PHP script to scrape links from HTML files

gistfile1.txt

<?php
$links = shell_exec('egrep -o -r "<a[^<]+?(\w*)</a>" --include=*.html *');
$output;

foreach(preg_split("/(\r?\n)/", $links) as $line){
  $file = explode(':', $line)[0];

  preg_match('/(?<=href=")[^"]+?(?=")/', $line, $url_matches);
  $url = $url_matches[0];

  preg_match('/(?<=\>)[^<]+?(?=\<)/', $line, $text_matches);
  $text = trim($text_matches[0]);

  // Does the link open a new window?
  $new = preg_match('/target="_blank"/', $line) ? 'Y' : 'N';

  $output .= $file . "," . $text . "," . $url . "," . $new . "\n";
}

echo $output;
file_put_contents('links.csv', $output);