PHP 读取大文件程序代码

 /** 返回文件从X行到Y行的内容(支持php5、php4) 
 * @param string $filename 文件名
 * @param int $startLine 开始的行数
 * @param int $endLine 结束的行数
 * @return string
 */
function getFileLines($filename, $startLine = 1, $endLine=50, $method='rb') {
    $content = array();
    $count = $endLine - $startLine; 
    // 判断php版本（因为要用到SplFileObject，PHP>=5.1.0）
    if(version_compare(PHP_VERSION, '5.1.0', '>=')){
        $fp = new SplFileObject($filename, $method);
        $fp->seek($startLine-1);// 转到第N行, seek方法参数从0开始计数
        for($i = 0; $i <= $count; ++$i) {
            $content[]=$fp->current();// current()获取当前行内容
            $fp->next();// 下一行
        }
    }else{//PHP<5.1
        $fp = fopen($filename, $method);
        if(!$fp) return 'error:can not read file';
        for ($i=1;$i<$startLine;++$i) {// 跳过前$startLine行
            fgets($fp);
        }
        for($i;$i<=$endLine;++$i){
            $content[]=fgets($fp);// 读取文件行内容
        }
        fclose($fp);
    }
    return array_filter($content); // array_filter过滤：false,null,''
}  

echo '<pre>';
var_dump(getFileLines('test.php',35270,35280));
echo '</pre>'; 

function readBigFile($filename, $count = 20, $tag = "rn") {
$content = "";//最终内容
$current = "";//当前读取内容寄存
$step= 1;//每次走多少字符
$tagLen = strlen($tag);
$start = 0;//起始位置
$i = 0;//计数器
$handle = fopen($filename,'r+');//读写模式打开文件，指针指向文件起始位置
while($i < $count && !feof($handle)) {
fseek($handle, $start, SEEK_SET);//指针设置在文件开头
$current = fread($handle,$step);//读取文件
$content .= $current;//组合字符串
$start += $step;//依据步长向前移动
//依据分隔符的长度截取字符串最后免得几个字符
$substrTag = substr($content, -$tagLen);
if ($substrTag == $tag) { //判断是否为判断是否是换行或其他分隔符
$i++;
$content .= "<br />";
}
}
//关闭文件
fclose($handle);
//返回结果
return $content;
}
$filename = "csdn.sql";//需要读取的文件
$tag = "n";//行分隔符 注意这里必须用双引号
$count = 100;//读取行数
$data = readBigFile($filename,$count,$tag);
echo $data;

<?php
$discuz_url = 'http://127.0.0.1/discuz/'; //论坛地址
$login_url = $discuz_url . 'logging.php?action=login'; //登录页地址

$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'] = 'tianxin';
$post_fields['password'] = '111111';
//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('/<inputs*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文件放在网站的temp目录下
$cookie_file = tempnam('./temp', 'cookie');

$ch = curl_init($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);

//取到了关键的cookie文件就可以带着cookie文件去模拟发帖,fid为论坛的栏目ID
$send_url = $discuz_url . "post.php?action=newthread&fid=2";

$ch = curl_init($send_url);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
$contents = curl_exec($ch);
curl_close($ch);

//这里的hash码和登陆窗口的hash码的正则不太一样，这里的hidden多了一个id属性
preg_match('/<inputs*type="hidden"s*name="formhash"s*id="formhash"s*value="(.*?)"s*/>/i', $contents, $matches);
if (!empty($matches)) {
    $formhash = $matches[1];
} else {
    die('Not found the forumhash.');
}

$post_data = array();
//帖子标题
$post_data['subject'] = 'test2';
//帖子内容
$post_data['message'] = 'test2';
$post_data['topicsubmit'] = "yes";
$post_data['extra'] = '';
//帖子标签
$post_data['tags'] = 'test';
//帖子的hash码，这个非常关键！假如缺少这个hash码，discuz会警告你来路的页面不正确
$post_data['formhash'] = $formhash;

$ch = curl_init($send_url);
curl_setopt($ch, CURLOPT_REFERER, $send_url);       //伪装REFERER
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
$contents = curl_exec($ch);
curl_close($ch);

//清理cookie文件
unlink($cookie_file);
?>

<?php$cookie_file=tempnam('./temp','cookie');$login_url='/bbs/logging.php?action=login&amp;loginsubmit=yes';$post_fields='username=用户名&password=用户密码&referer=index.php&formhash=24eca8af&loginfield=username&questionid=0&loginsubmit=登录';$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);$url='/bbs';$ch =curl_init($url);curl_setopt($ch,CURLOPT_HEADER,0);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);curl_setopt($ch,CURLOPT_COOKIEFILE,$cookie_file);$contents=curl_exec($ch);echo $contents;curl_close($ch);?>

function msubstr($str, $start=0, $length, $charset="utf-8", $suffix=true)
    {
        if(function_exists("mb_substr"))
            return mb_substr($str, $start, $length, $charset);
        elseif(function_exists('iconv_substr')) {
            return iconv_substr($str,$start,$length,$charset);
        }
        $re['utf-8']   = "/[x01-x7f]|[xc2-xdf][x80-xbf]|[xe0-xef][x80-xbf]{2}|[xf0-xff][x80-xbf]{3}/";
        $re['gb2312'] = "/[x01-x7f]|[xb0-xf7][xa0-xfe]/";
        $re['gbk']    = "/[x01-x7f]|[x81-xfe][x40-xfe]/";
        $re['big5']   = "/[x01-x7f]|[x81-xfe]([x40-x7e]|xa1-xfe])/";
        preg_match_all($re[$charset], $str, $match);
        $slice = join("",array_slice($match[0], $start, $length));
        if($suffix) return $slice."…";
        return $slice;
    }

<?php
//$start：指定开始截取字符串的位置；$length指定截取字符的长度
function substr2($string, $start, $length)
{
$len = strlen($string);
if($len > $length)
{
   $str = '';
   $len1 = $start + $length; //截取到原字符串的位置
   for($i=$start; $i<$len1; $i++)
   {
    if(ord(substr($string, $i, 2)) > 0xa0) //在ASCII中，0xa0表示汉字的开始
    {
     $str.=substr($string, $i, 2);
     $i++;
    }
    else
    {
     $str.=substr($string, $i, 1);
    }
   }
   return $str.'...';
}
else
{
   return $string;
}
}

?>

<?php
function chinesesubstr($str, $start, $len){
   $strlen = $start + $len;
   for($i=0; $i<$strlen; $i++){
    if(ord(substr($str, $i, 1)) > 0xa0){
     $tmpstr .= substr($str, $i, 2);
     $i++;
    }else{
     $tmpstr .= substr($str, $i, 1);
    }
   }
   return $tmpstr;
}
$str = "waiting for you 等wait你back";
echo chinesesubstr($str, 0, 19)
?>

function addFileToZip($path, $zip) {
$handler = opendir($path); //打开当前文件夹由$path指定。
/*
循环的读取文件夹下的所有文件和文件夹
其中$filename = readdir($handler)是每次循环的时候将读取的文件名赋值给$filename，
为了不陷于死循环，所以还要让$filename !== false。
一定要用!==，因为如果某个文件名如果叫'0'，或者某些被系统认为是代表false，用!=就会停止循环
*/
while (($filename = readdir($handler)) !== false) {
if ($filename != "." &amp;&amp; $filename != "..") {//文件夹文件名字为'.'和‘..’，不要对他们进行操作
if (is_dir($path . "/" . $filename)) {// 如果读取的某个对象是文件夹，则递归
addFileToZip($path . "/" . $filename, $zip);
} else { //将文件加入zip对象
$zip->addFile($path . "/" . $filename);
}
}
}
@closedir($path);
}

$zip = new ZipArchive();
if ($zip->open('images.zip', ZipArchive::OVERWRITE) === TRUE) {
addFileToZip('images/', $zip); //调用方法，对要打包的根目录进行操作，并将ZipArchive的对象传递给方法
$zip->close(); //关闭处理的zip文件
}

<?php
$zip = new ZipArchive;
if ($zip->open('test.zip') === TRUE) {
  $index=$zip->locateName('example.php', ZIPARCHIVE::FL_NOCASE|ZIPARCHIVE::FL_NODIR);
  $contents = $zip->getFromIndex($index);
}
?>

<?php
$zip = new ZipArchive;
if ($zip->open('test.zip') === TRUE) {
 for($i = 0; $i < $zip->numFiles; $i++)
   {
     if(substr_count($zip->getNameIndex($i), 'example.php')>0){
       $contents = $zip->getFromIndex($i);            
      }
   }
}
?>