使用PHP简单网页抓取和内容分析

<?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
function get_content_by_socket($url, $host){
    $fp = fsockopen($host, 80) or die("open ". $url ." failed");
    $header = "get /".$url ." http/1.1/r/n";
    $header .= "accept: */*/r/n";
    $header .= "accept-language: zh-cn/r/n";
    $header .= "accept-encoding: gzip, deflate/r/n";
    $header .= "user-agent: mozilla/4.0 (compatible; msie 6.0; windows nt 5.1; sv1; maxthon; infopath.1; .net clr 2.0.50727)/r/n";
    $header .= "host: ". $host ."/r/n";
    $header .= "connection: keep-alive/r/n";
    //$header .= "cookie: cnzz02=2; rtime=1; ltime=1148456424859; cnzz_eid=56601755-/r/n/r/n";
    $header .= "connection: close/r/n/r/n";

    fwrite($fp, $header);
    while (!feof($fp)) {
        $contents .= fgets($fp, 8192);
    }
    fclose($fp);
    return $contents;
}

//获取指定内容里的url
function get_content_url($host_url, $file_contents){

    //$reg = '/^(#|javascript.*?|ftp:////.+|http:////.+|.*?href.*?|play.*?|index.*?|.*?asp)+$/i';
    //$reg = '/^(down.*?/.html|/d+_/d+/.htm.*?)$/i';
    $rex = "/([hh][rr][ee][ff])/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*/i";
    $reg = '/^(down.*?/.html)$/i';
    preg_match_all ($rex, $file_contents, $r);
    $result = ""; //array();
    foreach($r as $c){
        if (is_array($c)){
            foreach($c as $d){
                if (preg_match($reg, $d)){ $result .= $host_url . $d."/n"; }
            }
        }
    }
    return $result;
}

//获取指定内容中的多媒体文件
function get_content_object($str, $split="|--:**:--|"){    
    $regx = "/href/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*(<b>.*?<//b>)/i";
    preg_match_all($regx, $str, $result);

    if (count($result) == 3){
        $result[2] = str_replace("<b>多媒体： ", "", $result[2]);
        $result[2] = str_replace("</b>", "", $result[2]);
        $result = $result[1][0] . $split .$result[2][0] . "/n";
    }
    return $result;
}

?>