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
| #!/usr/bin/perl -w
use strict;
use URI::URL;
use HTTP::Request;
use HTTP::Response;
use HTTP::Cookies;
require LWP::Parallel::RobotUA;
use HTML::Parse qw(parse_html);
use WWW::RobotRules;
#===========================================================================#
# Begin of configuration #
#===========================================================================#
$| = 1; # Buffer
my $arg;
my $VERSION = "Bot/1.1"; # Nom du robot
my $ua = LWP::Parallel::RobotUA->new('Mozilla/5.0 (compatible; Bot/1.1', 'bot@robotx.com');
$ua->delay(0);
$ua->max_hosts(400); # sets maximum number of locations accessed in parallel
$ua->max_req(400); # sets maximum number of parallel requests per host
$ua->wait(0);
$ua->max_redirect(8000000000);
$ua->protocols_allowed( [ 'http' ] );
$ua->protocols_forbidden( [ 'file', 'mailto', 'https', 'ftp', 'socks', 'gopher'] );
$ua->requests_redirectable( [ 'HEAD' ] );
$ua->timeout(4);
$ua->env_proxy;
$ua->redirect(1); # follow redirects
my $cookie_jar = HTTP::Cookies->new(
file => 'lwp_cookies.dat',
autosave => 1,
);
$ua->cookie_jar($cookie_jar);
#===========================================================================#
# The Robot #
#===========================================================================#
my %urls;
@urls{ @ARGV } = (1) x @ARGV;
foreach my $link ( keys %urls ){
&robot($link);
}
sub robot
{
foreach my $link ( @_ ) {
my $link = $_[0];
my $req = HTTP::Request->new( 'GET', $link );
$req->header('Accept' => [
qw(
text/html application/xhtml+xml application/msexcel
application/msword application/pdf application/rtf
application/x-javascript application/x-httpd-php
text/rtf text/nux application/sxc application/sxw
application/sxd application/mdi application/x-httpd-asp
application/x-httpd-aspx application/x-httpd-mspx
application/x-httpd-cfm application/x-httpd-jthml
application/x-httpd-pm )
]
);
my $res = $ua->request($req, $arg, 4096);
if ($res->is_success) {
my ($code, %page, $base);
$code = $res->content;
$base = $res->base;
%page = (
result => [
"$code", "$link"
]
);
print "$page{'result'}->[0]\n";
print "$page{'result'}->[1]\n";
my $extor = extor_links($code,$base);
robot($extor);
}
}
}
#===========================================================================#
# Extract links #
#===========================================================================#
sub extor_links
{
my($url, %saw, @urls);
my $html=$_[0];
my $base=$_[1];
foreach ($html) {
my $ht_tree = parse_html($_[0]);
my ($linkpair, $fqurl);
foreach $linkpair (@{$ht_tree->extract_links(qw<a>)}) {
my($link,$elem) = @$linkpair;
push(@urls, $fqurl)
unless $saw{ $fqurl = url($link,$base)->abs->as_string }++;
}
# print join("\n", sort keys %saw), "\n";
my $urlx = join("\n", sort keys %saw), "\n";
return $urlx;
}
} |
Partager