网络爬虫脚本

#!/usr/local/bin/php -q
<?php
/**
 * Created by PhpStorm.
 * User: jackqqxu
 * Date: 14-9-12
 * Time: 上午12:34
 *  解析一个目录下面的文件，分析所有的静态资源然后下载下来；
 */
//echo "请输入需要提取的文件路径:\n";
//$path = fread(STDIN, 100);
//echo "程序即将读取 $path 路径下面的文件\n";
//echo "请输入需要提取的文件类型：\n";
//$type = fread(STDIN, 100);
// Open a known directory, and proceed to read its contents
//$path = '/Users/jackqqxu/Desktop/task/game/a_grain_of_truth_files/css/';
$destPath = '/Users/jackqqxu/task/aliyunsvn/health/grain/views/locations/'; //静态文件html
$sourcePath = '/Users/jackqqxu/task/aliyunsvn/health/grain/js/'; //静态文件html
//$baseUrl = 'http://www.zamolski.com/agot/resources/stylesheets/';
$netSourceUrl = 'http://www.zamolski.com/agot/views/locations/'; //现在获取位置信息
//$type = '.css';
$type = '.js';  //很多需要获取定位的位置信息；
$typeLen = strlen($type);
//echo 'r=' . realpath('/Users/jackqqxu/Desktop/task/game/a_grain_of_truth_files/css/../images/ui/frame_h.png') . "\n\n";
//echo "the programe will read the $type from the $path\n";
//if (!is_dir($destPath)) {
//    exec('mkdir -p ' . $destPath);
//}
    if ($dh = opendir($sourcePath)) {
        while (($file = readdir($dh)) !== false) {
            $fileType = filetype($sourcePath . $file);
            if ($fileType != 'file') {
                continue;
            }
//            echo 'f=' . $file . substr($file, strlen($file)-$typeLen) . "\n";
            if (substr($file, strlen($file)-$typeLen) == $type) {   //类型相同
//                echo "filename: $file : filetype: " . filetype($path . $file) . "\n";
                echo '$sourcePath . $file=' . $sourcePath . $file . "\n";
                $fileContentArr = file($sourcePath . $file);
                foreach($fileContentArr as $fileLine) {
//                    if ($fileLine =~ /url\((.*?)\)/){
//                    if (preg_match_all("/url\((.*?)\)/", $fileLine, $matches))  {   //css中通过url获取其他图片；
                    if (preg_match_all("/gotoLocation\(\"(.*?)\"\)/", $fileLine, $matches))  {   //中通过关键词获取其他文件；
//                        print_r($matches);exit;
//                        foreach($matches[1] as $matchImgUrl) {
                        foreach($matches[1] as $matchUrl) {
                            $sourceUrl = $netSourceUrl . $matchUrl . '.html';
                            echo 'n='.$sourceUrl."\n";//exit;
                            $descFile = $destPath . $matchUrl . '.html';
//                            echo 'fs=' . function_exists('realpath');
//                            echo 'ni=' . $newImgFile."\n";//exit;
//                            echo 'mkdir -p=' . dirname($newImgFile);
//                            exec('mkdir -p ' . dirname($newImgFile));
                            $ret = file_put_contents($descFile, file_get_contents($sourceUrl));
                            if ($ret) {
                                echo "文件$descFile 写入成功\n";
//                                exit;
                            }
//                            exit;
                        }
                    }
                }
            }
        }
        closedir($dh);
    }
?>