uerr_t status = RETROK;
/* The queue of URLs we need to load. */
- struct url_queue *queue = url_queue_new ();
+ struct url_queue *queue;
/* The URLs we do not wish to enqueue, because they are already in
the queue, but haven't been downloaded yet. */
- struct hash_table *blacklist = make_string_hash_table (0);
+ struct hash_table *blacklist;
- /* We'll need various components of this, so better get it over with
- now. */
- struct url *start_url_parsed = url_parse (start_url, NULL);
+ int up_error_code;
+ struct url *start_url_parsed = url_parse (start_url, &up_error_code);
- url_enqueue (queue, xstrdup (start_url), NULL, 0);
- string_set_add (blacklist, start_url);
+ if (!start_url_parsed)
+ {
+ logprintf (LOG_NOTQUIET, "%s: %s.\n", start_url,
+ url_error (up_error_code));
+ return URLERROR;
+ }
+
+ queue = url_queue_new ();
+ blacklist = make_string_hash_table (0);
+
+ /* Enqueue the starting URL. Use start_url_parsed->url rather than
+ just URL so we enqueue the canonical form of the URL. */
+ url_enqueue (queue, xstrdup (start_url_parsed->url), NULL, 0);
+ string_set_add (blacklist, start_url_parsed->url);
while (1)
{
/* 1. Schemes other than HTTP are normally not recursed into. */
if (u->scheme != SCHEME_HTTP
+#ifdef HAVE_SSL
+ && u->scheme != SCHEME_HTTPS
+#endif
&& !(u->scheme == SCHEME_FTP && opt.follow_ftp))
{
DEBUGP (("Not following non-HTTP schemes.\n"));
/* 2. If it is an absolute link and they are not followed, throw it
out. */
- if (u->scheme == SCHEME_HTTP)
+ if (u->scheme == SCHEME_HTTP
+#ifdef HAVE_SSL
+ || u->scheme == SCHEME_HTTPS
+#endif
+ )
if (opt.relative_only && !upos->link_relative_p)
{
DEBUGP (("It doesn't really look like a relative link.\n"));
}
}
- /* 6. */
- {
- char *suf;
- /* Check for acceptance/rejection rules. We ignore these rules
- for HTML documents because they might lead to other files which
- need to be downloaded. Of course, we don't know which
- documents are HTML before downloading them, so we guess.
-
- A file is subject to acceptance/rejection rules if:
-
- * u->file is not "" (i.e. it is not a directory)
- and either:
- + there is no file suffix,
- + or there is a suffix, but is not "html" or "htm",
- + both:
- - recursion is not infinite,
- - and we are at its very end. */
-
- if (u->file[0] != '\0'
- && ((suf = suffix (url)) == NULL
- || (0 != strcmp (suf, "html") && 0 != strcmp (suf, "htm"))
- || (opt.reclevel != INFINITE_RECURSION && depth >= opt.reclevel)))
- {
- if (!acceptable (u->file))
- {
- DEBUGP (("%s (%s) does not match acc/rej rules.\n",
- url, u->file));
- goto out;
- }
- }
- }
+ /* 6. Check for acceptance/rejection rules. We ignore these rules
+ for directories (no file name to match) and for HTML documents,
+ which might lead to other files that do need to be downloaded.
+ That is, unless we've exhausted the recursion depth anyway. */
+ if (u->file[0] != '\0'
+ && !(has_html_suffix_p (u->file)
+ && depth < opt.reclevel - 1
+ && depth != INFINITE_RECURSION))
+ {
+ if (!acceptable (u->file))
+ {
+ DEBUGP (("%s (%s) does not match acc/rej rules.\n",
+ url, u->file));
+ goto out;
+ }
+ }
/* 7. */
if (u->scheme == parent->scheme)
}
/* 8. */
- if (opt.use_robots && u->scheme == SCHEME_HTTP)
+ if (opt.use_robots && (u->scheme == SCHEME_HTTP
+#ifdef HAVE_SSL
+ || u->scheme == SCHEME_HTTPS
+#endif
+ )
+ )
{
struct robot_specs *specs = res_get_specs (u->host, u->port);
if (!specs)