2011-07-14 19:33:28 +02:00
|
|
|
# Template build file for 'perl-WWW-RobotRules'.
|
|
|
|
|
pkgname=perl-WWW-RobotRules
|
|
|
|
|
version=6.01
|
|
|
|
|
wrksrc="WWW-RobotRules-$version"
|
|
|
|
|
distfiles="${CPAN_SITE}/WWW/WWW-RobotRules-$version.tar.gz"
|
2011-07-18 16:42:50 +02:00
|
|
|
build_style=perl-module
|
2012-05-23 18:26:56 +02:00
|
|
|
fulldepends="perl-URI perl"
|
2012-06-03 09:08:53 +02:00
|
|
|
revision=1
|
2011-07-14 19:33:28 +02:00
|
|
|
short_desc="WWW::RobotRules - database of robots.txt-derived permissions"
|
|
|
|
|
maintainer="davehome <davehome@redthumb.info.tm>"
|
|
|
|
|
homepage="http://search.cpan.org/~gaas/WWW-RobotRules-6.01/lib/WWW/RobotRules.pm"
|
|
|
|
|
license="GPL-2"
|
|
|
|
|
checksum=f817e3e982c9d869c7796bcb5737c3422c2272355424acd162d0f3b132bec9d3
|
|
|
|
|
long_desc="
|
|
|
|
|
This module parses /robots.txt files as specified in
|
|
|
|
|
A Standard for Robot Exclusion, at http://www.robotstxt.org/wc/norobots.html
|
|
|
|
|
Webmasters can use the /robots.txt file to forbid conforming robots from
|
|
|
|
|
accessing parts of their web site.
|
|
|
|
|
|
|
|
|
|
The parsed files are kept in a WWW::RobotRules object, and this object
|
|
|
|
|
provides methods to check if access to a given URL is prohibited. The same
|
|
|
|
|
WWW::RobotRules object can be used for one or more parsed /robots.txt files
|
|
|
|
|
on any number of hosts."
|
|
|
|
|
|
|
|
|
|
noarch=yes
|
|
|
|
|
|
