imported>Unknown at 05:23, 7 February 2021

2021-02-07T05:23:19Z

New page

= from =
http://douweosinga.com/projects/googletalk 를 참조하여서 kldp.net 에 aero 님께서 올리신 글입니다.
[http://bbs.kldp.org/viewtopic.php?t=54500 Korean Google Talk]

= code =
#!/usr/bin/perl

use LWP 5.65;
use URI::URL;

my $debug=0;
my $query = $ARGV[0];

print $query."\n";
my $close_counter=0;
while(1)
{
$query =~ m/\ (.*?)$/;
print "last_word :".$1."\n" if $debug;
$query = query_word($query);
unless($query)
{
$query = $1;
$close_counter++;
if($close_counter>1) { exit; }
}
else
{
print $query."\n";
$query = $1." ".$query;
$close_counter=0;
}
}

sub query_word
{
my $q = $_[0];
$q = '" '.$q.' "';
my $unencoded_url = 'http://www.google.com/search?hl=ko&num=10&q='.$q;
my $url = URI::URL->new($unencoded_url);

print "unencoded: " . $unencoded_url ."\n" if $debug;
print "encoded: " . $url->as_string . "\n" if $debug;

my $browser = LWP::UserAgent->new();
my $response = $browser->get($url->as_string, 'User-Agent'=>'Mozilla' );
if($response->is_success)
{
my $res = $response->content;
$res =~ s///gs;
$res =~ s/<\/b>//gs;
$res =~ s/\n//gs;
print "Response:\n$res\n" if $debug;
#$res =~ m/<\/a> (.*?) /i;
my @next_words = ();
while($res=~m/<\/a> (.*?) /g)
{
print $1."\n\n" if $debug;
my $s = $1;
my $next_word = get_next_words($s,$q);
if ($next_word) {push(@next_words,$next_word);}
pos($res)+1;
}
print "@next_words ".($#next_words+1)."\n" if $debug;
my $select = rand($#next_words+1);
print "selected :".$next_words[$select]."\n" if $debug;
return $next_words[$select];
}
else
{
print $response->error_as_HTML if $debug;
}
}

sub get_next_words
{
my($text,$q) = @_;
$q =~ s/"//g;
print "query :".$q."\n" if $debug;
$text =~ s/[a-zA-Z_&#|;:<>,?.~\*\^\$\[\]\-\+()\/=]//g;
print "text :".$text."\n" if $debug;
$text =~ m/($q)(\S*?)\ /;
print "match 1 |".$1."| 2 |".$2."| 3 |".$3."| 4 |".$4."|\n" if $debug;
return $2;
}

= result =
google_talks.pl "내가 보건데"
내가 보건데
한국의
대학이
어떻게
수용할
경우에는
양도세를
내야
한다
세금을
내야
하지
않겠소이까
자칭
선배라는
사람의
입장도
생각하는
도량은
있어야지요
20050109
33

Google/GoogleTalk - Revision history

imported>Unknown at 05:23, 7 February 2021