php读取大文件实例代码

ini_set('memory_limit', '-1');
$file = 'access.log';
$data = file($file);
$line = $data[count($data)-1];
echo $line; 

file = 'access.log';
$file = escapeshellarg($file); // 对命令行参数进行安全转义
$line = `tail -n 1 $file`;
echo $line; 

$fp = fopen($file, "r");
$line = 10;
$pos = -2;
$t = " ";
$data = "";
while ($line > 0) {
    while ($t != "n") {
        fseek($fp, $pos, SEEK_END);
        $t = fgetc($fp);
        $pos --;
    }
    $t = " ";
    $data .= fgets($fp);
    $line --;
}
fclose ($fp);
echo $data; 

整个代码执行完成耗时 0.0095 (s)

$fp = fopen($file, "r");
$num = 10;
$chunk = 4096;
$fs = sprintf("%u", filesize($file));
$max = (intval($fs) == PHP_INT_MAX) ? PHP_INT_MAX : filesize($file);
for ($len=0; $len<$max; $len+=$chunk) {
    $seekSize = ($max - $len &gt; $chunk) ? $chunk : $max - $len;
    fseek($fp, ($len + $seekSize) * -1, SEEK_END);
    $readData = fread($fp, $seekSize) . $readData;

    if (substr_count($readData, "n") &gt;= $num + 1) {
        preg_match("!(.*?n){".($num)."}$!", $readData, $match);
        $data = $match[0];
        break;
    }
}
fclose($fp);
echo $data; 

function tail($fp,$n,$base=5) {
    assert($n>0);
    $pos = $n+1;
    $lines = array();
    while(count($lines) <= $n) {
        try{
            fseek($fp,-$pos,SEEK_END);
        } catch (Exception $e) {
            fseek(0);
            break;
        }
        $pos *= $base;
        while(!feof($fp)) {
            array_unshift($lines,fgets($fp));
        }
    }
    return array_slice($lines,0,$n);
}
var_dump(tail(fopen("access.log","r+"), 10)); 

<?php
if ($_COOKIE['u'] == 'admin') {
    echo 'Login success.';
} else {
    echo 'Login failed.';
}
?>

<?php

// 取得目? Url ?定的 cookie, ??入 cookie.txt (使用 POST)
function setUrlCookie($url, $postdata)
{
    //$cookie_jar = tempnam('./','cookie'); // Create file with unique file name (cookie*)
    $cookie_jar = './cookie.txt';

    $resource = curl_init();
    curl_setopt($resource, CURLOPT_URL, $url);
    curl_setopt($resource, CURLOPT_POST, 1);
    curl_setopt($resource, CURLOPT_POSTFIELDS, $postdata);
    curl_setopt($resource, CURLOPT_COOKIEFILE, $cookie_jar);
    curl_setopt($resource, CURLOPT_COOKIEJAR, $cookie_jar);
    curl_setopt($resource, CURLOPT_RETURNTRANSFER, 1);
    curl_exec($resource);

    return $resource;
}

// 取得此 Url 的?热?br /> function getUrlContent($resource, $url)
{
    curl_setopt($resource, CURLOPT_URL, $url);
    curl_setopt($resource, CURLOPT_RETURNTRANSFER, 1);
    $content = curl_exec($resource);

    return $content;
}

// Test:
// post to url and get cookie
/*
$url = 'http://localhost/login.php';
$postdata = 'username=admin&password=1234';
$resource = setUrlCookie($url, $postdata); // set cookie 'u' => 'admin' or anything

// get contents (need cookie check)
$url = 'http://localhost/check_login.php';
echo getUrlContent($resource, $url); // Login success.
*/
?>

<?php
$cookie_jar_index = 'cookie.txt';
 
$url = "http://www.111cn.net";
$params = "username=dudu&password=****";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_jar_index);
//curl_setopt($ch, CURLOPT_COOKIE, "fruit=apple; colour=red");
//上面代码是直接传递cookie信息，而非文件
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $params);
//curl_setopt($ch, CURLOPT_NOBODY, 1);//这个不能打开，否则无法生成cookie文件
ob_start();
curl_exec($ch);
curl_close($ch);
ob_clean();
 
$url = "http://www.111cn.net";
$ch2 = curl_init();
curl_setopt($ch2, CURLOPT_URL, $url);
curl_setopt($ch2, CURLOPT_COOKIEFILE, $cookie_jar_index);
ob_start();
curl_exec($ch2);
curl_close($ch2);
$rs = ob_get_contents(); //$rs就是返回的内容
ob_clean();
 
print_r($rs);
 
?>

??php
// 初始化一个 cURL 对象
$curl = curl_init();

// 设置你需要抓取的URL
curl_setopt($curl, CURLOPT_URL, ‘http://www.cmx8.cn’);

// 设置header
curl_setopt($curl, CURLOPT_HEADER, 1);

// 设置cURL 参数，要求结果保存到字符串中还是输出到屏幕上。
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);

// 运行cURL，请求网页
$data = curl_exec($curl);

// 关闭URL请求
curl_close($curl);

// 显示获得的数据
var_dump($data);

?>

 
!extension_loaded(‘curl’) && die(‘The curl extension is not loaded.’);  
 
$discuz_url = ‘http://www.111cn.net’;//论坛地址  
$login_url = $discuz_url .’/logging.php?action=login’;//登录页地址  
$get_url = $discuz_url .’/my.php?item=threads’; //我的帖子  
 
$post_fields = array();  
//以下两项不需要修改  
$post_fields['loginfield'] = ‘username’;  
$post_fields['loginsubmit'] = ‘true’;  
//用户名和密码，必须填写  
$post_fields['username'] = ‘lxvoip’;  
$post_fields['password'] = ’88888888′;  
//安全提问  
$post_fields['questionid'] = 0;  
$post_fields['answer'] = ”;  
//@todo验证码  
$post_fields['seccodeverify'] = ”;  
 
//获取表单FORMHASH  
$ch = curl_init($login_url);  
curl_setopt($ch, CURLOPT_HEADER, 0);  
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);  
$contents = curl_exec($ch);  
curl_close($ch);  
preg_match(‘/<input/s*type=”hidden”/s*name=”formhash”/s*value=”(.*?)”/s*//>/i’, $contents, $matches);  
if(!empty($matches)) {  
   $formhash = $matches[1];  
} else {  
   die(‘Not found the forumhash.’);  
}  
 
//POST数据，获取COOKIE  
$cookie_file = dirname(__FILE__) . ‘/cookie.txt’;  
//$cookie_file = tempnam(‘/tmp’);  
$ch = curl_init($login_url);  
curl_setopt($ch, CURLOPT_HEADER, 0);  
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);  
curl_setopt($ch, CURLOPT_POST, 1);  
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);  
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);  
curl_exec($ch);  
curl_close($ch);  
 
//带着上面得到的COOKIE获取需要登录后才能查看的页面内容  
$ch = curl_init($get_url);  
curl_setopt($ch, CURLOPT_HEADER, 0);  
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);  
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);  
$contents = curl_exec($ch);  
curl_close($ch);  
 
var_dump($contents);

function crawl_dou_request($url,$timeout=1){//php 模拟get
ob_start();
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_USERAGENT,”MISE 6.0″);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT,$timeout);
$file_msg = curl_exec($ch);
curl_close($ch);
return $file_msg;
}

$file = '/com/netingcn/error.log';
print_r(pathinfo($file));

结果为：

Array(
    [dirname] => /com/netingcn
    [basename] => error.log
    [extension] => log
    [filename] => error
)

$handler = fopen($file, 'w'); // w 会冲掉以前的内容、a 是追加
fwrite($handler, 'content');
fclose($handler);              //记得关闭打开的文件句柄9、文件读取操作有很多，下面简单介绍几个：

$handler = fopen($file, 'r');

while(!feof($handler)) {
    $datas[] = fgets($handler);  //读取一行内容
}

while(!feof($handler)) {
    $datas[] = fgetss($handler); //读取一行内容并过来html标记
}

while(!feof($handler)) {
    $datas[] = fgetcsv($handler); //读取一行内容并解析csv字段
}

$content = fread($handler, $strLength); //读取指定长读的字符

fclose($handler);

    $fp = fopen($filePath,"r ");
    $a = read_content_to_array($fp);   // 取得文本文件中的内容
    fclose($fp);

/**
    @desc read file content to array
    @params $fp: file resource
    @return array
*/
function read_content_to_array($fp){
    $i=0;
    $a = array();
    while (!feof ($fp)) {            //while循环，条件：没到文件的末端。

        $buffer = fgets($fp, MAX_BYTES_PER_ROW);  //fgets() 函数用于从文件中逐行读取文件,,读取的字节数。默认是 1024 字节。MAX_BYTES_PER_ROW为自定义的一个常量，读取的字节数

        $block=explode(STR_TD_DIVIDER,$buffer); //用分隔符对操作的一行（$buffer)进行分割，返回由字符串组成的数组。STR_TD_DIVIDER为自定义的一个常量，每行中各个字段之间的分隔符。

        $a[$i]=$block;
        $i=$i+1;                     //通过while循环，带动i值递增，实现数组构建。
    }
    return $a;
}

$handle = fopen($filePath, "w ");
fwrite($handle,$str);
fclose($handle);

function getValue(url, name) {
 var reg = new RegExp('(\?|&)' + name + '=([^&?]*)', 'i');
 var arr = url.match(reg);

 if (arr) {
  return arr[2];
 }

 return null;
}

function getKeyValue(url) {
 var result = {};
 var reg = new RegExp('([\?|&])(.+?)=([^&?]*)', 'ig');
 var arr = reg.exec(url);

 while (arr) {
  result[arr[2]] = arr[3];

  arr = reg.exec(url);
 }

 return result;
}

function getKeyValue($url) {
 $result = array();
 $mr = preg_match_all('/(?|&)(.+?)=([^&?]*)/i', $url, $matchs);

 if ($mr !== FALSE) {
  for ($i = 0; $i < $mr; $i++) {
   $result[$matchs[2][$i]] = $matchs[3][$i];
  }
 }

 return $result;
}