PHP 获取网页内容的几个函数

内容摘要
这篇文章主要为大家详细介绍了PHP 获取网页内容的几个函数,具有一定的参考价值,可以用来参考一下。

稍微有点意义的函数是:get_content_by_socket(), get_url(), get_content_
文章正文

这篇文章主要为大家详细介绍了PHP 获取网页内容的几个函数,具有一定的参考价值,可以用来参考一下。

稍微有点意义的函数是:get_content_by_socket(), get_url(), get_content_url(), get_content_object 几个函数,也许能够给你点什么想法。经测试代码如下:

<?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 " OKn";
        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 " OKn";
        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 " OKn";
            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/1.1rn";
    $header .= "Accept: */*rn";
    $header .= "Accept-Language: zh-cnrn";
    $header .= "Accept-Encoding: gzip, deflatern";
    $header .= "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; InfoPath.1; .NET CLR 2.0.50727)rn";
    $header .= "Host: ". $host ."rn";
    $header .= "Connection: Keep-Alivern";
    //$header .= "Cookie: cnzz02=2; rtime=1; ltime=1148456424859; cnzz_eid=56601755-rnrn";
    $header .= "Connection: Closernrn";

    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="|--:**:--|"){
    $regx = "/hrefs*=s*['"]*([^>'"s]+)["'>]*s*(<b>.*?</b>)/i";
    preg_match_all($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;
}

?>


/***   代码来自php教程(www.idcnote.com)   ***/

注:关于PHP 获取网页内容的几个函数的内容就先介绍到这里,更多相关文章的可以留意

代码注释

作者:喵哥笔记

IDC笔记

学的不仅是技术,更是梦想!