Parsing anchors in rendered html with php

parse_a_rendered.php

<?php
  $url = "http://www.imdb.com/movies-in-theaters/";
  $input = @file_get_contents($url) or die("Could not access file: $url");
  $regexp = "<a\s[^>]*href=(\"??)([^\" >]*?)\\1[^>]*>(.*)<\/a>";
  if(preg_match_all("/$regexp/siU", $input, $matches)) {
    // $matches[2] = array of link addresses
    // $matches[3] = array of link text - including HTML code
    echo "<pre>";
    var_dump($matches[2]);
    echo "</pre>";
  }
?>