Gecko [ www.utparral.edu.mx ]

Name	Size	Permission
ab	51.43 KB	-rwxr-xr-x
annotate	10.2 KB	-rwxr-xr-x
apachectl	3.33 KB	-rwxr-xr-x
apr-1-config	6.84 KB	-rwxr-xr-x
apreq2-config	5.96 KB	-rwxr-xr-x
apu-1-config	6.42 KB	-rwxr-xr-x
apxs	23.3 KB	-rwxr-xr-x
aria_chk	4.56 MB	-rwxr-xr-x
aria_dump_log	4.35 MB	-rwxr-xr-x
aria_ftdump	4.37 MB	-rwxr-xr-x
aria_pack	4.4 MB	-rwxr-xr-x
aria_read_log	4.51 MB	-rwxr-xr-x
autopoint	25.97 KB	-rwxr-xr-x
bdftogd	3.91 KB	-rwxr-xr-x
bison	288.55 KB	-rwxr-xr-x
bmp2tiff	14.32 KB	-rwxr-xr-x
bsqldb	26.76 KB	-rwxr-xr-x
bunzip2	85.55 KB	-rwxr-xr-x
bzcat	85.55 KB	-rwxr-xr-x
bzcmp	2.08 KB	-rwxr-xr-x
bzdiff	2.08 KB	-rwxr-xr-x
bzegrep	1.64 KB	-rwxr-xr-x
bzfgrep	1.64 KB	-rwxr-xr-x
bzgrep	1.64 KB	-rwxr-xr-x
bzip2	85.55 KB	-rwxr-xr-x
bzip2recover	14.23 KB	-rwxr-xr-x
bzless	1.23 KB	-rwxr-xr-x
bzmore	1.23 KB	-rwxr-xr-x
captoinfo	66.7 KB	-rwxr-xr-x
checkgid	6.13 KB	-rwxr-xr-x
cjpeg	30.29 KB	-rwxr-xr-x
clear	6.12 KB	-rwxr-xr-x
corelist	15.03 KB	-rwxr-xr-x
cpan	8.18 KB	-rwxr-xr-x
crc32	715 B	-r-xr-xr-x
c_rehash	6.57 KB	-rwxr-xr-x
curl	174.83 KB	-rwxr-xr-x
curl-config	5.48 KB	-rwxr-xr-x
cwebp	50.9 KB	-rwxr-xr-x
datacopy	22.45 KB	-rwxr-xr-x
dbilogstrip	1.44 KB	-r-xr-xr-x
dbiprof	6.17 KB	-r-xr-xr-x
dbiproxy	5.37 KB	-r-xr-xr-x
dbl2png	14.3 KB	-rwxr-xr-x
dbmmanage	8.72 KB	-rwxr-xr-x
defncopy	18.76 KB	-rwxr-xr-x
derb	23.09 KB	-rwxr-xr-x
djpeg	26.27 KB	-rwxr-xr-x
dwebp	30.49 KB	-rwxr-xr-x
enc2xs	40.79 KB	-rwxr-xr-x
encguess	3.02 KB	-rwxr-xr-x
envsubst	34.55 KB	-rwxr-xr-x
envvars	1.03 KB	-rw-r--r--
envvars-std	1.03 KB	-rw-r--r--
fax2ps	18.52 KB	-rwxr-xr-x
fax2tiff	14.66 KB	-rwxr-xr-x
fcgistarter	10.27 KB	-rwxr-xr-x
fisql	26.91 KB	-rwxr-xr-x
fix_rights	956 B	-rwxr-xr-x
flex	353.36 KB	-rwxr-xr-x
flex++	353.36 KB	-rwxr-xr-x
freebcp	18.59 KB	-rwxr-xr-x
freetype-config	3.75 KB	-rwxr-xr-x
ftpasswd	33.94 KB	-rwxr-xr-x
ftpcount	15.67 KB	-rwxr-xr-x
ftpdctl	82.73 KB	-rwxr-xr-x
ftpmail	13.69 KB	-rwxr-xr-x
ftpquota	32.21 KB	-rwxr-xr-x
ftptop	23.52 KB	-rwxr-xr-x
ftpwho	47.84 KB	-rwxr-xr-x
gd2copypal	10.15 KB	-rwxr-xr-x
gd2togif	10.14 KB	-rwxr-xr-x
gd2topng	10.16 KB	-rwxr-xr-x
gdcmpgif	10.15 KB	-rwxr-xr-x
gdparttopng	10.16 KB	-rwxr-xr-x
gdtopng	10.14 KB	-rwxr-xr-x
genbrk	14.84 KB	-rwxr-xr-x
gencfu	10.74 KB	-rwxr-xr-x
gencnval	22.73 KB	-rwxr-xr-x
gendict	22.91 KB	-rwxr-xr-x
gen_php_doc.sh	240 B	-rwxr-xr-x
genrb	161.05 KB	-rwxr-xr-x
GET	14.34 KB	-r-xr-xr-x
gettext	34.53 KB	-rwxr-xr-x
gettextize	42.73 KB	-rwxr-xr-x
gettext.sh	4.52 KB	-rwxr-xr-x
gif2tiff	14.48 KB	-rwxr-xr-x
giftogd2	10.15 KB	-rwxr-xr-x
h2ph	28.55 KB	-rwxr-xr-x
h2xs	59.52 KB	-rwxr-xr-x
HEAD	14.34 KB	-r-xr-xr-x
htcacheclean	30.53 KB	-rwxr-xr-x
htdbm	18.47 KB	-rwxr-xr-x
htdigest	10.27 KB	-rwxr-xr-x
html_template_phplibtool	107 B	-rwxr-xr-x
htpasswd	18.41 KB	-rwxr-xr-x
httpd	696.97 KB	-rwxr-xr-x
httxt2dbm	10.23 KB	-rwxr-xr-x
iconv	26.38 KB	-rwxr-xr-x
icu-config	21.58 KB	-rwxr-xr-x
icuinfo	10.54 KB	-rwxr-xr-x
infocmp	58.65 KB	-rwxr-xr-x
infotocap	66.7 KB	-rwxr-xr-x
innochecksum	3.62 MB	-rwxr-xr-x
instmodsh	4.16 KB	-r-xr-xr-x
jpegtran	42.36 KB	-rwxr-xr-x
json_pp	4.89 KB	-rwxr-xr-x
ldapadd	67.11 KB	-rwxr-xr-x
ldapcompare	55 KB	-rwxr-xr-x
ldapdelete	59.09 KB	-rwxr-xr-x
ldapexop	55.06 KB	-rwxr-xr-x
ldapmodify	67.11 KB	-rwxr-xr-x
ldapmodrdn	55 KB	-rwxr-xr-x
ldappasswd	55.03 KB	-rwxr-xr-x
ldapsearch	79.36 KB	-rwxr-xr-x
ldapurl	18.34 KB	-rwxr-xr-x
ldapwhoami	55.02 KB	-rwxr-xr-x
libmcrypt-config	1.43 KB	-rwxr-xr-x
libnetcfg	15.42 KB	-rwxr-xr-x
libpng16-config	2.27 KB	-rwxr-xr-x
libpng-config	2.27 KB	-rwxr-xr-x
listaction	170.55 KB	-rwxr-xr-x
listaction_d	170.54 KB	-rwxr-xr-x
listfdb	14.17 KB	-rwxr-xr-x
listjpeg	6.13 KB	-rwxr-xr-x
listmp3	10.54 KB	-rwxr-xr-x
listswf	174.55 KB	-rwxr-xr-x
listswf_d	174.54 KB	-rwxr-xr-x
logresolve	10.34 KB	-rwxr-xr-x
lwp-download	8.34 KB	-r-xr-xr-x
lwp-mirror	2.45 KB	-r-xr-xr-x
lwp-request	14.34 KB	-r-xr-xr-x
lwp-rget	14.78 KB	-r-xr-xr-x
makeconv	55.35 KB	-rwxr-xr-x
makefdb	70.41 KB	-rwxr-xr-x
makeswf	23.2 KB	-rwxr-xr-x
mariabackup	22.87 MB	-rwxr-xr-x
mariadb	4.28 MB	-rwxr-xr-x
mariadb-access	109.37 KB	-rwxr-xr-x
mariadb-admin	3.83 MB	-rwxr-xr-x
mariadb-backup	22.87 MB	-rwxr-xr-x
mariadb-binlog	4.05 MB	-rwxr-xr-x
mariadb-check	3.83 MB	-rwxr-xr-x
mariadb-client-test	4.38 MB	-rwxr-xr-x
mariadb_config	10.52 KB	-rwxr-xr-x
mariadb-convert-table-format	4.12 KB	-rwxr-xr-x
mariadbd-multi	26.76 KB	-rwxr-xr-x
mariadbd-safe	30.43 KB	-rwxr-xr-x
mariadbd-safe-helper	3.49 MB	-rwxr-xr-x
mariadb-dump	3.92 MB	-rwxr-xr-x
mariadb-dumpslow	8.05 KB	-rwxr-xr-x
mariadb-find-rows	3.21 KB	-rwxr-xr-x
mariadb-fix-extensions	1.22 KB	-rwxr-xr-x
mariadb-hotcopy	34.14 KB	-rwxr-xr-x
mariadb-import	3.82 MB	-rwxr-xr-x
mariadb-install-db	21.48 KB	-rwxr-xr-x
mariadb-ldb	4.05 MB	-rwxr-xr-x
mariadb-plugin	3.53 MB	-rwxr-xr-x
mariadb-secure-installation	13.38 KB	-rwxr-xr-x
mariadb-setpermission	17.13 KB	-rwxr-xr-x
mariadb-show	3.82 MB	-rwxr-xr-x
mariadb-slap	3.84 MB	-rwxr-xr-x
mariadb-test	4.21 MB	-rwxr-xr-x
mariadb-tzinfo-to-sql	3.53 MB	-rwxr-xr-x
mariadb-upgrade	3.62 MB	-rwxr-xr-x
mariadb-waitpid	3.52 MB	-rwxr-xr-x
mbstream	3.55 MB	-rwxr-xr-x
ming-config	561 B	-rwxr-xr-x
mp2bug	1.16 KB	-r-xr-xr-x
msgattrib	22.39 KB	-rwxr-xr-x
msgcat	18.38 KB	-rwxr-xr-x
msgcmp	22.49 KB	-rwxr-xr-x
msgcomm	18.37 KB	-rwxr-xr-x
msgconv	18.35 KB	-rwxr-xr-x
msgen	18.35 KB	-rwxr-xr-x
msgexec	14.38 KB	-rwxr-xr-x
msgfilter	26.45 KB	-rwxr-xr-x
msgfmt	79.41 KB	-rwxr-xr-x
msggrep	46.73 KB	-rwxr-xr-x
msginit	43.15 KB	-rwxr-xr-x
msgmerge	51.37 KB	-rwxr-xr-x
msgunfmt	30.57 KB	-rwxr-xr-x
msguniq	18.36 KB	-rwxr-xr-x
msql2mysql	1.42 KB	-rwxr-xr-x
myisamchk	4 MB	-rwxr-xr-x
myisam_ftdump	3.88 MB	-rwxr-xr-x
myisamlog	3.86 MB	-rwxr-xr-x
myisampack	3.91 MB	-rwxr-xr-x
my_print_defaults	3.53 MB	-rwxr-xr-x
myrocks_hotbackup	24.46 KB	-rwxr-xr-x
mysql	4.28 MB	-rwxr-xr-x
mysqlaccess	109.37 KB	-rwxr-xr-x
mysqladmin	3.83 MB	-rwxr-xr-x
mysqlbinlog	4.05 MB	-rwxr-xr-x
mysqlcheck	3.83 MB	-rwxr-xr-x
mysql_client_test	4.38 MB	-rwxr-xr-x
mysql_config	4.54 KB	-rwxr-xr-x
mysql_convert_table_format	4.12 KB	-rwxr-xr-x
mysqld_multi	26.76 KB	-rwxr-xr-x
mysqld_safe	30.43 KB	-rwxr-xr-x
mysqld_safe_helper	3.49 MB	-rwxr-xr-x
mysqldump	3.92 MB	-rwxr-xr-x
mysqldumpslow	8.05 KB	-rwxr-xr-x
mysql_find_rows	3.21 KB	-rwxr-xr-x
mysql_fix_extensions	1.22 KB	-rwxr-xr-x
mysqlhotcopy	34.14 KB	-rwxr-xr-x
mysqlimport	3.82 MB	-rwxr-xr-x
mysql_install_db	21.48 KB	-rwxr-xr-x
mysql_ldb	4.05 MB	-rwxr-xr-x
mysql_plugin	3.53 MB	-rwxr-xr-x
mysql_secure_installation	13.38 KB	-rwxr-xr-x
mysql.server	11.93 KB	-rwxr-xr-x
mysql_setpermission	17.13 KB	-rwxr-xr-x
mysqlshow	3.82 MB	-rwxr-xr-x
mysqlslap	3.84 MB	-rwxr-xr-x
mysqltest	4.21 MB	-rwxr-xr-x
mysql_tzinfo_to_sql	3.53 MB	-rwxr-xr-x
mysql_upgrade	3.62 MB	-rwxr-xr-x
mysql_waitpid	3.52 MB	-rwxr-xr-x
mytop	61.06 KB	-rwxr-xr-x
ncurses5-config	5.17 KB	-rwxr-xr-x
ngettext	34.55 KB	-rwxr-xr-x
onig-config	1.35 KB	-rwxr-xr-x
openssl	642.05 KB	-rwxr-xr-x
osql	8.84 KB	-rwxr-xr-x
pal2rgb	14.82 KB	-rwxr-xr-x
pcre-config	2.31 KB	-rwxr-xr-x
pcregrep	36.34 KB	-rwxr-xr-x
pcretest	66.56 KB	-rwxr-xr-x
pear	817 B	-rwxr-xr-x
peardev	838 B	-rwxr-xr-x
pearinfo	538 B	-rwxr-xr-x
pecl	751 B	-rwxr-xr-x
perl	3.3 MB	-rwxr-xr-x
perl5.34.1	3.3 MB	-rwxr-xr-x
perlbug	44.13 KB	-rwxr-xr-x
perldoc	274 B	-rwxr-xr-x
perlivp	10.58 KB	-rwxr-xr-x
perlthanks	44.13 KB	-rwxr-xr-x
perror	3.71 MB	-rwxr-xr-x
phar	14.89 KB	-rwxr-xr-x
phar.phar	14.89 KB	-rwxr-xr-x
php	18.06 MB	-rwxr-xr-x
php-8.2.12	18.06 MB	-rwxr-xr-x
php-cgi	18.06 MB	-rwxr-xr-x
php-cgi-8.2.12	18.06 MB	-rwxr-xr-x
php-config	4.39 KB	-rwxr-xr-x
php-config-8.2.12	4.39 KB	-rwxr-xr-x
phpdbg	18.06 MB	-rwxr-xr-x
phpize	4.43 KB	-rwxr-xr-x
phpize-8.2.12	4.43 KB	-rwxr-xr-x
phpunit	1.9 KB	-rwxr-xr-x
piconv	8.18 KB	-rwxr-xr-x
pkgdata	43.7 KB	-rwxr-xr-x
pl2pm	4.44 KB	-rwxr-xr-x
png2dbl	14.38 KB	-rwxr-xr-x
pngfix	46.48 KB	-rwxr-xr-x
png-fix-itxt	6.11 KB	-rwxr-xr-x
pngtogd	10.14 KB	-rwxr-xr-x
pngtogd2	10.15 KB	-rwxr-xr-x
pod2html	4.05 KB	-rwxr-xr-x
pod2man	14.69 KB	-rwxr-xr-x
pod2text	10.56 KB	-rwxr-xr-x
pod2usage	4.02 KB	-rwxr-xr-x
podchecker	3.58 KB	-rwxr-xr-x
POST	14.34 KB	-r-xr-xr-x
ppm2tiff	14.51 KB	-rwxr-xr-x
prove	13.35 KB	-rwxr-xr-x
prxs	8.96 KB	-rwxr-xr-x
ptar	3.49 KB	-rwxr-xr-x
ptardiff	2.59 KB	-rwxr-xr-x
ptargrep	4.3 KB	-rwxr-xr-x
ras2tiff	10.48 KB	-rwxr-xr-x
raw2adpcm	10.21 KB	-rwxr-xr-x
raw2tiff	18.35 KB	-rwxr-xr-x
rdjpgcom	10.18 KB	-rwxr-xr-x
recode-sr-latin	14.33 KB	-rwxr-xr-x
replace	3.5 MB	-rwxr-xr-x
reset	18.59 KB	-rwxr-xr-x
resolveip	3.52 MB	-rwxr-xr-x
resolve_stack_dump	3.53 MB	-rwxr-xr-x
rgb2ycbcr	14.46 KB	-rwxr-xr-x
rotatelogs	18.41 KB	-rwxr-xr-x
sabcmd	21.13 KB	-rwxr-xr-x
sablot-config	1.11 KB	-rwxr-xr-x
shasum	9.76 KB	-rwxr-xr-x
splain	18.97 KB	-rwxr-xr-x
sqlite	27.8 KB	-rwxr-xr-x
sqlite3	1.74 MB	-rwxr-xr-x
sst_dump	4.04 MB	-rwxr-xr-x
streamzip	5.31 KB	-r-xr-xr-x
suexec	14.36 KB	-rwsr-xr-x
swftocxx	154.57 KB	-rwxr-xr-x
swftoperl	154.57 KB	-rwxr-xr-x
swftophp	154.57 KB	-rwxr-xr-x
swftopython	154.57 KB	-rwxr-xr-x
swftotcl	154.57 KB	-rwxr-xr-x
tabs	14.31 KB	-rwxr-xr-x
tdspool	286.9 KB	-rwxr-xr-x
thumbnail	14.92 KB	-rwxr-xr-x
tic	66.7 KB	-rwxr-xr-x
tiff2bw	14.8 KB	-rwxr-xr-x
tiff2pdf	66.52 KB	-rwxr-xr-x
tiff2ps	55.95 KB	-rwxr-xr-x
tiff2rgba	14.32 KB	-rwxr-xr-x
tiffcmp	18.41 KB	-rwxr-xr-x
tiffcp	43.31 KB	-rwxr-xr-x
tiffcrop	112.88 KB	-rwxr-xr-x
tiffdither	14.48 KB	-rwxr-xr-x
tiffdump	18.52 KB	-rwxr-xr-x
tiffinfo	18.55 KB	-rwxr-xr-x
tiffmedian	22.44 KB	-rwxr-xr-x
tiffset	10.23 KB	-rwxr-xr-x
tiffsplit	14.3 KB	-rwxr-xr-x
toe	14.38 KB	-rwxr-xr-x
tput	14.41 KB	-rwxr-xr-x
tset	18.59 KB	-rwxr-xr-x
tsql	282.99 KB	-rwxr-xr-x
uconv	47.36 KB	-rwxr-xr-x
unzip-mem	14.21 KB	-rwxr-xr-x
unzzip	10.21 KB	-rwxr-xr-x
unzzipcat	10.2 KB	-rwxr-xr-x
unzzipcat-mem	10.17 KB	-rwxr-xr-x
unzzipcat-seeko	10.2 KB	-rwxr-xr-x
unzzipdir	6.16 KB	-rwxr-xr-x
unzzipdir-mem	6.13 KB	-rwxr-xr-x
use-devel-checklib	2.81 KB	-r-xr-xr-x
wcmgr	6.1 KB	-rwxr-xr-x
webalizer	157.1 KB	-rwxr-xr-x
webazolver	157.1 KB	-rwxr-xr-x
webpng	14.28 KB	-rwxr-xr-x
wrjpgcom	10.19 KB	-rwxr-xr-x
wsrep_sst_backup	2.95 KB	-rwxr-xr-x
wsrep_sst_common	54.05 KB	-rw-r--r--
wsrep_sst_mariabackup	51.01 KB	-rwxr-xr-x
wsrep_sst_mysqldump	7.7 KB	-rwxr-xr-x
wsrep_sst_rsync	32.31 KB	-rwxr-xr-x
wsrep_sst_rsync_wan	32.31 KB	-rwxr-xr-x
xgettext	330.1 KB	-rwxr-xr-x
xml2-config	1.69 KB	-rwxr-xr-x
xmlcatalog	14.35 KB	-rwxr-xr-x
xmllint	64.38 KB	-rwxr-xr-x
xmlwf	26.57 KB	-rwxr-xr-x
xslt-config	2.36 KB	-rwxr-xr-x
xsltproc	22.52 KB	-rwxr-xr-x
xsubpp	5.06 KB	-rwxr-xr-x
yacc	45 B	-rwxr-xr-x
zipcmp	19 KB	-rwxr-xr-x
zipdetails	49.95 KB	-r-xr-xr-x
zipmerge	14.88 KB	-rwxr-xr-x
ziptool	27.7 KB	-rwxr-xr-x
zzcat	6.13 KB	-rwxr-xr-x
zzdir	10.16 KB	-rwxr-xr-x
zzxorcat	10.16 KB	-rwxr-xr-x
zzxorcopy	10.17 KB	-rwxr-xr-x
zzxordir	10.19 KB	-rwxr-xr-x

Code Editor : lwp-rget

#!/opt/lampp/bin/perl -w

eval 'exec /opt/lampp/bin/perl -w -S $0 ${1+"$@"}'
    if 0; # not running under some shell

=head1 NAME

lwp-rget - Retrieve web documents recursively

=head1 SYNOPSIS

lwp-rget [--verbose] [--auth=USER:PASS] [--depth=N] [--hier] [--iis]
	  [--keepext=mime/type[,mime/type]] [--limit=N] [--nospace]
	  [--prefix=URL] [--referer=URL] [--sleep=N] [--tolower] <URL>
 lwp-rget --version

=head1 DESCRIPTION

This program will retrieve a document and store it in a local file.  It
will follow any links found in the document and store these documents
as well, patching links so that they refer to these local copies.
This process continues until there are no more unvisited links or the
process is stopped by the one or more of the limits which can be
controlled by the command line arguments.

This program is useful if you want to make a local copy of a
collection of documents or want to do web reading off-line.

All documents are stored as plain files in the current directory. The
file names chosen are derived from the last component of URL paths.

The options are:

=over 3

=item --auth=USER:PASS<n>

Set the authentication credentials to user "USER" and password "PASS" if
any restricted parts of the web site are hit.  If there are restricted
parts of the web site and authentication credentials are not available,
those pages will not be downloaded.

=item --depth=I<n>

Limit the recursive level. Embedded images are always loaded, even if
they fall outside the I<--depth>. This means that one can use
I<--depth=0> in order to fetch a single document together with all
inline graphics.

The default depth is 5.

=item --hier

Download files into a hierarchy that mimics the web site structure.
The default is to put all files in the current directory.

=item --referer=I<URI>

Set the value of the Referer header for the initial request.  The
special value C<"NONE"> can be used to suppress the Referer header in
any of subsequent requests.  The Referer header will always be suppressed
in all normal C<http> requests if the referring page was transmitted over
C<https> as recommended in RFC 2616.

=item --iis

Sends an "Accept: */*" on all URL requests as a workaround for a bug in
IIS 2.0.  If no Accept MIME header is present, IIS 2.0 returns with a
"406 No acceptable objects were found" error.  Also converts any back
slashes (\\) in URLs to forward slashes (/).

=item --keepext=I<mime/type[,mime/type]>

Keeps the current extension for the list MIME types.  Useful when
downloading text/plain documents that shouldn't all be translated to
*.txt files.

=item --limit=I<n>

Limit the number of documents to get.  The default limit is 50.

=item --nospace

Changes spaces in all URLs to underscore characters (_).  Useful when
downloading files from sites serving URLs with spaces in them.	Does not
remove spaces from fragments, e.g., "file.html#somewhere in here".

=item --prefix=I<url_prefix>

Limit the links to follow. Only URLs that start the prefix string are
followed.

The default prefix is set as the "directory" of the initial URL to
follow.	 For instance if we start lwp-rget with the URL
C<http://www.sn.no/foo/bar.html>, then prefix will be set to
C<http://www.sn.no/foo/>.

Use C<--prefix=''> if you don't want the fetching to be limited by any
prefix.

=item --sleep=I<n>

Sleep I<n> seconds before retrieving each document. This options allows
you to go slowly, not loading the server you visiting too much.

=item --tolower

Translates all links to lowercase.  Useful when downloading files from
IIS since it does not serve files in a case sensitive manner.

=item --verbose

Make more noise while running.

=item --quiet

Don't make any noise.

=item --version

Print program version number and quit.

=item --help

Print the usage message and quit.

=back

Before the program exits the name of the file, where the initial URL
is stored, is printed on stdout.  All used filenames are also printed
on stderr as they are loaded.  This printing can be suppressed with
the I<--quiet> option.

=head1 SEE ALSO

L<lwp-request>, L<LWP>

=head1 AUTHOR

Gisle Aas <aas@sn.no>

=cut

use strict;

use Getopt::Long    qw(GetOptions);
use URI::URL	    qw(url);
use LWP::MediaTypes qw(media_suffix);
use HTML::Entities  ();

use vars qw($VERSION);
use vars qw($MAX_DEPTH $MAX_DOCS $PREFIX $REFERER $VERBOSE $QUIET $SLEEP $HIER $AUTH $IIS $TOLOWER $NOSPACE %KEEPEXT);

my $progname = $0;
$progname =~ s|.*/||;  # only basename left
$progname =~ s/\.\w*$//; #strip extension if any

$VERSION = sprintf("%d.%02d", q$Revision: 2.4 $ =~ /(\d+)\.(\d+)/);

#$Getopt::Long::debug = 1;
#$Getopt::Long::ignorecase = 0;

# Defaults
$MAX_DEPTH = 5;
$MAX_DOCS  = 50;

GetOptions('version'  => \&print_version,
	   'help'     => \&usage,
	   'depth=i'  => \$MAX_DEPTH,
	   'limit=i'  => \$MAX_DOCS,
	   'verbose!' => \$VERBOSE,
	   'quiet!'   => \$QUIET,
	   'sleep=i'  => \$SLEEP,
	   'prefix:s' => \$PREFIX,
	   'referer:s'=> \$REFERER,
	   'hier'     => \$HIER,
	   'auth=s'   => \$AUTH,
	   'iis'      => \$IIS,
	   'tolower'  => \$TOLOWER,
	   'nospace'  => \$NOSPACE,
	   'keepext=s' => \$KEEPEXT{'OPT'},
	  ) || usage();

sub print_version {
    require LWP;
    my $DISTNAME = 'libwww-perl-' . LWP::Version();
    print <<"EOT";
This is lwp-rget version $VERSION ($DISTNAME)

This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
EOT
    exit 0;
}

my $start_url = shift || usage();
usage() if @ARGV;

require LWP::UserAgent;
my $ua = new LWP::UserAgent;
$ua->agent("$progname/$VERSION " . $ua->agent);
$ua->env_proxy;

unless (defined $PREFIX) {
    $PREFIX = url($start_url);	 # limit to URLs below this one
    eval {
	$PREFIX->eparams(undef);
	$PREFIX->equery(undef);
    };

$_ = $PREFIX->epath;
    s|[^/]+$||;
    $PREFIX->epath($_);
    $PREFIX = $PREFIX->as_string;
}

%KEEPEXT = map { lc($_) => 1 } split(/\s*,\s*/, ($KEEPEXT{'OPT'}||0));

my $SUPPRESS_REFERER;
$SUPPRESS_REFERER++ if ($REFERER || "") eq "NONE";

print <<"" if $VERBOSE;
START	  = $start_url
MAX_DEPTH = $MAX_DEPTH
MAX_DOCS  = $MAX_DOCS
PREFIX	  = $PREFIX

my $no_docs = 0;
my %seen = ();	   # mapping from URL => local_file

my $filename = fetch($start_url, undef, $REFERER);
print "$filename\n" unless $QUIET;

sub fetch
{
    my($url, $type, $referer, $depth) = @_;

# Fix http://sitename.com/../blah/blah.html to
    #	  http://sitename.com/blah/blah.html
    $url = $url->as_string if (ref($url));
    while ($url =~ s#(https?://[^/]+/)\.\.\/#$1#) {}

# Fix backslashes (\) in URL if $IIS defined
    $url = fix_backslashes($url) if (defined $IIS);

$url = url($url);
    $type  ||= 'a';
    # Might be the background attribute
    $type = 'img' if ($type eq 'body' || $type eq 'td');
    $depth ||= 0;

# Print the URL before we start checking...
    my $out = (" " x $depth) . $url . " ";
    $out .= "." x (60 - length($out));
    print STDERR $out . " " if $VERBOSE;

# Can't get mailto things
    if ($url->scheme eq 'mailto') {
	print STDERR "*skipping mailto*\n" if $VERBOSE;
	return $url->as_string;
    }

# The $plain_url is a URL without the fragment part
    my $plain_url = $url->clone;
    $plain_url->frag(undef);

# Check PREFIX, but not for <IMG ...> links
    if ($type ne 'img' and  $url->as_string !~ /^\Q$PREFIX/o) {
	print STDERR "*outsider*\n" if $VERBOSE;
	return $url->as_string;
    }

# Translate URL to lowercase if $TOLOWER defined
    $plain_url = to_lower($plain_url) if (defined $TOLOWER);

# If we already have it, then there is nothing to be done
    my $seen = $seen{$plain_url->as_string};
    if ($seen) {
	my $frag = $url->frag;
	$seen .= "#$frag" if defined($frag);
	$seen = protect_frag_spaces($seen);
	print STDERR "$seen (again)\n" if $VERBOSE;
	return $seen;
    }

# Too much or too deep
    if ($depth > $MAX_DEPTH and $type ne 'img') {
	print STDERR "*too deep*\n" if $VERBOSE;
	return $url;
    }
    if ($no_docs > $MAX_DOCS) {
	print STDERR "*too many*\n" if $VERBOSE;
	return $url;
    }

# Fetch document 
    $no_docs++;
    sleep($SLEEP) if $SLEEP;
    my $req = HTTP::Request->new(GET => $url);
    # See: http://ftp.sunet.se/pub/NT/mirror-microsoft/kb/Q163/7/74.TXT
    $req->header ('Accept', '*/*') if (defined $IIS);  # GIF/JPG from IIS 2.0
    $req->authorization_basic(split (/:/, $AUTH)) if (defined $AUTH);
    if ($referer && !$SUPPRESS_REFERER) {
	if ($req->url->scheme eq 'http') {
	    # RFC 2616, section 15.1.3
	    $referer = url($referer) unless ref($referer);
	    undef $referer if ($referer->scheme || '') eq 'https';
	}
	$req->referer($referer) if $referer;
    }
    my $res = $ua->request($req);

# Check outcome
    if ($res->is_success) {
	my $doc = $res->content;
	my $ct = $res->content_type;
	my $name = find_name($res->request->url, $ct);
	print STDERR "$name\n" unless $QUIET;
	$seen{$plain_url->as_string} = $name;

# If the file is HTML, then we look for internal links
	if ($ct eq "text/html") {
	    # Save an unprosessed version of the HTML document.	 This
	    # both reserves the name used, and it also ensures that we
	    # don't loose everything if this program is killed before
	    # we finish.
	    save($name, $doc);
	    my $base = $res->base;

# Follow and substitute links...
	    $doc =~
s/
  (
    <(img|a|body|area|frame|td)\b   # some interesting tag
    [^>]+			    # still inside tag (not strictly correct)
    \b(?:src|href|background)	    # some link attribute
    \s*=\s*			    # =
  )
    (?:				    # scope of OR-ing
	 (")([^"]*)"	|	    # value in double quotes  OR
	 (')([^']*)'	|	    # value in single quotes  OR
	    ([^\s>]+)		    # quoteless value
    )
/
  new_link($1, lc($2), $3||$5, HTML::Entities::decode($4||$6||$7),
           $base, $name, "$url", $depth+1)
/giex;
	   # XXX
	   # The regular expression above is not strictly correct.
	   # It is not really possible to parse HTML with a single
	   # regular expression, but it is faster.  Tags that might
	   # confuse us include:
	   #	<a alt="href" href=link.html>
	   #	<a alt=">" href="link.html">
	   #
	}
	save($name, $doc);
	return $name;
    }
    else {
	print STDERR $res->code . " " . $res->message . "\n" if $VERBOSE;
	$seen{$plain_url->as_string} = $url->as_string;
	return $url->as_string;
    }
}

sub new_link
{
    my($pre, $type, $quote, $url, $base, $localbase, $referer, $depth) = @_;

$url = protect_frag_spaces($url);

$url = fetch(url($url, $base)->abs, $type, $referer, $depth);
    $url = url("file:$url", "file:$localbase")->rel
	unless $url =~ /^[.+\-\w]+:/;

$url = unprotect_frag_spaces($url);

return $pre . $quote . $url . $quote;
}

sub protect_frag_spaces
{
    my ($url) = @_;

$url = $url->as_string if (ref($url));

if ($url =~ m/^([^#]*#)(.+)$/)
    {
      my ($base, $frag) = ($1, $2);
      $frag =~ s/ /%20/g;
      $url = $base . $frag;
    }

return $url;
}

sub unprotect_frag_spaces
{
    my ($url) = @_;

$url = $url->as_string if (ref($url));

if ($url =~ m/^([^#]*#)(.+)$/)
    {
      my ($base, $frag) = ($1, $2);
      $frag =~ s/%20/ /g;
      $url = $base . $frag;
    }

return $url;
}

sub fix_backslashes
{
    my ($url) = @_;
    my ($base, $frag);

$url = $url->as_string if (ref($url));

if ($url =~ m/([^#]+)(#.*)/)
    {
      ($base, $frag) = ($1, $2);
    }
    else
    {
      $base = $url;
      $frag = "";
    }

$base =~ tr/\\/\//;
    $base =~ s/%5[cC]/\//g;	# URL-encoded back slash is %5C

return $base . $frag;
}

sub to_lower
{
    my ($url) = @_;
    my $was_object = 0;

if (ref($url))
    {
      $url = $url->as_string;
      $was_object = 1;
    }

if ($url =~ m/([^#]+)(#.*)/)
    {
      $url = lc($1) . $2;
    }
    else
    {
      $url = lc($url);
    }

if ($was_object == 1)
    {
      return url($url);
    }
    else
    {
      return $url;
    }
}

sub translate_spaces
{
    my ($url) = @_;
    my ($base, $frag);

$url = $url->as_string if (ref($url));

if ($url =~ m/([^#]+)(#.*)/)
    {
      ($base, $frag) = ($1, $2);
    }
    else
    {
      $base = $url;
      $frag = "";
    }

$base =~ s/^ *//;	# Remove initial spaces from base
    $base =~ s/ *$//;	# Remove trailing spaces from base

$base =~ tr/ /_/;
    $base =~ s/%20/_/g; # URL-encoded space is %20

return $base . $frag;
}

sub mkdirp
{
    my($directory, $mode) = @_;
    my @dirs = split(/\//, $directory);
    my $path = shift(@dirs);   # build it as we go
    my $result = 1;   # assume it will work

unless (-d $path) {
	$result &&= mkdir($path, $mode);
    }

foreach (@dirs) {
	$path .= "/$_";
	if ( ! -d $path) {
	    $result &&= mkdir($path, $mode);
	}
    }

return $result;
}

sub find_name
{
    my($url, $type) = @_;
    #print "find_name($url, $type)\n";

# Translate spaces in URL to underscores (_) if $NOSPACE defined
    $url = translate_spaces($url) if (defined $NOSPACE);

# Translate URL to lowercase if $TOLOWER defined
    $url = to_lower($url) if (defined $TOLOWER);

$url = url($url) unless ref($url);

my $path = $url->path;

# trim path until only the basename is left
    $path =~ s|(.*/)||;
    my $dirname = ".$1";
    if (!$HIER) {
	$dirname = "";
    }
    elsif (! -d $dirname) {
	mkdirp($dirname, 0775);
    }

my $extra = "";  # something to make the name unique
    my $suffix;

if ($KEEPEXT{lc($type)}) {
        $suffix = ($path =~ m/\.(.*)/) ? $1 : "";
    }
    else {
        $suffix = media_suffix($type);
    }

$path =~ s|\..*||;	# trim suffix
    $path = "index" unless length $path;

while (1) {
	# Construct a new file name
	my $file = $dirname . $path . $extra;
	$file .= ".$suffix" if $suffix;
	# Check if it is unique
	return $file unless -f $file;

# Try something extra
	unless ($extra) {
	    $extra = "001";
	    next;
	}
	$extra++;
    }
}

sub save
{
    my $name = shift;
    #print "save($name,...)\n";
    open(FILE, ">$name") || die "Can't save $name: $!";
    binmode FILE;
    print FILE $_[0];
    close(FILE);
}

sub usage
{
    print <<""; exit 1;
Usage: $progname [options] <URL>
Allowed options are:
  --auth=USER:PASS  Set authentication credentials for web site
  --depth=N	    Maximum depth to traverse (default is $MAX_DEPTH)
  --hier	    Download into hierarchy (not all files into cwd)
  --referer=URI     Set initial referer header (or "NONE")
  --iis		    Workaround IIS 2.0 bug by sending "Accept: */*" MIME
		    header; translates backslashes (\\) to forward slashes (/)
  --keepext=type    Keep file extension for MIME types (comma-separated list)
  --limit=N	    A limit on the number documents to get (default is $MAX_DOCS)
  --nospace	    Translate spaces URLs (not #fragments) to underscores (_)
  --version	    Print version number and quit
  --verbose	    More output
  --quiet	    No output
  --sleep=SECS	    Sleep between gets, ie. go slowly
  --prefix=PREFIX   Limit URLs to follow to those which begin with PREFIX
  --tolower	    Translate all URLs to lowercase (useful with IIS servers)

}

${this.title}

Code Editor : lwp-rget