use HTML::TreeBuilder::XPath; my $tree = HTML::TreeBuilder::XPath->new; $tree->parse_file("/path/to/file.html"); $tree->eof; my @links = $tree->findnodes('//a') ; for my $link ( @links ){ print $link->attr('href'), "\n"; } #### my @links = $tree->findnodes('//td/a') ; for my $link ( @links ){ print $link->attr('href'), "\n"; } #### /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0001.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0002.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0003.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0004.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0005.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0006.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0007.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0008.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0009.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365-0010.txt /Archives/edgar/data/1050122/000092735601000365/0000927356-01-000365.txt