- Mar 16, 2012
- 356
- 376
Here's a nice little script that will scrape google image results:
Example: http://blogoscoped.com/temp/google-image-scraper-2007.html
PHP:
<?php /**/ ?><?header("Content-type: text/html; charset=utf-8");?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "DTD/xhtml1-strict.dtd"><html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head> <title>Get Images</title> </head><body> <? $results = getGoogleImages('horses');foreach ($results as $result) { echo '<p><a href="' . htmlentities($result['url']) . '">' . '<img src="' . htmlentities($result['thumbnail']) . '" alt="" ' . 'oncontextmenu="' . "this.src='" . htmlentities($result['image']) . "';" . 'return false;" ' . 'style="border: 0px solid black" /></a><br />' . '<em>' . htmlentities($result['description']) . '</em>' . '</p>';} ?> </body></html><? function getGoogleImages($q, $doSafeSearch = false){ $results = array(); $safe = ($doSafeSearch) ? 'on' : 'off'; $url = 'http://images.google.com/images?safe=' . $safe . '&q=' . urlencode($q); //// file_get_contents is disabled - must use curl// $result = file_get_contents($url); $ch = curl_init($url); $handle = fopen("page1.txt", "w"); curl_setopt($ch, CURLOPT_FILE, $handle); curl_setopt($ch, CURLOPT_HEADER, 0); curl_exec($ch); curl_close($ch); fclose($handle); $handle = fopen("page1.txt", "r"); $result = ''; while (!feof($handle)) { $result .= fread($handle, 8192); } fclose($handle);// $result = file_get_contents($url);// file_get_contents is disabled - must use curl//// $from = 'dyn.Img("'; $startPos = strPos($result, $from); $endPos = strPos($result, ');dyn.updateStatus'); $functions = substr( $result, $startPos + strlen($from), $endPos ); $functions = explode('");dyn.Img("', $functions); foreach ($functions as $f) { $i = count($results); list($results[$i]['url'], $v1, $hash, $results[$i]['image'], $results[$i]['width'], $results[$i]['height'], $results[$i]['description'], $v2, $v3, $more, $extension, $domain) = explode('","', $f); list($results[$i]['url'], $params) = explode('&h', $results[$i]['url']); $prefix = 'http://tbn0.google.com/images?q=tbn:'; $results[$i]['thumbnail'] = $prefix . $hash . ':' . $results[$i]['image']; $results[$i]['description'] = strip_tags($results[$i]['description']); } return $results;} ?>Example: http://blogoscoped.com/temp/google-image-scraper-2007.html