/* Handling of recursive HTTP retrieving.
Copyright (C) 1995, 1996, 1997, 2000 Free Software Foundation, Inc.
-This file is part of Wget.
+This file is part of GNU Wget.
-This program is free software; you can redistribute it and/or modify
+GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
-This program is distributed in the hope that it will be useful,
+GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
-along with this program; if not, write to the Free Software
+along with Wget; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
#include <config.h>
#endif /* HAVE_UNISTD_H */
#include <errno.h>
#include <assert.h>
-#include <ctype.h>
#include <sys/types.h>
#include "wget.h"
static struct hash_table *dl_file_url_map;
static struct hash_table *dl_url_file_map;
-/* List of HTML URLs. */
-static slist *urls_html;
+/* List of HTML files downloaded in this Wget run. Used for link
+ conversion after Wget is done. */
+static slist *downloaded_html_files;
/* List of undesirable-to-load URLs. */
static struct hash_table *undesirable_urls;
undesirable_urls = NULL;
free_vec (forbidden);
forbidden = NULL;
- slist_free (urls_html);
- urls_html = NULL;
+ slist_free (downloaded_html_files);
+ downloaded_html_files = NULL;
FREE_MAYBE (base_dir);
FREE_MAYBE (robots_host);
first_time = 1;
run. They should probably be at a different location. */
if (!undesirable_urls)
undesirable_urls = make_string_hash_table (0);
- if (!dl_file_url_map)
- dl_file_url_map = make_string_hash_table (0);
- if (!dl_url_file_map)
- dl_url_file_map = make_string_hash_table (0);
hash_table_clear (undesirable_urls);
string_set_add (undesirable_urls, this_url);
- hash_table_clear (dl_file_url_map);
- hash_table_clear (dl_url_file_map);
- urls_html = NULL;
/* Enter this_url to the hash table, in original and "enhanced" form. */
u = newurl ();
err = parseurl (this_url, u, 0);
if (err == URLOK)
{
string_set_add (undesirable_urls, u->url);
- hash_table_put (dl_file_url_map, xstrdup (file), xstrdup (u->url));
- hash_table_put (dl_url_file_map, xstrdup (u->url), xstrdup (file));
- urls_html = slist_prepend (urls_html, file);
if (opt.no_parent)
base_dir = xstrdup (u->dir); /* Set the base dir. */
/* Set the canonical this_url to be sent as referer. This
/* inl is set if the URL we are working on (constr) is stored in
undesirable_urls. Using it is crucial to avoid unnecessary
repeated continuous hits to the hash table. */
- inl = string_set_exists (undesirable_urls, constr);
+ inl = string_set_contains (undesirable_urls, constr);
/* If it is FTP, and FTP is not followed, chuck it out. */
if (!inl)
xfree (constr);
constr = newloc;
}
- /* In case of convert_links: If there was no error, add it to
- the list of downloaded URLs. We might need it for
- conversion. */
- if (opt.convert_links && filename)
- {
- if (dt & RETROKF)
- {
- hash_table_put (dl_file_url_map,
- xstrdup (filename), xstrdup (constr));
- hash_table_put (dl_url_file_map,
- xstrdup (constr), xstrdup (filename));
- /* If the URL is HTML, note it. */
- if (dt & TEXTHTML)
- urls_html = slist_prepend (urls_html, filename);
- }
- }
/* If there was no error, and the type is text/html, parse
it recursively. */
if (dt & TEXTHTML)
return RETROK;
}
\f
+void
+register_download (const char *url, const char *file)
+{
+ if (!opt.convert_links)
+ return;
+ if (!dl_file_url_map)
+ dl_file_url_map = make_string_hash_table (0);
+ hash_table_put (dl_file_url_map, xstrdup (file), xstrdup (url));
+ if (!dl_url_file_map)
+ dl_url_file_map = make_string_hash_table (0);
+ hash_table_put (dl_url_file_map, xstrdup (url), xstrdup (file));
+}
+
+void
+register_html (const char *url, const char *file)
+{
+ if (!opt.convert_links)
+ return;
+ downloaded_html_files = slist_prepend (downloaded_html_files, file);
+}
+
/* convert_links() is called from recursive_retrieve() after we're
done with an HTML file. This call to convert_links is not complete
because it converts only the downloaded files, and Wget cannot know
convert_all_links to go once more through the entire list of
retrieved HTMLs, and re-convert them.
- All the downloaded HTMLs are kept in urls_html, and downloaded URLs
+ All the downloaded HTMLs are kept in downloaded_html_files, and downloaded URLs
in urls_downloaded. From these two lists information is
extracted. */
void
{
slist *html;
- /* Destructively reverse urls_html to get it in the right order.
+ /* Destructively reverse downloaded_html_files to get it in the right order.
recursive_retrieve() used slist_prepend() consistently. */
- urls_html = slist_nreverse (urls_html);
+ downloaded_html_files = slist_nreverse (downloaded_html_files);
- for (html = urls_html; html; html = html->next)
+ for (html = downloaded_html_files; html; html = html->next)
{
urlpos *urls, *cur_url;
char *url;
char **entries;
char *line, *cmd, *str, *p;
char *base_version, *version;
- int len, num, i;
+ int num, i;
int wget_matched; /* is the part meant for Wget? */
entries = NULL;
return NULL;
/* Kill version number. */
- if (opt.useragent)
- {
- STRDUP_ALLOCA (base_version, opt.useragent);
- STRDUP_ALLOCA (version, opt.useragent);
- }
- else
- {
- int len = 10 + strlen (version_string);
- base_version = (char *)alloca (len);
- sprintf (base_version, "Wget/%s", version_string);
- version = (char *)alloca (len);
- sprintf (version, "Wget/%s", version_string);
- }
+ if (opt.useragent)
+ {
+ STRDUP_ALLOCA (base_version, opt.useragent);
+ STRDUP_ALLOCA (version, opt.useragent);
+ }
+ else
+ {
+ int len = 10 + strlen (version_string);
+ base_version = (char *)alloca (len);
+ sprintf (base_version, "Wget/%s", version_string);
+ version = (char *)alloca (len);
+ sprintf (version, "Wget/%s", version_string);
+ }
for (p = version; *p; p++)
*p = TOLOWER (*p);
for (p = base_version; *p && *p != '/'; p++)
wget_matched = 1;
while ((line = read_whole_line (fp)))
{
- len = strlen (line);
+ int len = strlen (line);
/* Destroy <CR><LF> if present. */
if (len && line[len - 1] == '\n')
line[--len] = '\0';
/* May the URL url be loaded according to disallowing rules stored in
forbidden? */
static int
-robots_match (struct urlinfo *u, char **forbidden)
+robots_match (struct urlinfo *u, char **fb)
{
int l;
- if (!forbidden)
+ if (!fb)
return 1;
DEBUGP (("Matching %s against: ", u->path));
- for (; *forbidden; forbidden++)
+ for (; *fb; fb++)
{
- DEBUGP (("%s ", *forbidden));
- l = strlen (*forbidden);
- /* If dir is forbidden, we may not load the file. */
- if (strncmp (u->path, *forbidden, l) == 0)
+ DEBUGP (("%s ", *fb));
+ l = strlen (*fb);
+ /* If dir is fb, we may not load the file. */
+ if (strncmp (u->path, *fb, l) == 0)
{
DEBUGP (("matched.\n"));
return 0; /* Matches, i.e. does not load... */
projects / wget / blobdiff