Source code file content

subversion / 2c.lt / stats_functions.php

<?php
function getExcerpt($content) {
  $text = html_entity_decode($content);
  $excerpt = array();
  //match all tags
  preg_match_all("|<[^>]+>(.*)</[^>]+>|", $text, $p, PREG_PATTERN_ORDER);
  for ($x = 0; $x < sizeof($p[0]); $x++) {
    //match tags containing "<p>"
    if (preg_match('<p>i', $p[0][$x])) {
      $strip = strip_tags($p[0][$x]);
      if (preg_match("/\./", $strip))
        $excerpt[] = $strip;
    }
    if (isset($excerpt[0])){
      preg_match("/([^.]+.)/", $strip,$matches);
      return $matches[1];
    }
  }
  return false;
}

function getMetaTitle($content){
  $pattern = "|<[\s]*title[\s]*>([^<]+)<[\s]*/[\s]*title[\s]*>|Ui";
  if(preg_match($pattern, $content, $match))
  return $match[1];
  else
  return false;
}

function getMetaDescription($content) {
  $metaDescription = false;
  $metaDescriptionPatterns = array("/<meta.+description.+content[\s]*=[\s]*\"([^\"]+)\"[^>]*>/Ui", "/<meta.+description.+content[\s]*=[\s]*'([^']+)'[^>]*>/Ui");
  foreach ($metaDescriptionPatterns as $pattern) {
    if (preg_match($pattern, $content, $match))
      $metaDescription = $match[1];
    break;
  }
  return $metaDescription;
}

$url = 'http://2c.lt/';             //url to scrape
$content = file_get_contents($url);
$title = getMetaTitle($content);
$description = getMetaDescription($content);
$excerpt = getExcerpt($content);
print "title: $title ";
print "<br />";
print "description: $description ";
print "<br />";
print "excerpt: $excerpt";

?>