php code for scrape links

#webdev #php

To scrape links from a webpage using PHP, you can use the file_get_contents function to fetch the HTML content and then parse it using the DOMDocument class. Here's a simple example: Site : SportsFire

<?php

// Function to scrape links from a given URL
function scrapeLinks($url) {
    // Get the HTML content of the webpage
    $html = file_get_contents($url);

    // Create a new DOMDocument instance
    $dom = new DOMDocument();

    // Suppress errors due to malformed HTML
    libxml_use_internal_errors(true);

    // Load the HTML content
    $dom->loadHTML($html);

    // Clear the errors
    libxml_clear_errors();

    // Create an array to hold the links
    $links = [];

    // Get all <a> elements
    $anchors = $dom->getElementsByTagName('a');

    // Loop through the anchors and collect the href attributes
    foreach ($anchors as $anchor) {
        $href = $anchor->getAttribute('href');
        // Add the link to the array if it's not empty
        if (!empty($href)) {
            $links[] = $href;
        }
    }

    return $links;
}

// Example usage
$url = 'https://www.example.com'; // Change this to the URL you want to scrape
$links = scrapeLinks($url);

// Print the scraped links
foreach ($links as $link) {
    echo $link . PHP_EOL;
}
?>