日期:2014-05-17  浏览次数:20512 次

php网页分析 内容抓取 爬虫 文件分析
<?php

//获取所有内容url保存到文件
function get_index($save_file, $prefix="index_"){
    $count = 68;
    $i = 1;
    if (file_exists($save_file)) @unlink($save_file);
    $fp = fopen($save_file, "a+") or die("Open ". $save_file ." failed");
    while($i<$count){
        $url = $prefix . $i .".htm";
        echo "Get ". $url ."...";
        $url_str = get_content_url(get_url($url));
        echo " OK\n";
        fwrite($fp, $url_str);
        ++$i;
    }
    fclose($fp);
}

//获取目标多媒体对象
function get_object($url_file, $save_file, $split="|--:**:--|"){
    if (!file_exists($url_file)) die($url_file ." not exist");
    $file_arr = file($url_file);
    if (!is_array($file_arr) || empty($file_arr)) die($url_file ." not content");
    $url_arr = array_unique($file_arr);
    if (file_exists($save_file)) @unlink($save_file);
    $fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
    foreach($url_arr as $url){
        if (empty($url)) continue;
        echo "Get ". $url ."...";
        $html_str = get_url($url);
        echo $html_str;
        echo $url;
        exit;
        $obj_str = get_content_object($html_str);
        echo " OK\n";
        fwrite($fp, $obj_str);
    }
    fclose($fp);
}

//遍历目录获取文件内容
function get_dir($save_file, $dir){
    $dp = opendir($dir);
    if (file_exists($save_file)) @unlink($save_file);
    $fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
    while(($file = readdir($dp)) != false){
        if ($file!="." && $file!=".."){
            echo "Read file ". $file ."...";
            $file_content = file_get_contents($dir . $file);
            $obj_str = get_content_object($file_content);
            echo " OK\n";
            fwrite($fp, $obj_str);
        }
    }
    fclose($fp);
}


//获取指定url内容
function get_url($url){
    $reg = '/^http:\/\/[^\/].+$/';
    if (!preg_match($reg, $url)) die($url ." invalid");
    $fp = fopen($url, "r") or die("Open url: ". $url ." failed.");
    while($fc = fread($fp, 8192)){
        $content .= $fc;
    }
    fclose($fp);
    if (empty($content)){
        die("Get url: ". $url ." content failed.");
    }
    return $content;
}

//使用socket获取指定网页