{ return file_get_contents($uri); } public function get($type) { $method = "_get_{$type}"; if (method_exists($this, $method)) { return call_user_method($method, $this); } } protected function _get_images() { if (!empty($this->markup)) { preg_match_all('/<img([^>]+)\\/>/i', $this->markup, $images); return !empty($images[1]) ? $images[1] : FALSE; } } protected function _get_links() { if (!empty($this->markup)) { preg_match_all('/<a([^>]+)\\>(.*?)\\<\\/a\\>/i', $this->markup, $links); return !empty($links[1]) ? $links[1] : FALSE; } } } $crawl = new Crawler('http://www.cricinfo.com/ci/content/current/match/fixtures/index.html'); $images = $crawl->get('images'); $links = $crawl->get('links'); foreach ($links as $value) { print $value . "\n"; }
<?php include_once "Crawler.class.php"; $LEVELS = 1; //how many levels deep do you want to Crawl? //CRAWL the page specified by url and look for all images or links if (empty($_REQUEST['url']) || $_REQUEST['url'] == " ") { $url = "http://bcmoney-mobiletv.com"; } else { $url = $_REQUEST['url']; } $crawl = new Crawler($url, $LEVELS); $images = $crawl->get('images'); $links = $crawl->get('links'); $embeds = $crawl->get('embeds'); //DEBUG (print parsed values) echo "<a href=\"{$url}\" target=\"_blank\">{$url}</a>"; echo "<br/><br/>IMAGES: <pre>"; print_r($images); echo "</pre><br/>LINKS: <pre>"; print_r($links); echo "</pre><br/>EMBEDS: <pre>"; print_r($embeds); echo "</pre>"; /* foreach ($images as $image) { ; } foreach ($links as $link) { ; } foreach ($embeds as $embed) { ; } */