/* Handling of recursive HTTP retrieving.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
- 2004, 2005, 2006, 2007 Free Software Foundation, Inc.
+ 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
This file is part of GNU Wget.
You should have received a copy of the GNU General Public License
along with Wget. If not, see <http://www.gnu.org/licenses/>.
-In addition, as a special exception, the Free Software Foundation
-gives permission to link the code of its release of Wget with the
-OpenSSL project's "OpenSSL" library (or with modified versions of it
-that use the same license as the "OpenSSL" library), and distribute
-the linked executables. You must obey the GNU General Public License
-in all respects for all of the code used other than "OpenSSL". If you
-modify this file, you may extend this exception to your version of the
-file, but you are not obligated to do so. If you do not wish to do
-so, delete this exception statement from your version. */
+Additional permission under GNU GPL version 3 section 7
-#include <config.h>
+If you modify this program, or any covered work, by linking or
+combining it with the OpenSSL project's OpenSSL library (or a
+modified version of that library), containing parts covered by the
+terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
+grants you additional permission to convey the resulting work.
+Corresponding Source for a non-source form of such a combination
+shall include the source code for the parts of OpenSSL used as well
+as that of the covered work. */
+
+#include "wget.h"
#include <stdio.h>
#include <stdlib.h>
#include <errno.h>
#include <assert.h>
-#include "wget.h"
#include "url.h"
#include "recur.h"
#include "utils.h"
#include "hash.h"
#include "res.h"
#include "convert.h"
+#include "html-url.h"
+#include "css-url.h"
#include "spider.h"
\f
/* Functions for maintaining the URL queue. */
int depth; /* the depth */
bool html_allowed; /* whether the document is allowed to
be treated as HTML. */
-
+ struct iri *iri; /* sXXXav */
+ bool css_allowed; /* whether the document is allowed to
+ be treated as CSS. */
struct queue_element *next; /* next element in queue */
};
into it. */
static void
-url_enqueue (struct url_queue *queue,
- const char *url, const char *referer, int depth, bool html_allowed)
+url_enqueue (struct url_queue *queue, struct iri *i,
+ const char *url, const char *referer, int depth,
+ bool html_allowed, bool css_allowed)
{
struct queue_element *qel = xnew (struct queue_element);
+ qel->iri = i;
qel->url = url;
qel->referer = referer;
qel->depth = depth;
qel->html_allowed = html_allowed;
+ qel->css_allowed = css_allowed;
qel->next = NULL;
++queue->count;
DEBUGP (("Enqueuing %s at depth %d\n", url, depth));
DEBUGP (("Queue count %d, maxcount %d.\n", queue->count, queue->maxcount));
+ if (i)
+ DEBUGP (("[IRI Enqueuing %s with %s\n", quote (url),
+ i->uri_encoding ? quote (i->uri_encoding) : "None"));
+
if (queue->tail)
queue->tail->next = qel;
queue->tail = qel;
succeeded, or false if the queue is empty. */
static bool
-url_dequeue (struct url_queue *queue,
+url_dequeue (struct url_queue *queue, struct iri **i,
const char **url, const char **referer, int *depth,
- bool *html_allowed)
+ bool *html_allowed, bool *css_allowed)
{
struct queue_element *qel = queue->head;
if (!queue->head)
queue->tail = NULL;
+ *i = qel->iri;
*url = qel->url;
*referer = qel->referer;
*depth = qel->depth;
*html_allowed = qel->html_allowed;
+ *css_allowed = qel->css_allowed;
--queue->count;
}
\f
static bool download_child_p (const struct urlpos *, struct url *, int,
- struct url *, struct hash_table *);
+ struct url *, struct hash_table *, struct iri *);
static bool descend_redirect_p (const char *, const char *, int,
- struct url *, struct hash_table *);
+ struct url *, struct hash_table *, struct iri *);
/* Retrieve a part of the web beginning with START_URL. This used to
struct hash_table *blacklist;
int up_error_code;
- struct url *start_url_parsed = url_parse (start_url, &up_error_code);
+ struct url *start_url_parsed;
+ struct iri *i = iri_new ();
+ set_uri_encoding (i, opt.locale, true);
+ start_url_parsed = url_parse (start_url, &up_error_code, i);
if (!start_url_parsed)
{
logprintf (LOG_NOTQUIET, "%s: %s.\n", start_url,
/* 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, true);
+ url_enqueue (queue, i, xstrdup (start_url_parsed->url), NULL, 0, true,
+ false);
string_set_add (blacklist, start_url_parsed->url);
while (1)
bool descend = false;
char *url, *referer, *file = NULL;
int depth;
- bool html_allowed;
+ bool html_allowed, css_allowed;
+ bool is_css = false;
bool dash_p_leaf_HTML = false;
if (opt.quota && total_downloaded_bytes > opt.quota)
/* Get the next URL from the queue... */
- if (!url_dequeue (queue,
+ if (!url_dequeue (queue, (struct iri **) &i,
(const char **)&url, (const char **)&referer,
- &depth, &html_allowed))
+ &depth, &html_allowed, &css_allowed))
break;
/* ...and download it. Note that this download is in most cases
DEBUGP (("Already downloaded \"%s\", reusing it from \"%s\".\n",
url, file));
+ /* this sucks, needs to be combined! */
if (html_allowed
&& downloaded_html_set
&& string_set_contains (downloaded_html_set, file))
- descend = true;
+ {
+ descend = true;
+ is_css = false;
+ }
+ if (css_allowed
+ && downloaded_css_set
+ && string_set_contains (downloaded_css_set, file))
+ {
+ descend = true;
+ is_css = true;
+ }
}
else
{
int dt = 0;
char *redirected = NULL;
- status = retrieve_url (url, &file, &redirected, referer, &dt, false);
+ status = retrieve_url (url, &file, &redirected, referer, &dt,
+ false, i);
if (html_allowed && file && status == RETROK
&& (dt & RETROKF) && (dt & TEXTHTML))
- descend = true;
+ {
+ descend = true;
+ is_css = false;
+ }
+
+ /* a little different, css_allowed can override content type
+ lots of web servers serve css with an incorrect content type
+ */
+ if (file && status == RETROK
+ && (dt & RETROKF) &&
+ ((dt & TEXTCSS) || css_allowed))
+ {
+ descend = true;
+ is_css = true;
+ }
if (redirected)
{
if (descend)
{
if (!descend_redirect_p (redirected, url, depth,
- start_url_parsed, blacklist))
+ start_url_parsed, blacklist, i))
descend = false;
else
/* Make sure that the old pre-redirect form gets
}
}
- /* If the downloaded document was HTML, parse it and enqueue the
+ /* If the downloaded document was HTML or CSS, parse it and enqueue the
links it contains. */
if (descend)
{
bool meta_disallow_follow = false;
struct urlpos *children
- = get_urls_html (file, url, &meta_disallow_follow);
+ = is_css ? get_urls_css_file (file, url) :
+ get_urls_html (file, url, &meta_disallow_follow, i);
if (opt.use_robots && meta_disallow_follow)
{
if (children)
{
struct urlpos *child = children;
- struct url *url_parsed = url_parsed = url_parse (url, NULL);
+ struct url *url_parsed = url_parse (url, NULL, i);
+ struct iri *ci;
char *referer_url = url;
bool strip_auth = (url_parsed != NULL
&& url_parsed->user != NULL);
if (dash_p_leaf_HTML && !child->link_inline_p)
continue;
if (download_child_p (child, url_parsed, depth, start_url_parsed,
- blacklist))
+ blacklist, i))
{
- url_enqueue (queue, xstrdup (child->url->url),
+ ci = iri_new ();
+ set_uri_encoding (ci, i->content_encoding, false);
+ url_enqueue (queue, ci, xstrdup (child->url->url),
xstrdup (referer_url), depth + 1,
- child->link_expect_html);
+ child->link_expect_html,
+ child->link_expect_css);
/* We blacklist the URL we have enqueued, because we
don't want to enqueue (and hence download) the
same URL twice. */
}
}
- if (file
- && (opt.delete_after
+ if (file
+ && (opt.delete_after
|| opt.spider /* opt.recursive is implicitely true */
|| !acceptable (file)))
{
/* Either --delete-after was specified, or we loaded this
- (otherwise unneeded because of --spider or rejected by -R)
- HTML file just to harvest its hyperlinks -- in either case,
+ (otherwise unneeded because of --spider or rejected by -R)
+ HTML file just to harvest its hyperlinks -- in either case,
delete the local file. */
DEBUGP (("Removing file due to %s in recursive_retrieve():\n",
opt.delete_after ? "--delete-after" :
- (opt.spider ? "--spider" :
+ (opt.spider ? "--spider" :
"recursive rejection criteria")));
logprintf (LOG_VERBOSE,
(opt.delete_after || opt.spider
xfree (url);
xfree_null (referer);
xfree_null (file);
+ iri_free (i);
}
/* If anything is left of the queue due to a premature exit, free it
{
char *d1, *d2;
int d3;
- bool d4;
- while (url_dequeue (queue,
- (const char **)&d1, (const char **)&d2, &d3, &d4))
+ bool d4, d5;
+ struct iri *d6;
+ while (url_dequeue (queue, (struct iri **)&d6,
+ (const char **)&d1, (const char **)&d2, &d3, &d4, &d5))
{
+ iri_free (d6);
xfree (d1);
xfree_null (d2);
}
static bool
download_child_p (const struct urlpos *upos, struct url *parent, int depth,
- struct url *start_url_parsed, struct hash_table *blacklist)
+ struct url *start_url_parsed, struct hash_table *blacklist,
+ struct iri *iri)
{
struct url *u = upos->url;
const char *url = u->url;
if (string_set_contains (blacklist, url))
{
- if (opt.spider)
+ if (opt.spider)
{
char *referrer = url_string (parent, URL_AUTH_HIDE_PASSWD);
- DEBUGP (("download_child_p: parent->url is: `%s'\n", parent->url));
+ DEBUGP (("download_child_p: parent->url is: %s\n", quote (parent->url)));
visited_url (url, referrer);
xfree (referrer);
}
if (!specs)
{
char *rfile;
- if (res_retrieve_file (url, &rfile))
+ if (res_retrieve_file (url, &rfile, iri))
{
specs = res_parse_from_file (rfile);
+
+ /* Delete the robots.txt file if we chose to either delete the
+ files after downloading or we're just running a spider. */
+ if (opt.delete_after || opt.spider)
+ {
+ logprintf (LOG_VERBOSE, "Removing %s.\n", rfile);
+ if (unlink (rfile))
+ logprintf (LOG_NOTQUIET, "unlink: %s\n",
+ strerror (errno));
+ }
+
xfree (rfile);
}
else
static bool
descend_redirect_p (const char *redirected, const char *original, int depth,
- struct url *start_url_parsed, struct hash_table *blacklist)
+ struct url *start_url_parsed, struct hash_table *blacklist,
+ struct iri *iri)
{
struct url *orig_parsed, *new_parsed;
struct urlpos *upos;
bool success;
- orig_parsed = url_parse (original, NULL);
+ orig_parsed = url_parse (original, NULL, NULL);
assert (orig_parsed != NULL);
- new_parsed = url_parse (redirected, NULL);
+ new_parsed = url_parse (redirected, NULL, NULL);
assert (new_parsed != NULL);
upos = xnew0 (struct urlpos);
upos->url = new_parsed;
success = download_child_p (upos, orig_parsed, depth,
- start_url_parsed, blacklist);
+ start_url_parsed, blacklist, iri);
url_free (orig_parsed);
url_free (new_parsed);
projects / wget / blobdiff