Dagelijkse Mop

#!/usr/bin/perl -w

use strict;
use IO::File;
use POSIX qw(strftime);
require LWP::UserAgent;

# Utility Functions
my $ua = LWP::UserAgent->new();

sub get_page {
  my ($url, $file_to_store) = @_;
  my $request = HTTP::Request->new("GET", $url);
  my $response = $ua->request($request, $file_to_store);

  if ($response->is_success) {
    return $response->content();
  } else {
    print $response->error_as_HTML;
    return 0;
  }
}


my %dilbert = ( 'url' => 'http://www.dilbert.com' );
my %ucomics = ( 'url' => 'http://www.ucomics.com' );

# A parser returns (url of the strip, url of the img) for a comic

my %alt_name = ( 'Dilbert' => 'Dilbert.com' );

sub dilbert_parser {
	my ($comic) = @_;
	defined($alt_name{$comic}) and $comic = $alt_name{$comic};

	my ($url) = $dilbert{page} =~ /OPTION VALUE="(\S*)">\s*$comic/i;
	$url or return;
	#print "XXX $url\n";
	$url = $dilbert{url} . $url if $url !~ /^http/i;
	my $buf = get_page($url);
	$buf =~ /IMG\s*SRC=\S*["'](\S*\d\d\d\d\d\d\d+\.(?:gif|jpg))["'][^>]*alt/i 
									or return;
	my $img = $1;
	$img = $dilbert{url} . $img if $img !~ /^http/i;
	return ($url, $img);
}

sub ucomics_parser {
	my ($comic) = @_;
	my ($url) = $ucomics{page} =~ /OPTION VALUE="(\S*)">\s*$comic/i;
	$url or return;
	$url = $ucomics{url} . $url if $url !~ /^http/i;
	my $buf = get_page($url);
        $buf =~ /IMG\s*SRC=\S*"(\S*\/\S+\d\d\d+\.(?:gif|jpg))/i or return;
	return ($url, $1);
} 

my @sites = ( \%dilbert, \%ucomics );

my @comics = ('Dilbert' 	=> \&dilbert_parser,
	      'Garfield' 	=> \&ucomics_parser,
	      'Peanuts' 	=> \&dilbert_parser,
	      'Betty'  		=> \&dilbert_parser,
	      'Nancy' 		=> \&dilbert_parser,
	      'Calvin & Hobbes'	=> \&ucomics_parser,
	      'FoxTrot'	        => \&ucomics_parser,
	      'Get Fuzzy'	=> \&dilbert_parser,
	      'Frank and Ernest'=> \&dilbert_parser,
	      'Ziggy' 		=> \&ucomics_parser,
	      'Herman'		=> \&dilbert_parser,
	      'Non Sequitur'	=> \&ucomics_parser,
	      'Reality Check'	=> \&dilbert_parser,
	      'B.C.'		=> \&dilbert_parser,
	      'PC and Pixel'	=> \&dilbert_parser,
	      'The Born Loser'	=> \&dilbert_parser,
	      'Doonesbury'	=> \&ucomics_parser,
	      'Wizard of Id'	=> \&dilbert_parser,
	      'Shoe'		=> \&ucomics_parser,
	      'Cathy'		=> \&ucomics_parser,
	      #'Charlie',
	      #'Ballard Street',
	      'Speed Bump'	=> \&dilbert_parser,
	      'Jump Start'	=> \&dilbert_parser,
	      'Pickles'		=> \&dilbert_parser,
	      #'The 5th Wave',
	     );

foreach my $site (@sites) {
  $site->{page} = get_page($site->{url})
    or $site->{page} = "NONE\n";
}

chdir(($^O =~ /Win32/) ? "d:/public_html" : "/home/public_html") or 
					die "Could not chdir: $!";

my $time = time();

#check for yesterdays page
my $date = strftime("%m%d%Y", localtime($time));
my $archive_page = "comics-archive/comics-$date.html";

my $file;

unless (-e $archive_page) {
  $file = new IO::File;
  open($file, "> $archive_page") or die "could not open $archive_page: $!";
}

my $html_str = "";
sub output {
  $html_str .= "@_";	
  print $file "@_" if $file;
}

my $now = localtime($time);
output "<html> <title> Comic Strips</title> <body bgcolor=white>".
  "<meta http-equiv=\"expires\" content=\"Sun, 13 Aug 2000 16:30:00 PDT\">".
  "<br> <br>".
  "<center><large><b> Comic Strips</b><large> (Updated daily. This page: ".
  "$now PDT)".
  "<br></center>\n".
  "<table width=100\% cellpadding=0 cellspacing=0>";

my @missing_comics = ();

for (my $i=0; $i<@comics/2; $i++) {
  my ($comic, $fn) = ($comics[$i*2], $comics[$i*2+1]);

  push @missing_comics, $comic;

  my ($url, $img) = &$fn($comic);

  $img or next;

  #print "XXXX: $url $img\n";

  output "<tr> <td width=10\%> </td> <td> ".
    "<STRONG> $comic </strong> <br> <a href=\"$url\">".
      "<img src=\"$img\" alt=\"$comic\" border=0></a>".
	"<br><br></td> </tr>\n";

  if ($file) {
    my $dir = "comics-archive-images/$comic";
    mkdir($dir);
    my @arr = split(/\//, $img);
    my $img_name = $arr[-1];
    $img_name =~ s/\d+\././;
    get_page($img, "$dir/$date-$img_name");
  }

  pop @missing_comics;
}

#include Jaimie Hollenback's comic as he requested:
$html_str .= "<tr> <td width=10\%> </td> <td> ".
          '<strong> Kim & Jason </strong> <br> '.
          '<a href="http://www.kimandjason.com">'.
	  '<img src="http://www.kimandjason.com/stuff/kj_today.gif" border=0'.
	  ' alt="(c) Copyright by Jason Kotecki. www.KimandJason.com"></a>'.
	  "<br><br></td> </tr>\n";

output "</table> <br> <br> ".
  ((@missing_comics) ? "Missing: @missing_comics <br>\n" : '');

$html_str .= "<a href=\"comics-archive/comics-".
  strftime("%m%d%Y", localtime($time-86400)).
  ".html\"> Yesterday's page</a>. ";

if ($file) {
  print $file "<a href=\"comics-". strftime("%m%d%Y", localtime($time+86400)).
    ".html\"> Next</a> <a href=\"comics-".
      strftime("%m%d%Y", localtime($time-86400)). ".html\"> Prev</a>";
}	

output "<br> <a href=\"http://www.angadi.org/comics.pl\">Source Code</a>. ".
  '<a href="mailto:raghuangadi@yahoo.com">Mail me</a> any comics you want included here. <br>'.
  "<em> <a href=\"http://www.angadi.org/\">Raghu Angadi</a> </em>".
  "</body> </html>\n";

open(OUT, "> comics.html") or die "Could not open comics.html: $!";
print OUT $html_str;
Terug naar inhoud
Terug naar pagina begin