use strict; use HTML::TableExtract; # I'm using LWP in the real code, but this is a minimalistic attempt at a working example my $html_doc_name = '/tmp/symbols.html'; my $html_doc_string; my $te = new HTML::TableExtract( headers => ['Character', 'Entity'] ); my $ts; my $row; undef $/; # the absence of this one little line always causes me so much trouble open(HTML, $html_doc_name) or die "Couldn't open html file: $!\n"; $html_doc_string = ; close(HTML) or die "Couldn't close html file: $!\n"; $te->parse($html_doc_string); # Examine all matching tables foreach $ts ($te->table_states) { print "Table (", join(',', $ts->coords), "):\n"; foreach $row ($ts->rows) { print join("\t\t", @$row), "\n"; } }