#!/usr/bin/perl
use warnings;
use strict;
use LWP::Simple;
use HTML::TableExtract;

my $file = 'earnings.dat';
my $url  = 
"http://www.earnings.com/fin/earnListing.jsp?date=2003-05-04";

# Be kind to the website, at least during testing!
# Get the $url only when $file is missing or more than 1 day old.
mirror($url, $file) unless -e $file or -M $file > 1;

# Slurp $file into $content.
my $content = do {
 local (*F, $/);
 open F, $file or die;
 <F>;
};

my $te = HTML::TableExtract->new(
  headers => [qw(Company Symbol Estimate Actual)],
);

$te->parse($content);

#use Data::Dumper;
#$Data::Dumper::Useqq = 1;

# Examine all matching tables
foreach my $ts ($te->table_states) {
  print "Table (", join(',', $ts->coords), "):\n";
  foreach my $row ($ts->rows) {
     foreach (@$row) {
       tr{ \t\n\xA0}{ }s;
       s{^\s+}{};
       s{\s+$}{};
     }
#    print Dumper $row;
    print join(',', @$row), "\n";
  }
}