1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
| #!/usr/bin/perl -w
use strict;
use URI::URL;
use HTTP::Status;
use HTTP::Request;
use HTTP::Cookies;
use HTTP::Headers;
use HTTP::Response;
use HTML::LinkExtor;
use LWP::RobotUA;
require WWW::RobotRules::AnyDBM_File;
#...........................................................................#
# Config #
#...........................................................................#
$| = 1;
my $VERSION = "MonRobot/0.1 (+http://dirthangel.free.fr)";
my $rules = WWW::RobotRules::AnyDBM_File->new('Mozilla/5.0 (compatible; MonRobot/0.1 +http://dirthangel.free.fr)', 'cachefile');
my $ua = LWP::RobotUA->new('Mozilla/5.0 (compatible; MonRobot/0.1 +http://dirthangel.free.fr)', 'hdd@free.fr', $rules);
$ua->delay(1/60);
$ua->host_wait(0);
$ua->timeout(3);
$ua->env_proxy;
$ua->max_redirect(10);
$ua->protocols_allowed( [ 'http' ] );
$ua->protocols_forbidden( [ 'file', 'mailto', 'https', 'ftp', 'socks', 'gopher', 'wais' ] );
$ua->requests_redirectable( [ 'HEAD' ] );
my $cookie_jar = HTTP::Cookies->new(
file => 'MonRobot_cookies.dat',
autosave => 1,
);
$ua->cookie_jar($cookie_jar);
my $headers = HTTP::Headers->new(
Accept => [qw(text/html)]
);
$ua->default_headers($headers);
my (@web, $find, @push, @webx, @exclude);
#...........................................................................#
# "Options" #
#...........................................................................#
if (!$ARGV[0]) {
print "Le robot a été lancé sans arguments :@\n";
exit(0);
}
if ($ARGV[0] =~ /^http:\/\//g ) {
robot(@ARGV);
}
#...........................................................................#
# Le robot #
#...........................................................................#
sub robot {
foreach my $url (@_) {
# Fabrication d'une requete
my $request = HTTP::Request->new('GET', $url);
# Execution de la requete
my $res = $ua->request($request);
# Etat de la requete
if ($res->is_success) {
my $code = $res->content;
my $date = date();
my $base = $res->base;
my $content_type = $res->content_type;
my @page = (
"$code","$url",
"$date", "$content_type",
);
print "$page[0]\n";
print "$page[1]\n";
print "$page[2]\n";
print "$page[3]\n";
@webx = links($code, $base);
}
else
{
print "Error: " . $res->status_line . "\n";
}
}
if (!@webx) {
exit(0);
}
else
{
robot(@webx);
}
}
#...........................................................................#
# On cherche les liens #
#...........................................................................#
sub links {
my ($a, $b) = @_;
my $p = HTML::LinkExtor->new(\&callback);
$p->utf8_mode;
$p->parse($a);
@web = map { $_ = url($_, $b)->abs; } @web;
return @web;
}
#...........................................................................#
# Extract links #
#...........................................................................#
sub callback {
my($tag, %attr) = @_;
return if $tag ne 'a';
push(@web, values %attr);
}
#...........................................................................#
# Date du jour #
#...........................................................................#
sub date {
my @tab_date =localtime(time);
my $jour = $tab_date[3];
my $mois = ($tab_date[4]+1);
my $annee = ($tab_date[5]+1900);
return ("$jour/$mois/$annee");
} |