The Code

This Perl script splits the advice page into two variables, based on the headings "in addition to" and "instead of." It then loops through those sections, using regular expressions to match the products' information. The script then formats and prints the information.

Save the following script to a file called get_advice.pl:

#!/usr/bin/perl -w
# get_advice.pl
#
# A script to scrape Amazon to retrieve customer buying advice
# Usage: perl get_advice.pl <asin>
use strict; use LWP::Simple;

# Take the ASIN from the command line.
my $asin = shift @ARGV or die "Usage: perl get_advice.pl <asin>\n";

# Assemble the URL from the passed ASIN.
my $url = "http://amazon.com/o/tg/detail/-/$asin/?vi=advice";

# Set up unescape-HTML rules. Quicker than URI::Escape.
my %unescape = ('&quot;'=>'"', '&amp;'=>'&', '&nbsp;'=>' ');
my $unescape_re = join '|' => keys %unescape;

# Request the URL.
my $content = get($url);
die "Could not retrieve $url" unless $content;

# Get our matching data.
my ($inAddition) = (join '', $content) &return;
    =~ m!in addition to(.*?)(instead of)?</td></tr>!mis;
my ($instead)    = (join '', $content) &return;
    =~ m!recommendations instead of(.*?)</table>!mis;

# Look for "in addition to" advice.
if ($inAddition) { print "-- In Addition To --\n\n";
   while ($inAddition =~ m!<td width=10>(.*?)</td>\n<td width=90%>.*?ASIN/&return;
(.*?)/.*?">(.*?)</a>.*?</td>.*?<td width=10% align=center>(.*?)</td>!mgis) {
       my ($place,$thisAsin,$title,$number) = ($1||'',$2||'',$3||'',$4||'');
       $title =~ s/($unescape_re)/$unescape{$1}/migs; #unescape HTML 
       print "$place $title ($thisAsin)\n(Recommendations: $number)\n\n";
   }
}

# Look for "instead of" advice.
if ($instead) { print "-- Instead Of --\n\n";
    while ($instead =~ m!<td width=10>(.*?)</td>\n<td width=90%>.*?ASIN/(.&return;
*?)/.*?">(.*?)</a>.*?</td>.*?<td width=10% align=center>(.*?)</td>!mgis) {
        my ($place,$thisAsin,$title,$number) &return;
          = ($1||'',$2||'',$3||'',$4||'');
        $title =~ s/($unescape_re)/$unescape{$1}/migs; #unescape HTML 
        print "$place $title ($thisAsin)\n(Recommendations: $number)\n\n";
    }
}