#!/usr/bin/env perl
# 
#   (C) 2001 Alan Donovan.
# 
#   Author: Alan Donovan <adonovan@lcs.mit.edu>
# 
#   extractcd -- extract CD cover information from Amazon web pages.
#                Use in conjunction with cdcover(1) to make inlay
#		 cards.
# 
#   $Id: extractcd,v 1.1.1.1 2002/08/23 13:40:34 adonovan Exp $
# 
#   This program is free software; you can redistribute it and/or
#   modify it under the terms of the GNU General Public License
#   as published by the Free Software Foundation; either version 2
#   of the License, or any later version.
# 
#   This program is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied waranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#   See the GNU General Public License for more details.
#   <http://www.gnu.org/copyleft/gpl.html>.
# 

sub restore()
{    
    my($i) = (@_);
    $i =~ s/&amp;/\&/g;	# restore '&'
    $i =~ s/&nbsp;/ /g;	# restore ' '
    $i =~ s/&lt;/\</g;	# restore '<'
    $i =~ s/&gt;/\>/g;	# restore '>'
    $i;
}

########################################################################

$usage="usage: extractcd <amazon-ASIN>\n";

(@ARGV == 1) || die $usage;

$ASIN = shift;

$url = "http://www.amazon.com/exec/obidos/ASIN/$ASIN";

# e.g. B00001ZWEF
print "Extracting CD info from Amazon...\n";

$page = `lynx -source '$url' | tee ASIN-$ASIN.html`;
($page eq "") && die "Can't open URL.\n";

$_= $page;

s/\n/ /g;	# make into 1 line

# get picture
if(m?(http://images.amazon.com/images/./$ASIN[\.\w]+\.gif)?)
{
    $pic = $1;
    system("wget $pic -O ASIN-$ASIN.gif"); 
}
elsif (m?(http://images.amazon.com/images/./$ASIN[\.\w]+\.jpg)?)
{
    $pic = $1;
    system("wget $pic -O ASIN-$ASIN.jpg"); 
    system("djpeg ASIN-$ASIN.jpg | ppmquant 256 | ppmtogif >ASIN-$ASIN.gif");
}
else
{
    die "Sorry: no picture!  Aborting.\n";
}

print "Picture:\n\t$pic\n\n";
system("xview ASIN-$ASIN.gif &");

# get title / artist:
/<b class=sans>(.*?)<\/b>.*?<a.*?>(.*?)<\/a>/;
$artist=&restore($2);
$title=&restore($1);
print "Artist:\n\t$artist\n\n";
print "Title:\n\t$title\n\n";


#
#  NB: Amazon uses upper/lower cases interchangeably
#

# get track listing
(/<b class="h1">Listen to Samples.*?<table.*?>(.*?)<\/table>/i) ||
    die "Can't get track listing!\n";
$_ = $1; # extract table contents
s/>Listen</></g; # remove 'Listen' buttons
s/<.*?>/ /g; # remove tags
$_=&restore($_);
s/\s*[0-9]+\.\s*/\n/g; # break into lines
s/^\s*//;    # trim leading space

open(OUT, ">ASIN-$ASIN.txt") || die "can't open file \`ASIN-$ASIN.txt' for output.\n";
print OUT "$_\n";
close(OUT);

s/\n/\n\t/g; # format for display
print "Tracks:\n\t$_\n\n";

# escape doublequotes for safety:
$artist =~ s/\"/\\\"/g;
$title  =~ s/\"/\\\"/g;
system("cdcover \"$artist\" \"$title\" \"ASIN-$ASIN.txt\" \"ASIN-$ASIN.gif\"");
$title =~ s/ //g; # remove spaces from filename (as does cdcover)
system("gv \"$title.ps\"");