Perl使用Tesseract-OCR实现验证码识别教程

pf.pl http://www.proxyfire.net/index.php?pageid=eliteproxylist       elite.txt
pf.pl http://www.proxyfire.net/index.php?pageid=anonymousproxylist   anony.txt
pf.pl http://www.proxyfire.net/index.php?pageid=transparentproxylist trans.txt
pf.pl http://www.proxyfire.net/index.php?pageid=socks4proxylist      s4.txt
pf.pl http://www.proxyfire.net/index.php?pageid=socks5proxylist      s5.txt
type *.txt > all.tmp
del *.txt /s/q
ren all.tmp all.txt
@pause

use strict;
 
our $url    = $ARGV[0];
our $file   = $ARGV[1];
 
my $res = undef;
my @tmp = undef;
my @pxy = undef;
 
    `wget $url -q -O ___html`;
    open FH, "<___html";
    @tmp = ;
    close FH;
    $res = join('',@tmp);
    undef(@tmp);
    `del ___html /s /q`;
 
@tmp = ( $res =~ /<img alt="" src="([^" border="0">]+)><\/td>(\d+)'http://www.proxyfire.net'.$tmp[$i], 'port'=>$tmp[$i+1]};
    $i = $i + 1;
}
 
for (my $i=0; $i < @pxy; $i++) {     if( length(${$pxy[$i]}{ip})>0 )
    {
        `echo off & wget ${$pxy[$i]}{ip} -q -O ___png`;
        `tesseract ___png ___ -l chi_tra`;
 
        my $txt = undef;  
        open FH,"<___.txt";
        $txt = ;
        close FH;
        if ( length($txt)>11 )
        {
            $txt =~ s/\s+//g;
            $txt =~ s/日/8/g;
            $txt =~ s/昍/88/g;
            $txt =~ s/s0/60/g;
            $txt =~ s/s1/61/g;
            $txt =~ s/s2/62/g;
            $txt =~ s/s3/69/g;
            $txt =~ s/s4/64/g;
            $txt =~ s/s5/65/g;
            $txt =~ s/s7/67/g;
            $txt =~ s/s8/68/g;
            $txt =~ s/s9/69/g;
            $txt =~ s/0s/06/g;
            $txt =~ s/1s/16/g;
            $txt =~ s/2s/26/g;
            $txt =~ s/3s/96/g;
            $txt =~ s/4s/46/g;
            $txt =~ s/5s/56/g;
            $txt =~ s/6s/66/g;
            $txt =~ s/7s/76/g;
            $txt =~ s/8s/86/g;
            $txt =~ s/9s/96/g;
            $txt =~ s/ss/66/g;
            $txt =~ s/\.s/\.6/g;
            ${$pxy[$i]}{ip} = $txt;
 
            my $bak1 = $txt;
            my $bak2 = $txt;
            $bak1 =~ s/13/19/g;
            $bak1 =~ s/\.32\./\.92\./g;
            $bak1 =~ s/\.33\./\.99\./g;
 
            $bak2 =~ s/19/13/g;
            $bak2 =~ s/\.243/\.249/g;
            $bak2 =~ s/203\./209\./g;
 
            open FHX,">>$file";
            print FHX ${$pxy[$i]}{ip}.":".${$pxy[$i]}{port}."\n";
            print FHX $bak1.":".${$pxy[$i]}{port}."\n";
            print FHX $bak2.":".${$pxy[$i]}{port}."\n";
            close FHX;
 
        }
        my $txt = undef;
    }
}
`del ___* /s /q`;
undef($url);
undef($file);
undef($res);
undef(@tmp);
undef(@pxy);