PHP抓取并保存網頁所有圖片

使用simple_html_dom.php一鍵保存url下所有圖片資源

<?php
include_once('simple_html_dom.php');
$url = $argv[1];

echo "start fetching images from $url".PHP_EOL.PHP_EOL;
$data = loadData($url);
$html = str_get_html($data);
$images = $html->find('img');
$srcs = array();
foreach ($images as $image) {
    $src = $image->attr['src'];
    saveImg($src);
    $srcs[] = $src;
}
echo PHP_EOL.'finish';
function loadData($url) {
    //useragent是為了防止淘寶等公司對腳本訪問的限制

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_USERAGENT, 'MMozilla/5.0 (Windows NT 6.1; rv:36.0) Gecko/20100101 Firefox/36.0');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5);
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
return curl_exec($ch);

}
function saveImg($src) {
    $path = dirname(FILE).'/images/'.date('YmdHis').rand(100, 999);
    $suffix = getSuffix($src);
    $fileName = $path.'.'.$suffix;
    if (file_put_contents($fileName, file_get_contents($src))) {
        echo "save $src success".PHP_EOL;
    }
}
function getSuffix($src) {
    $pattern = '/.+.(.+)/';
    preg_match($pattern, $src, $matches);
    $suffix = $matches[1];
    if (!in_array(strtolower($suffix), array('jpg','jpeg','png','bmp','gif'))) {
        $suffix = 'png';
    }

return $suffix;

}
?></pre>