#!/usr/bin/perl
print "Content-type: text/html\n\n";
use POSIX;
use CGI::Carp "fatalsToBrowser";
my $StripNumber = 1;
use LWP::Simple;
# https://www.webmasterworld.com/perl/5018940.htm
# use HTTP::Tiny;
# sub get {
# my ($url) = @_;
# return HTTP::Tiny->new->get($url)->{content};
# }
# https://stackoverflow.com/a/63796968/1424877
# use WWW::Curl::Simple;
# sub get {
# my ($url) = @_;
# my $curl = WWW::Curl::Simple->new();
# return $curl->get($url)->content;
# }
#sub get {
# my ($url) = @_;
# return `curl "$url"`
#}
# Simplified from the HTML::Entities package.
sub num_entity {
return '<' if ($_ eq '<');
return '>' if ($_ eq '>');
return '"' if ($_ eq '"');
return '&' if ($_ eq '&');
my $result = sprintf "&#x%X;", ord($_[0]);
return $result;
}
sub encode_entities {
my $ref;
if (defined wantarray) {
my $x = $_[0];
$ref = \$x; # copy
} else {
$ref = \$_[0]; # modify in-place
}
# Encode control chars, high-bit chars, and <&>'"
$$ref =~ s/([^\n\r\t !\#\$%\(-;=?-~])/num_entity($1)/ge;
}
sub unpack_args {
my $cgi_args = join('&', @_);
@_ = split(/&/, $cgi_args);
foreach my $i (@_) {
my $varname;
my $vardata;
($varname, $vardata) = split(/=/, $i);
if ($varname eq "q") {
$StripNumber = int($vardata);
}
}
}
sub htmlize($) {
my ($foo) = @_;
$foo =~ s/%([0-9A-Fa-f][0-9A-Fa-f])/chr(hex($1))/ge;
$foo =~ s/"/"/gs;
$foo =~ s/<//gs;
$foo =~ s/&/&/gs;
$foo =~ s/\n/
/gs;
return $foo;
}
sub get_page {
# get the original page from Qwantz
my $qwantz_url = "https://www.qwantz.com/index.php?comic=${StripNumber}";
$content = get($qwantz_url);
# read in whole file, not just one line or paragraph
undef $/;
# Get the date.
$content =~ m/Dinosaur Comics - (.*?)<\/title>/sg;
my $comicdate = $1;
# Get the RSS title.
my $rsstitle = "";
if ($content =~ m/<span class="rss-title">(.*?)<\/span>/sg) {
$rsstitle = htmlize($1);
}
print <<END
<div align="right"><small>$comicdate</small></div>
<div style="width:30%;float:right" align="right"><small>$rsstitle</small></div>
<h1>Daily Dinosaur Comic</h1>
END
;
# Get the image(s?) and title text.
while (
$content =~ m/<img src=".*comics\/([^"]+)"[^<]+title="([^"]*)"/sg
) {
my $imagepath = $1;
my $titletext = htmlize($2);
last if ($imagepath eq "");
print <<END
<p> from <a href="${qwantz_url}">www.qwantz.com</a>
<img src="https://www.qwantz.com/comics/${imagepath}"/>
<p> ${titletext}
END
;
}
# Get the contact e-mail subject joke.
# The first several comics have no e-mail subject line.
# For an example of an e-mail body, see comic #250.
$content =~ m/mailto:ryan\@qwantz.com\?subject=([^"]*)"/sg;
my $emailtext = $1;
my $replytext = "";
# LWP::Simple::get() encodes "&body=" as "%26body%3D"
# for some reason. Decode percent-sign hex values here.
$emailtext =~ s/%([0-9A-Fa-f][0-9A-Fa-f])/chr(hex($1))/ge;
my $numfields = ($emailtext =~ /([^\&]*)\&body=(.*)/s);
print "<!-- emtext=\"$emailtext\" numfields=$numfields -->";
if ($numfields >= 1 && !($2 eq "")) {
$emailtext = htmlize($1);
$replytext = htmlize($2);
} else {
$emailtext = htmlize($emailtext);
}
if ($replytext eq "") {
print "<p><b>Subject:</b> ${emailtext}\n\n";
} else {
print "<p><b>Subject:</b> ${emailtext} <i>${replytext}</i>\n\n";
}
}
my $query;
if (!defined $ENV{'QUERY_STRING'}) {
$query = "";
} else {
$query = $ENV{'QUERY_STRING'};
}
my @args = split('&', $query);
unpack_args(@args);
print <<END
<html>
<head>
<title>Daily Dinosaur Mirror
END
;
get_page();
$prev = $StripNumber - 1;
$next = $StripNumber + 1;
# These strips are missing for some reason?
if ($StripNumber == 1372) { $next = 1379; }
if ($StripNumber == 1379) { $prev = 1372; }
if ($prev > 0) {
print <
previous — —
— next
END
;
} else {
print <
first strip — — — next
END
;
}
print <
END
;
exit 0;