Villa Opera Lamartine

2014년 6월 3일 화요일

get naver kin

use LWP::UserAgent;
use autodie qw/ open close /;
use WWW::Mechanize;
use LWP::Simple qw($ua get);
use Encode;

$filename="naverkin-phy.txt";
if(-e $filename)
    {
        unlink($filename);
    }

$ua->agent('My agent/1.0');

# create WWW::Mechanize object
# autocheck 1 checks each request to ensure it was successful
my $mech = WWW::Mechanize->new();

$mech->get("http://kin.naver.com/qna/list.nhn?m=noanswer&dirId=1114&page=1");
#$no=197187698;

$list_cont = $mech->content();

$list_cont=encode("euc-kr", $list_cont);
#print $list_cont;

@link = split(/docId=(\d{9})/, $list_cont);

for ($i=1; $i<=$#link; $i++){
    if ($i%2 == 1){
    push(@no, $link[$i]);
    }
}

@no = sort {$a <=> $b} @no; # 1,2,3 순으로 정렬; Ascending

for ($i=1; $i<=$#no; $i++){

print $no[$i]." article is extracted...\n";

# paste from url of webbrowser manually later modify
$mech->get("http://kin.naver.com/qna/detail.nhn?d1id=11&dirId=1114&docId=$no[$i]");

$cont = $mech->content();
$cont=encode("euc-kr", $cont);

#@temp = split(/og:url/, $cont);
#@temp = split(/science&no=/, $temp[1]);
#@temp = split(/&page/, $temp[1]);

@temp = split(/tit_cont/, $cont);
@temp = split(/recom_q/, $temp[1]);
@temp = split(/img/, $temp[0]);
@temp = split(/dl/, $temp[0]);

$subject = $temp[0];
$subject =~ s/">//g;
$subject =~ s/h3>//g;
$subject =~ s/<//g;
$subject =~ s/\///g;
$subject =~ s/^\s+//g;
$subject =~ s/\s+$//g;

$subject = "subject: ".$subject;

@temp = split(/tit_cont/, $cont);
@temp = split(/recom_q/, $temp[1]);
@temp = split(/<dl>/, $temp[0]);
@temp = split(/<\/dl>/, $temp[1]);
@temp = split(/<dt>/, $temp[0]);
@temp = split(/<\/dt>/, $temp[1]);

$name = $temp[0];

$name =~ s/^\s+//g;
$name =~ s/\s+$//g;
$name = "name: ".$name;

@temp = split(/본문/, $cont);
@temp = split(/게시중단 안내/, $temp[3]);
$out = $temp[1];
$out =~ s/!<--$//;
$out =~ s/<\/div>//;
$out =~ s/\!<--//;
$memo = $out;

#print $memo;

$memo = "memo: ".$memo;

@temp = split(/본문/, $cont);
@temp = split(/게시중단 안내/, $temp[3]);
@img_url = split(/src="/,$temp[1]);
@img_url = split(/\?type/,$img_url[1]);
#print $img_url[0];

$img_url[0]=~ m/jpg|png|JPG|PNG/;

if ($img_url[0]){
$img_type = $&;
$mech->mirror($img_url[0], $no.".".$img_type);
}

$attached = "file:".$no.".".$img_type;

open MYFILE, ">>", "naverkin-phy.txt" or die ;
print MYFILE "$no[$i]";
print MYFILE "------------------------------------------------------------------------------\n";
print MYFILE "$name\n";
print MYFILE "$subject\n";
print MYFILE "$memo\n";
print MYFILE "$attached\n";

}

get bgm from bgmstore

2014년 5월 30일 금요일

우분투에서 루트 권한으로 명령 실행

우분투에서 루트 권한으로 명령을 실행하기 위해서는 root password가 설정되어 있어야 한다.

sudo passwd root

이후 sudo 명령을 사용할 수 있다

윈도우에 git 클라이언트 설치

다운로드
http://git-scm.com/download/win

path에 설치폴더의 바이너리 경로를 등록

명령프롬프트에서 실행하면 된다

perl mechanize example

use LWP::UserAgent;
use autodie qw/ open close /;
use WWW::Mechanize;
use LWP::Simple qw($ua get);
use Encode;

$ua->agent('My agent/1.0');

# create WWW::Mechanize object
# autocheck 1 checks each request to ensure it was successful
my $mech = WWW::Mechanize->new();

$filename = "ilbe.txt";
if(-e $filename)
    {
        unlink($filename);
    }

$mech->get("http://www.ilbe.com/ilbe");

@link = $mech->find_all_links( url_regex => qr/\d{10}/);

for $new_link (@link){

$url = $new_link->url_abs();

$no = $url;
$no =~ m/\d{10}/;

$no = $&;

$mech->get($url);
$cont = $mech->content();

print $no." article is extracted...\n";
@files=();

# paste from url of webbrowser manually later modify

#@temp = split(/og:url/, $cont);
#@temp = split(/science&no=/, $temp[1]);
#@temp = split(/&page/, $temp[1]);

#$no = $temp[0];

$cont=encode("euc-kr", $cont);

@temp = split(/author/, $cont);
@temp = split(/<\/div>/, $temp[1]);
@temp = split(/<\/div>/, $temp[0]);
@temp = split(/margin-right:3px;/, $temp[0]);
$name = $temp[1];
$name =~ s/"//;
$name =~ s/\/>//;
$name =~ s/^\s+//;
@temp = split(/<\/span>/, $name);
$name =~ s/\s+$//;
$name = $temp[0];
#print $name;

@temp = split(/기사 제목/, $cont);
@temp = split(/-->/, $temp[1]);
@temp = split(///;
$memo =~ s/^\s+//;

#print $memo;

@img = $mech->find_all_links( text_regex => qr/png/i );

$i = 0;
for my $img_url (@img) {
    $i++;
    print $img_url->url_abs;
    $mech->mirror($img_url->url_abs, $no."-".$i.".png");
    push (@files, $no."-".$i.".png");

}

@img = $mech->find_all_links( text_regex => qr/jpg/i );
for my $img_url (@img) {
    $i++;
    print $img_url->url_abs;
    $mech->mirror($img_url->url_abs, $no."-".$i.".jpg");
    push (@files, $no."-".$i.".jpg");

    #Opens FROM_DIR, ao I can read from it


}

$attached = "file:";
for ($i=0; $i<=$#files; $i++){
$attached = $attached.$files[$i]." ";

}

$name = "name: ".$name;
$subject = "subject: ".$subject;
$memo = "memo: ".$memo;

open MYFILE, ">>$filename" or die ;
print MYFILE "$no";
print MYFILE "------------------------------------------------------------------------------\n";
print MYFILE "$name\n";
print MYFILE "$subject\n";
print MYFILE "$memo\n";
print MYFILE "$attached\n";
}

2014년 5월 23일 금요일

펄 모듈 설치 모듈이 서브 타입으로 되어 있을 때

모듈이름이
WWW::Mechanize::Firefox

다 써주어야 한다.

cpan install WWW::Mechanize::Firefox

대소문자도 구분하니까 유의

2014년 5월 8일 목요일

하위 폴더의 모든 파일에서 특정 문자열을 검색하는 펄스크립트

use strict;
use warnings;
use Cwd;

use File::Find;

my $search_pattern=$ARGV[0];
my $file_pattern =$ARGV[1];

if (@ARGV <2){
print "Useage: $0 [string to search] [file type]\n";
exit 1;
}

find(\&d, cwd);

sub d {

my $file = $File::Find::name;

$file =~ s,/,\\,g;

return unless -f $file;
return unless $file =~ /$file_pattern/;

open F, $file or print "couldn't open $file\n" && return;

while (<F>) {
    if (my ($found) = m/($search_pattern)/o) {
      print "found $found in $file\n";
      last;
    }
}

close F;
}