Ich möchte diesen Patch anwenden, also habe ich Code kopiert, der bei "Index: src / options.h" beginnt und mit "+ @ item" endet, und ihn in eine neue Datei eingefügt, die im wgetQuellcode-Ordner erstellt wurde. Dann habe ich:
$ patch -p0 < name_of_patch
(Patch is indented 1 space.)
patching file src/options.h
patch: **** malformed patch at line 6: char **excludes; /* List of excluded FTP directories. */
Wie soll ich das anwenden?
Dies ist der Inhalt der von mir erstellten Datei:
Index: src/options.h
===================================================================
--- src/options.h (revision 2276)
+++ src/options.h (working copy)
@@ -62,6 +62,8 @@
char **excludes; /* List of excluded FTP directories. */
char **includes; /* List of FTP directories to
follow. */
+ int maxsize; /* Maximum file size (kB) */
+ int minsize; /* Minimum file size (kB) */
bool ignore_case; /* Whether to ignore case when
matching dirs and files */
Index: src/init.c
===================================================================
--- src/init.c (revision 2276)
+++ src/init.c (working copy)
@@ -182,6 +182,8 @@
{ "loadcookies", &opt.cookies_input, cmd_file },
{ "logfile", &opt.lfilename, cmd_file },
{ "login", &opt.ftp_user, cmd_string },/* deprecated*/
+ { "maxsize", &opt.maxsize, cmd_number },
+ { "minsize", &opt.minsize, cmd_number },
{ "mirror", NULL, cmd_spec_mirror },
{ "netrc", &opt.netrc, cmd_boolean },
{ "noclobber", &opt.noclobber, cmd_boolean },
Index: src/http.c
===================================================================
--- src/http.c (revision 2276)
+++ src/http.c (working copy)
@@ -2252,7 +2252,7 @@
retried, and retried, and retried, and... */
uerr_t
http_loop (struct url *u, char **newloc, char **local_file, const char
*referer,
- int *dt, struct url *proxy)
+ int *dt, struct url *proxy, bool can_ommit)
{
int count;
bool got_head = false; /* used for time-stamping and filename
detection */
@@ -2285,6 +2285,27 @@
if (opt.ftp_glob && has_wildcards_p (u->path))
logputs (LOG_VERBOSE, _("Warning: wildcards not supported in HTTP.\n"));
+ /* Try fetching the document header and checking the document length */
+ if (can_ommit && !opt.spider && !opt.ignore_length &&
+ (opt.minsize > 0 || opt.maxsize > 0))
+ {
+ /* Setup hstat struct. */
+ xzero (hstat);
+ hstat.referer = referer;
+
+ *dt = HEAD_ONLY;
+ err = gethttp (u, &hstat, dt, proxy);
+
+ if (err == RETRFINISHED && hstat.contlen > 0 &&
+ (opt.minsize > 0 && hstat.contlen < opt.minsize * 1024 ||
+ opt.maxsize > 0 && hstat.contlen > opt.maxsize * 1024))
+ {
+ logputs (LOG_VERBOSE, _("File too small or too big -- not
retrieving.\n"));
+ ret = FILEBADFILE;
+ goto exit;
+ }
+ }
+
/* Setup hstat struct. */
xzero (hstat);
hstat.referer = referer;
@@ -2300,7 +2321,7 @@
/* Reset the document type. */
*dt = 0;
-
+
/* THE loop */
do
{
Index: src/http.h
===================================================================
--- src/http.h (revision 2276)
+++ src/http.h (working copy)
@@ -32,7 +32,7 @@
struct url;
uerr_t http_loop (struct url *, char **, char **, const char *, int *,
- struct url *);
+ struct url *, bool);
void save_cookies (void);
void http_cleanup (void);
time_t http_atotm (const char *);
Index: src/res.c
===================================================================
--- src/res.c (revision 2276)
+++ src/res.c (working copy)
@@ -545,7 +545,7 @@
*file = NULL;
opt.timestamping = false;
opt.spider = false;
- err = retrieve_url (robots_url, file, NULL, NULL, NULL, false);
+ err = retrieve_url (robots_url, file, NULL, NULL, NULL, false, false);
opt.timestamping = saved_ts_val;
opt.spider = saved_sp_val;
xfree (robots_url);
Index: src/retr.c
===================================================================
--- src/retr.c (revision 2276)
+++ src/retr.c (working copy)
@@ -601,7 +601,7 @@
uerr_t
retrieve_url (const char *origurl, char **file, char **newloc,
- const char *refurl, int *dt, bool recursive)
+ const char *refurl, int *dt, bool recursive, bool can_ommit)
{
uerr_t result;
char *url;
@@ -676,7 +676,7 @@
#endif
|| (proxy_url && proxy_url->scheme == SCHEME_HTTP))
{
- result = http_loop (u, &mynewloc, &local_file, refurl, dt, proxy_url);
+ result = http_loop (u, &mynewloc, &local_file, refurl, dt, proxy_url,
can_ommit);
}
else if (u->scheme == SCHEME_FTP)
{
@@ -856,7 +856,7 @@
opt.follow_ftp = old_follow_ftp;
}
else
- status = retrieve_url (cur_url->url->url, &filename, &new_file, NULL,
&dt, opt.recursive);
+ status = retrieve_url (cur_url->url->url, &filename, &new_file, NULL,
&dt, opt.recursive, false);
if (filename && opt.delete_after && file_exists_p (filename))
{
Index: src/retr.h
===================================================================
--- src/retr.h (revision 2276)
+++ src/retr.h (working copy)
@@ -49,7 +49,7 @@
char *fd_read_hunk (int, hunk_terminator_t, long, long);
char *fd_read_line (int);
-uerr_t retrieve_url (const char *, char **, char **, const char *, int *,
bool);
+uerr_t retrieve_url (const char *, char **, char **, const char *, int *,
bool, bool);
uerr_t retrieve_from_file (const char *, bool, int *);
const char *retr_rate (wgint, double);
Index: src/recur.c
===================================================================
--- src/recur.c (revision 2276)
+++ src/recur.c (working copy)
@@ -247,7 +247,7 @@
int dt = 0;
char *redirected = NULL;
- status = retrieve_url (url, &file, &redirected, referer, &dt, false);
+ status = retrieve_url (url, &file, &redirected, referer, &dt, false,
!html_allowed);
if (html_allowed && file && status == RETROK
&& (dt & RETROKF) && (dt & TEXTHTML))
Index: src/main.c
===================================================================
--- src/main.c (revision 2276)
+++ src/main.c (working copy)
@@ -189,6 +189,8 @@
{ "level", 'l', OPT_VALUE, "reclevel", -1 },
{ "limit-rate", 0, OPT_VALUE, "limitrate", -1 },
{ "load-cookies", 0, OPT_VALUE, "loadcookies", -1 },
+ { "max-size", 'M', OPT_VALUE, "maxsize", -1 },
+ { "min-size", 's', OPT_VALUE, "minsize", -1 },
{ "mirror", 'm', OPT_BOOLEAN, "mirror", -1 },
{ "no", 'n', OPT__NO, NULL, required_argument },
{ "no-clobber", 0, OPT_BOOLEAN, "noclobber", -1 },
@@ -446,6 +448,10 @@
N_("\
--limit-rate=RATE limit download rate to RATE.\n"),
N_("\
+ -M, --max-size=SIZE limit maximum file size to SIZE (kB).\n"),
+ N_("\
+ -s, --min-size=SIZE limit minimum file size to SIZE (kB).\n"),
+ N_("\
--no-dns-cache disable caching DNS lookups.\n"),
N_("\
--restrict-file-names=OS restrict chars in file names to ones OS
allows.\n"),
@@ -675,7 +681,6 @@
stdout);
exit (0);
}
-
#ifndef TESTING
int
main (int argc, char *const *argv)
@@ -979,7 +984,7 @@
opt.follow_ftp = old_follow_ftp;
}
else
- status = retrieve_url (*t, &filename, &redirected_URL, NULL, &dt,
opt.recursive);
+ status = retrieve_url (*t, &filename, &redirected_URL, NULL, &dt,
opt.recursive, false);
if (opt.delete_after && file_exists_p(filename))
{
Index: doc/wget.texi
===================================================================
--- doc/wget.texi (revision 2276)
+++ doc/wget.texi (working copy)
@@ -1592,7 +1592,7 @@
@item -l @var{depth}
@itemx --level=@var{depth}
Specify recursion maximum depth level @var{depth} (@pxref{Recursive
-Download}). The default maximum depth is 5.
+Download}). The default maximum depth is 5. Zero means infinite recursion.
@cindex proxy filling
@cindex delete after retrieval
@@ -1803,6 +1803,15 @@
Specify the domains that are @emph{not} to be followed.
(@pxref{Spanning Hosts}).
+@cindex file size range
+@item -s @var{size}
+@itemx --min-size=@var{size}
+Limit the minimum size of non-HTML files to @var{size} kB. Smaller files will
not be retrieved.
+
+@item -M @var{size}
+@itemx --max-size=@var{size}
+Limit the maximum size of non-HTML files to @var{size} kB. Larger files will
not be retrieved.
+
@cindex follow FTP links
@item --follow-ftp
Follow @sc{ftp} links from @sc{html} documents. Without this option,
@@ -3064,6 +3073,14 @@
too.
@item
+Retrieve in directory 'pics' all jpeg images from a given site, excluding
+files smaller than 50k (to avoid thumbnails) or larger than 400k.
+
+@example
+wget -Ppics -nd -r -l0 -Ajpg,jpeg -s50 -M400 http://www.server.com
+@end example
+
+@item
Suppose you were in the middle of downloading, when Wget was
interrupted. Now you do not want to clobber the files already present.
It would be:
Index: src/utils.c
===================================================================
--- src/utils.c (revision 2276)
+++ src/utils.c (working copy)
@@ -432,33 +432,52 @@
#endif
}
-/* stat file names named PREFIX.1, PREFIX.2, etc., until one that
- doesn't exist is found. Return a freshly allocated copy of the
- unused file name. */
+/*
+ * Stat file names named PREFIX-1.SUFFIX, PREFIX-2.SUFFIX, etc., until
+ * one that doesn't exist is found. Return a freshly allocated copy of
+ * the unused file name.
+ */
static char *
-unique_name_1 (const char *prefix)
+unique_name_1 (const char *s)
{
int count = 1;
- int plen = strlen (prefix);
- char *template = (char *)alloca (plen + 1 + 24);
- char *template_tail = template + plen;
+ int p, l = strlen (s);
+ char *prefix = (char *) alloca (l + 1);
+ char *suffix = (char *) alloca (l + 1);
+ char *filename = (char *) alloca (l + 26);
+
+ /* Look for last '.' in filename */
+
+ for(p = l; p >= 0 && s[p] != '.'; p--);
- memcpy (template, prefix, plen);
- *template_tail++ = '.';
+ /* If none found, then prefix is the whole filename */
+
+ if (p < 0)
+ p = l;
+ /* Extract prefix and (possibly empty) suffix from filename */
+
+ memcpy (prefix, s, p);
+ prefix[p] = '\0';
+
+ memcpy (suffix, s+p, l-p);
+ suffix[l-p] = '\0';
+
+ /* Try indexed filenames until an unused one is found */
+
do
- number_to_string (template_tail, count++);
- while (file_exists_p (template));
+ sprintf (filename, "%s-%d%s", prefix, count++, suffix);
+ while (file_exists_p (filename));
- return xstrdup (template);
+ return xstrdup (filename);
}
/* Return a unique file name, based on FILE.
- More precisely, if FILE doesn't exist, it is returned unmodified.
- If not, FILE.1 is tried, then FILE.2, etc. The first FILE.<number>
- file name that doesn't exist is returned.
+ More precisely, if FILE.SUF doesn't exist, it is returned unmodified.
+ If not, FILE-1.SUF is tried, then FILE-2.SUF etc. The first
+ FILE-<number>.SUF file name that doesn't exist is returned.
The resulting file is not created, only verified that it didn't
exist at the point in time when the function was called.
Index: doc/wget.texi
===================================================================
--- doc/wget.texi (revision 2276)
+++ doc/wget.texi (working copy)
@@ -561,16 +561,16 @@
cases, the local file will be @dfn{clobbered}, or overwritten, upon
repeated download. In other cases it will be preserved.
-When running Wget without @samp{-N}, @samp{-nc}, or @samp{-r},
-downloading the same file in the same directory will result in the
-original copy of @var{file} being preserved and the second copy being
-named @samp{@var{file}.1}. If that file is downloaded yet again, the
-third copy will be named @samp{@var{file}.2}, and so on. When
-@samp{-nc} is specified, this behavior is suppressed, and Wget will
-refuse to download newer copies of @samp{@var{file}}. Therefore,
-``@code{no-clobber}'' is actually a misnomer in this mode---it's not
-clobbering that's prevented (as the numeric suffixes were already
-preventing clobbering), but rather the multiple version saving that's
+When running Wget without @samp{-N}, @samp{-nc}, or @samp{-r}, downloading the
+same file in the same directory will result in the original copy of @var{file}
+being preserved and the second copy being named
+@samp{@var{prefix}-1.@var{suffix}}, assuming @var{file} = @var{prefix.suffix}.
+If that file is downloaded yet again, the third copy will be named
+@samp{@var{prefix}-2.@var{suffix}}, and so on. When @samp{-nc} is specified,
+this behavior is suppressed, and Wget will refuse to download newer copies of
+@samp{@var{file}}. Therefore, ``@code{no-clobber}'' is actually a misnomer in
+this mode---it's not clobbering that's prevented (as the numeric suffixes were
+already preventing clobbering), but rather the multiple version saving that's
prevented.
When running Wget with @samp{-r}, but without @samp{-N} or @samp{-nc},
@@ -1592,7 +1592,7 @@
@item -l @var{depth}
@itemx --level=@var{depth}
Specify recursion maximum depth level @var{depth} (@pxref{Recursive
-Download}). The default maximum depth is 5.
+Download}). The default maximum depth is 5. Zero means infinite recursion.
@cindex proxy filling
@cindex delete after retrieval
@@ -1803,6 +1803,15 @@
Specify the domains that are @emph{not} to be followed.
(@pxref{Spanning Hosts}).
+@cindex file size range
+@item -s @var{size}
+@itemx --min-size=@var{size}
+Limit the minimum size of non-HTML files to @var{size} kB. Smaller files will
not be retrieved.
+
+@item -M @var{size}
+@itemx --max-size=@var{size}
+Limit the maximum size of non-HTML files to @var{size} kB. Larger files will
not be retrieved.
+
@cindex follow FTP links
@item --follow-ftp
Follow @sc{ftp} links from @sc{html} documents. Without this option,
@@ -3064,6 +3073,14 @@
too.
@item
+Retrieve in directory 'pics' all jpeg images from a given site, excluding
+files smaller than 50k (to avoid thumbnails) or larger than 400k.
+
+@example
+wget -Ppics -nd -r -l0 -Ajpg,jpeg -s50 -M400 http://www.server.com
+@end example
+
+@item
Antworten:
Dies ist ein häufiges Problem bei Unterschieden, die ohne Leerzeicheneinzug in eine Textdatei kopiert / eingefügt werden. Sie müssen vor jeder Zeile Leerzeichen einfügen, mit Ausnahme von Zeilen, die mit den Symbolen "+", "-" und "@@" beginnen. Um dieses Problem zu vermeiden, ist es besser, die Diff-Dateien selbst von Hand zu generieren (mit
diffoder einem Diff-Tool zur Versionskontrolle) und dann die Diff-Datei als Ganzes herunterzuladen, anstatt sie von Ihrem Browser zu kopieren und einzufügen.Ich würde vorschlagen, dass Sie vor dem Anwenden des Patches prüfen, ob der Patch Upstream erstellt hat und in einer neueren / neuesten / stabilen Version verfügbar ist, wodurch Ihr Problem auf saubere Weise gelöst wird. Selbst wenn Sie die
.cDatei patchen , werden Sie sie trotzdem kompilieren. Warum also nicht mit einem frischen stabilen Tarball, wenn der Patch in den Upstream umgewandelt wurde?quelle
Ich stimme Nikhils allgemeinen Kommentaren zu. Ich möchte jedoch nur darauf hinweisen, dass es im Allgemeinen besser ist, die HTML-Datei herunterzuladen und dann in Text zu konvertieren, als sie auszuschneiden und einzufügen. Zum Beispiel können Sie tun
1) wget -c http://osdir.com/ml/web.wget.patches/2007-07/msg00011.html
2) Öffnen Sie msg00011.html beispielsweise mit Openoffice. und als Text speichern. Der OO-Konverter macht einen guten Job, und ich habe keine offensichtlichen Probleme mit den konvertierten Patches gesehen.
quelle