fork download 
  1. <?php
  2.  
  3. function get_url_metadata($url) {
  4.   $metadata = array();
  5.  
  6.   // 1. Fetch the HTML content of the URL
  7.   $ch = curl_init();
  8.   curl_setopt($ch, CURLOPT_URL, $url);
  9.   curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  10.   curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); // Follow redirects
  11.   curl_setopt($ch, CURLOPT_USERAGENT, 'Your_Bot_Name'); // Set a user agent
  12.   $html = curl_exec($ch);
  13.   curl_close($ch);
  14.  
  15.   if ($html === false) {
  16.     return $metadata; // Handle errors gracefully
  17.   }
  18.  
  19.   // 2. Use a DOM parser to extract data
  20.   $doc = new DOMDocument();
  21.   @$doc->loadHTML($html); // Suppress warnings on invalid HTML
  22.  
  23.   // 2.1 Extract title
  24.   $title_tags = $doc->getElementsByTagName('title');
  25.   if ($title_tags->length > 0) {
  26.     $metadata['title'] = $title_tags->item(0)->nodeValue;
  27.   }
  28.  
  29.   // 2.2 Extract meta tags
  30.   $meta_tags = $doc->getElementsByTagName('meta');
  31.   foreach ($meta_tags as $meta) {
  32.     $property = $meta->getAttribute('property');
  33.     $name = $meta->getAttribute('name');
  34.     $content = $meta->getAttribute('content');
  35.  
  36.     if (!empty($property)) {
  37.       $metadata[$property] = $content;
  38.     } elseif (!empty($name)) {
  39.       $metadata[$name] = $content;
  40.     }
  41.   }
  42.  
  43.   // 2.3 Extract description (common case)
  44.   if (isset($metadata['og:description']) || isset($metadata['description'])) {
  45.     $metadata['description'] = isset($metadata['og:description']) ? $metadata['og:description'] : $metadata['description'];
  46.   }
  47.  
  48.   // 2.4 Extract image (common case)
  49.   if (isset($metadata['og:image'])) {
  50.     $metadata['image'] = $metadata['og:image'];
  51.   }
  52.  
  53.   return $metadata;
  54. }
  55.  
  56. // Example usage:
  57. $url = 'https://www.google.com';
  58. $metadata = get_url_metadata($url);
  59.  
  60. print_r($metadata);
  61.  
  62. ?>
  63.  
Success #stdin #stdout 0.04s 25892KB
comments (?)
stdin 
Standard input is empty
stdout 
Array
(
)
https://ideone.com/RkrIW3
language:
PHP (php 7.3.5)
created:
2 days ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!