",	tag_find_urls },
-#define TAG_LINK	13
+#define TAG_LINK	14
   { "link",	tag_handle_link },
-#define TAG_META	14
+#define TAG_META	15
   { "meta",	tag_handle_meta },
-#define TAG_OVERLAY	15
+#define TAG_OVERLAY	16
   { "overlay",	tag_find_urls },
-#define TAG_SCRIPT	16
+#define TAG_SCRIPT	17
   { "script",	tag_find_urls },
-#define TAG_TABLE	17
+#define TAG_TABLE	18
   { "table",	tag_find_urls },
-#define TAG_TD		18
+#define TAG_TD		19
   { "td",	tag_find_urls },
-#define TAG_TH		19
+#define TAG_TH		20
   { "th",	tag_find_urls }
 };
 
@@ -120,7 +123,7 @@ static struct {
   { TAG_AREA,		"href",		TUA_EXTERNAL },
   { TAG_BGSOUND,	"src",		0 },
   { TAG_BODY,		"background",	0 },
-  { TAG_EMBED,		"href",		0 },
+  { TAG_EMBED,		"href",		TUA_EXTERNAL },
   { TAG_EMBED,		"src",		0 },
   { TAG_FIG,		"src",		0 },
   { TAG_FRAME,		"src",		0 },
@@ -141,10 +144,11 @@ static struct {
    from the information above.  However, some places in the code refer
    to the attributes not mentioned here.  We add them manually.  */
 static const char *additional_attributes[] = {
-  "rel",			/* for TAG_LINK */
-  "http-equiv",			/* for TAG_META */
-  "name",			/* for TAG_META */
-  "content"			/* for TAG_META */
+  "rel",			/* used by tag_handle_link */
+  "http-equiv",			/* used by tag_handle_meta */
+  "name",			/* used by tag_handle_meta */
+  "content",			/* used by tag_handle_meta */
+  "action"			/* used by tag_handle_form */
 };
 
 static const char **interesting_tags;
@@ -475,6 +479,22 @@ tag_handle_base (int tagid, struct taginfo *tag, struct map_context *ctx)
     ctx->base = xstrdup (newbase);
 }
 
+/* Mark the URL found in <form action=...> for conversion. */
+
+static void
+tag_handle_form (int tagid, struct taginfo *tag, struct map_context *ctx)
+{
+  int attrind;
+  char *action = find_attr (tag, "action", &attrind);
+  if (action)
+    {
+      struct urlpos *action_urlpos = append_one_url (action, 0, tag,
+						     attrind, ctx);
+      if (action_urlpos)
+	action_urlpos->ignore_when_downloading = 1;
+    }
+}
+
 /* Handle the LINK tag.  It requires special handling because how its
    links will be followed in -p mode depends on the REL attribute.  */
 
@@ -484,12 +504,18 @@ tag_handle_link (int tagid, struct taginfo *tag, struct map_context *ctx)
   int attrind;
   char *href = find_attr (tag, "href", &attrind);
 
-  /* All <link href="..."> link references are external,
-     except for <link rel="stylesheet" href="...">.  */
+  /* All <link href="..."> link references are external, except those
+     known not to be, such as style sheet and shortcut icon:
+
+       <link rel="stylesheet" href="...">
+       <link rel="shortcut icon" href="...">
+  */
   if (href)
     {
       char *rel  = find_attr (tag, "rel", NULL);
-      int inlinep = (rel && 0 == strcasecmp (rel, "stylesheet"));
+      int inlinep = (rel
+		     && (0 == strcasecmp (rel, "stylesheet")
+			 || 0 == strcasecmp (rel, "shortcut icon")));
       append_one_url (href, inlinep, tag, attrind, ctx);
     }
 }
@@ -515,10 +541,13 @@ tag_handle_meta (int tagid, struct taginfo *tag, struct map_context *ctx)
 	 get to the URL.  */
 
       struct urlpos *entry;
-
       int attrind;
-      char *p, *refresh = find_attr (tag, "content", &attrind);
       int timeout = 0;
+      char *p;
+
+      char *refresh = find_attr (tag, "content", &attrind);
+      if (!refresh)
+	return;
 
       for (p = refresh; ISDIGIT (*p); p++)
 	timeout = 10 * timeout + *p - '0';