diff options
Diffstat (limited to 'man')
| -rw-r--r-- | man/Makefile.in | 1 | ||||
| -rw-r--r-- | man/httrack.1 | 59 |
2 files changed, 52 insertions, 8 deletions
diff --git a/man/Makefile.in b/man/Makefile.in index 18a5607..bf39c78 100644 --- a/man/Makefile.in +++ b/man/Makefile.in @@ -69,6 +69,7 @@ INSTALL_SCRIPT = @INSTALL_SCRIPT@ INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ LDFLAGS = @LDFLAGS@ LFS_FLAG = @LFS_FLAG@ +LIBOBJS = @LIBOBJS@ LIBS = @LIBS@ LIBTOOL = @LIBTOOL@ LN_S = @LN_S@ diff --git a/man/httrack.1 b/man/httrack.1 index db3d75b..7b06722 100644 --- a/man/httrack.1 +++ b/man/httrack.1 @@ -1,7 +1,7 @@ .\" Process this file with .\" groff -man -Tascii httrack.1 .\" -.TH httrack 1 "HTTrack version 3.30-RC-19+swf (compiled Oct 4 2003)" "httrack website copier" +.TH httrack 1 "May 2005" "httrack website copier" .SH NAME httrack \- offline browser : copy websites to a local directory .SH SYNOPSIS @@ -62,7 +62,7 @@ httrack \- offline browser : copy websites to a local directory ] [ .B -NN, --structure[=N] ] [ -.B -%M, --mime-html[=N] +.B -%M, --mime-html ] [ .B -LN, --long-names[=N] ] [ @@ -104,6 +104,10 @@ httrack \- offline browser : copy websites to a local directory ] [ .B -F, --user-agent ] [ +.B -%R, --referer +] [ +.B -%E, --from +] [ .B -%F, --footer ] [ .B -%l, --language @@ -156,6 +160,8 @@ httrack \- offline browser : copy websites to a local directory ] [ .B -%H, --debug-headers ] [ +.B -%!, --disable-security-limits +] [ .B -V, --userdef-cmd ] [ .B -%U, --user @@ -173,7 +179,7 @@ allows you to download a World Wide Web site from the Internet to a local direct .B httrack www.someweb.com/bob/ mirror site www.someweb.com/bob/ and only this site .TP -.B httrack www.someweb.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg +.B httrack www.someweb.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg -mime:application/* mirror the two sites together (with shared links) and accept any .jpg files on .com sites .TP .B httrack www.someweb.com/bob/bobby.html +* -r6 @@ -268,8 +274,10 @@ test all URLs (even forbidden ones) (--test) structure type (0 *original structure, 1+: see below) (--structure[=N]) .IP -or user defined structure (-N "%h%p/%n%q.%t") +.IP -%N +delayed type check, don t make any link test but wait for files download to start instead (experimental) (%N0 don t use, %N1 use for unknown extensions, * %N2 always use) .IP -%M -generate a RFC MIME-encapsulated full-archive (.mht) (--mime-html[=N]) +generate a RFC MIME-encapsulated full-archive (.mht) (--mime-html) .IP -LN long names (L1 *long names / L0 8-3 conversion / L2 ISO9660 compatible) (--long-names[=N]) .IP -KN @@ -295,7 +303,7 @@ check document type if unknown (cgi,asp..) (u0 don t check, * u1 check but /, u2 .IP -j *parse Java Classes (j0 don t parse) (--parse-java[=N]) .IP -sN -follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always) (--robots[=N]) +follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always, 3=always (even strict rules)) (--robots[=N]) .IP -%h force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (--http-10) .IP -%k @@ -308,12 +316,18 @@ update hacks: various hacks to limit re-transfers when updating (identical size, url hacks: various hacks to limit duplicate URLs (strip //, www.foo.com==foo.com..) (--urlhack) .IP -%A assume that a type (cgi,asp..) is always linked with a mime type (-%A php3,cgi=text/html;dat,bin=application/x-zip) (--assume <param>) +.IP -can +also be used to force a specific file type: --assume foo.cgi=text/html .IP -@iN internet protocol (0=both ipv6+ipv4, 4=ipv4 only, 6=ipv6 only) (--protocol[=N]) .SS Browser ID: .IP -F -user-agent field (-F "user-agent name") (--user-agent <param>) +user-agent field sent in HTTP headers (-F "user-agent name") (--user-agent <param>) +.IP -%R +default referer field sent in HTTP headers (--referer <param>) +.IP -%E +from email address sent in HTTP headers (--from <param>) .IP -%F footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]" (--footer <param>) .IP -%l @@ -327,7 +341,7 @@ store all files in cache (not useful if files on disk) (--store-all-in-cache) .IP -%n do not re-download locally erased files (--do-not-recatch) .IP -%v -display on screen filenames downloaded (in realtime) - * %v1 short version (--display) +display on screen filenames downloaded (in realtime) - * %v1 short version - %v2 full animation (--display) .IP -Q no log - quiet mode (--do-not-log) .IP -q @@ -386,8 +400,18 @@ debug HTTP headers in logfile (--debug-headers) *use optimized engine (limited memory boundary checks) (--fast-engine) .IP -#0 filter test (-#0 *.gif www.bar.com/foo.gif ) (--debug-testfilters <param>) +.IP -#1 +simplify test (-#1 ./foo/bar/../foobar) +.IP -#2 +type test (-#2 /foo/bar.php) .IP -#C cache list (-#C *.com/spider*.gif (--debug-cache <param>) +.IP -#R +cache repair (damaged cache) (--debug-oldftp) +.IP -#d +debug parser (--debug-parsing) +.IP -#E +extract new.zip cache meta-data in meta.zip .IP -#f always flush log files (--advanced-flushlogs) .IP -#FN @@ -413,13 +437,21 @@ generate transfer rate statictics every minutes (--debug-ratestats) .IP -#! execute a shell command (-#! "echo hello") (--exec <param>) +.SS Dangerous options: (do NOT use unless you exactly know what you are doing) +.IP -%! +bypass built-in security limits aimed to avoid bandwith abuses (bandwidth, simultaneous connections) (--disable-security-limits) +.IP -IMPORTANT +NOTE: DANGEROUS OPTION, ONLY SUITABLE FOR EXPERTS +.IP -USE +IT WITH EXTREME CARE + .SS Command-line specific options: .IP -V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd <param>) .IP -%U run the engine with another id when called as root (-%U smith) (--user <param>) .IP -%W -use an external library function as a wrapper (-%W link-detected=foo.so:myfunction) (--callback <param>) +use an external library function as a wrapper (-%W link-detected=foo.so:myfunction[,myparameters]) (--callback <param>) .SS Details: Option N .IP -N0 @@ -470,6 +502,7 @@ Identical to N99 exept that there is no "web" directory %h Host name (ex: www.someweb.com) %M URL MD5 (128 bits, 32 ascii bytes) %Q query string MD5 (128 bits, 32 ascii bytes) + %r protocol name (ex: http) %q small query string MD5 (16 bits, 4 ascii bytes) %s? Short name version (ex: %sN) %[param] param variable in query string @@ -535,6 +568,12 @@ foo.cgi?q=45 -> foo4B54.html?q=45 (relative URI, default) .SS start : int (* myfunction)(httrackp* opt); .SS end : int (* myfunction)(void); .SS change-options : int (* myfunction)(httrackp* opt); +.SS preprocess-html : int (* myfunction)(char** html,int* len,char* url +adresse,char* url +fichier); +.SS postprocess-html : int (* myfunction)(char** html,int* len,char* url +adresse,char* url +fichier); .SS check-html : int (* myfunction)(char* html,int len,char* url adresse,char* url fichier); @@ -554,6 +593,8 @@ struct* stats); .SS pause : void (* myfunction)(char* lockfile); .SS save-file : void (* myfunction)(char* file); .SS link-detected : int (* myfunction)(char* link); +.SS link-detected2 : int (* myfunction)(char* link, char* start +tag); .SS transfer-status : int (* myfunction)(lien back* back); .SS save-name : int (* myfunction)(char* adr @@ -561,6 +602,8 @@ complete,char* fil complete,char* referer adr,char* referer fil,char* save); +.SS And <wrappername> +init() functions if defined, called upon plug .SH FILES .I /etc/httrack.conf .RS |