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);
{ "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 }
};
{ 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 },
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;
if (!link_has_scheme)
{
- /* We have no base, and the link does not have a host
- attached to it. Nothing we can do. */
- /* #### Should we print a warning here? Wget 1.5.x used to. */
+ /* Base URL is unavailable, and the link does not have a
+ location attached to it -- we have to give up. Since
+ this can only happen when using `--force-html -i', print
+ a warning. */
+ logprintf (LOG_NOTQUIET,
+ _("%s: Cannot resolve incomplete link %s.\n"),
+ ctx->document_file, link_uri);
return NULL;
}
xfree (complete_uri);
}
+ DEBUGP (("appending \"%s\" to urlpos.\n", url->url));
+
newel = (struct urlpos *)xmalloc (sizeof (struct urlpos));
memset (newel, 0, sizeof (*newel));
/* All the tag_* functions are called from collect_tags_mapper, as
specified by KNOWN_TAGS. */
-/* For most tags, all we want to do is harvest URLs from their
- attributes. */
+/* Default tag handler: collect URLs from attributes specified for
+ this tag by tag_url_attributes. */
static void
tag_find_urls (int tagid, struct taginfo *tag, struct map_context *ctx)
if (tag_url_attributes[i].tagid == tagid)
{
/* We've found the index of tag_url_attributes where the
- attributes of our tags begin. */
+ attributes of our tag begin. */
first = i;
break;
}
{
/* Find whether TAG/ATTRIND is a combination that contains a
URL. */
- char *attrvalue = tag->attrs[attrind].value;
+ char *link = tag->attrs[attrind].value;
/* If you're cringing at the inefficiency of the nested loops,
- remember that the number of attributes the inner loop
- iterates over is laughably small -- three in the worst case
- (IMG). */
+ remember that they both iterate over a laughably small
+ quantity of items. The worst-case inner loop is for the IMG
+ tag, which has three attributes. */
for (i = first; i < size && tag_url_attributes[i].tagid == tagid; i++)
{
if (0 == strcasecmp (tag->attrs[attrind].name,
tag_url_attributes[i].attr_name))
{
int flags = tag_url_attributes[i].flags;
- append_one_url (attrvalue, !(flags & TUA_EXTERNAL),
- tag, attrind, ctx);
+ append_one_url (link, !(flags & TUA_EXTERNAL), tag, attrind, ctx);
}
}
}
}
+/* Handle the BASE tag, for <base href=...>. */
+
static void
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. */
+
static void
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);
}
}
-/* Some pages use a META tag to specify that the page be refreshed by
- a new page after a given number of seconds. The general format for
- this is:
-
- <meta http-equiv=Refresh content="NUMBER; URL=index2.html">
-
- So we just need to skip past the "NUMBER; URL=" garbage to get to
- the URL. */
+/* Handle the META tag. This requires special handling because of the
+ refresh feature and because of robot exclusion. */
static void
tag_handle_meta (int tagid, struct taginfo *tag, struct map_context *ctx)
if (http_equiv && 0 == strcasecmp (http_equiv, "refresh"))
{
- struct urlpos *entry;
+ /* Some pages use a META tag to specify that the page be
+ refreshed by a new page after a given number of seconds. The
+ general format for this is:
+ <meta http-equiv=Refresh content="NUMBER; URL=index2.html">
+
+ So we just need to skip past the "NUMBER; URL=" garbage to
+ 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';
projects / wget / blobdiff