Beefy Boxes and Bandwidth Generously Provided by pair Networks
Your skill will accomplish
what the force of many cannot
 
PerlMonks  

TheBench.org strip grabber

by billyjoeray (Initiate)
on Mar 15, 2000 at 01:08 UTC ( [id://5384]=sourcecode: print w/replies, xml ) Need Help??
Category: web stuff/misc
Author/Contact Info billyjoeray@netzero.net ICQ: 15291367
Description: This script can be run on regular intervals to download the latest strips from thebench.org I'm putting this here because its a little big for the front page, but for whoever reads this, I'd like some tips on how to clean up my code and some wisdom on how to easily write code with 'use scrict;' I always seem to be needing to use variables in a global sense.
#!/usr/bin/perl -w

use LWP::UserAgent;
use HTTP::Request::Common;

$numofstrips = NumofStrips();

$home = `echo \$HOME`;chop $home;$rcfile = "$home\/.stripnum";

if (-f $rcfile) {
    $stripnum = `cat ~/.stripnum`;
} else {
    print "~/.stripnum does not exist, creating...\n";
    system 'echo 1 > ~/.stripnum';
    $stripnum = `cat ~/.stripnum`;
}

if (-d "$home\/.strips") {
} else {
    print "directory $home\/.strips does not exist, creating...\n";
    system "mkdir $home\/.strips";
}
print "Should only see this once!\n";
mainblock: {
    $url = "http://thebench.org/index.php3?strip=$stripnum";
    $bot = new LWP::UserAgent;
    $bot->agent('Mozilla');
    $response = $bot->request(GET $url);
    $content = $response->content;

    @content = split(/\n/, $content);

  content: for($i=0;$i<$#content;$i++) {
      $content[$i] =~ /.*Strip \#(.*):<.*/;
      if ($1) { $number = $1; last content; }
  }
    if ($number != $stripnum) { 
        print "$stripnum does not seem to exhist\n";
        $numofstrips = NumofStrips();
        print "$numofstrips seems to be total number of strips\n";
        $numofstrips++;
        if ($stripnum == $numofstrips) {
            open (FILE, ">$rcfile") || die;
            print (FILE "$stripnum") || die;
            close FILE;
            die "Got last file exiting\n";
        }
        else {
            $stripnum++;
        }
        print "lets try to get $stripnum\n";
        goto mainblock;
    }
    undef $filetodl;
  searchforfiletodl: for (split "\n", $content) {
        $filetodl = "$1.jpg" if/.*img\/strips\/(.*).jpg/;
        if ($filetodl){
            #print $filetodl;
            last searchforfiletodl;
        }
    }
    $imgurl = "http://thebench.org/img/strips/$filetodl";
    print "Downloading $imgurl\n";
    $response = $bot->request(GET $imgurl);
    $content = $response->content;


    $file = "$home\/.strips\/$number.jpg";
    print "opening $file\n";
    open (FILE, ">$file") || die;
    print (FILE "$content") || die;
    print "success!\n";
    close FILE;
    $stripnum++;
    print "$stripnum\n";
    open (FILE, ">$rcfile") || die;
    print (FILE $stripnum) || die;
    close FILE;
}

goto mainblock;

sub NumofStrips {
    my $url = "http://thebench.org/archive.php3";
    my $bot = new LWP::UserAgent;
    $bot->agent('Mozilla');
    my $response = $bot->request(GET $url);
    my $content = $response->content;
    @content = split(/\/td/, $content);
    searchfornumofstrips: for($i=0;$i<$#content;$i++){
        $content[$i] =~ /<tr><td valign='top'><p>(.*)<\/p></;
        if($1) { $numofstrips = $1; last searchfornumofstrips; }
    }
    return $numofstrips;
}

print "This isnt supposed to happen!\n"; die;

Log In?
Username:
Password:

What's my password?
Create A New User
Domain Nodelet?
Node Status?
node history
Node Type: sourcecode [id://5384]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this?Last hourOther CB clients
Other Users?
Others avoiding work at the Monastery: (4)
As of 2024-04-20 01:31 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    No recent polls found