PHP批量删除、清除UTF-8文件BOM头的代码实例
代码一：
复制代码 代码如下:
function checkBOM ($filename) {
global $auto;
$contents = file_get_contents($filename);
$charset[1] = substr($contents, 0, 1);
$charset[2] = substr($contents, 1, 1);
$charset[3] = substr($contents, 2, 1);
if (ord($charset[1]) == 239 && ord($charset[2]) == 187 && ord($charset[3]) == 191) {
if ($auto == 1) {
$rest = substr($contents, 3);
rewrite ($filename, $rest);
return ("BOM found, automatically removed.");
} else {
return ("BOM found.");
}
}
else return ("BOM Not Found.");
}
代码二：
复制代码 代码如下:
header('content-Type: text/html; charset=utf-8');
if(isset($_GET['dir'])){ //设置文件目录，如果没有设置，则自动设置为当前文件所在目录
$basedir=$_GET['dir'];
}else{
$basedir='.';
}
$auto=1;/*设置为1标示检测BOM并去除，设置为0标示只进行BOM检测，不去除*/
echo '当前查找的目录为：'.$basedir.'当前的设置是：';
echo $auto?'检测文件BOM同时去除检测到BOM文件的BOM
':'只检测文件BOM不执行去除BOM操作
';
checkdir($basedir);
function checkdir($basedir){
if($dh=opendir($basedir)){
while (($file=readdir($dh)) !== false){
if($file != '.' && $file != '..'){
if(!is_dir($basedir.'/'.$file)){
echo '文件: '.$basedir.'/'.$file .checkBOM($basedir.'/'.$file).'
';
}else{
$dirname=$basedir.'/'.$file;
checkdir($dirname);
}
}
}
closedir($dh);
}
}
function checkBOM($filename){
global $auto;
$contents=file_get_contents($filename);
$charset[1]=substr($contents,0,1);
$charset[2]=substr($contents,1,1);
$charset[3]=substr($contents,2,1);
if(ord($charset[1])==239 && ord($charset[2])==187 && ord($charset[3])==191){
if($auto==1){
$rest=substr($contents,3);
rewrite($filename,$rest);
return (' 找到BOM并已自动去除');
}else{
return (' 找到BOM');
}
}else{
return (' 没有找到BOM');
}
}
function rewrite($filename,$data){
$filenum=fopen($filename,'w');
flock($filenum,LOCK_EX);
fwrite($filenum,$data);
fclose($filenum);
}
?>
代码三：
复制代码 代码如下:
##把该文件放在需求去除BOM头的目录下跑一下却可。
if (isset ( $_GET ['dir'] )) { // config the basedir
$basedir = $_GET ['dir'];
} else {
$basedir = '.';
}
$auto = 1;
checkdir ( $basedir );
function checkdir($basedir) {
if ($dh = opendir ( $basedir )) {
while ( ($file = readdir ( $dh )) !== false ) {
if ($file != '.' && $file != '..') {
if (! is_dir ( $basedir . "/" . $file )) { // 如果是文件
echo "filename: $basedir/$file " . checkBOM ( "$basedir/$file" ) . "
";
} else {
$dirname = $basedir . "/" . $file; // 如果是目录
checkdir ( $dirname ); // 递归
}
}
}
closedir ( $dh );
}
}
function checkBOM($filename) {
global $auto;
$contents = file_get_contents ( $filename );
$charset [1] = substr ( $contents, 0, 1 );
$charset [2] = substr ( $contents, 1, 1 );
$charset [3] = substr ( $contents, 2, 1 );
if (ord ( $charset [1] ) == 239 && ord ( $charset [2] ) == 187 && ord ( $charset [3] ) == 191) { // BOM
// 的前三个字符的ASCII
// 码分别为
// 239
// 187
// 191
if ($auto == 1) {
$rest = substr ( $contents, 3 );
rewrite ( $filename, $rest );
return ("BOM found, automatically removed.");
} else {
return ("BOM found.");
}
} else
return ("BOM Not Found.");
}
function rewrite($filename, $data) {
$filenum = fopen ( $filename, "w" );
flock ( $filenum, LOCK_EX );
fwrite ( $filenum, $data );
fclose ( $filenum );
}
?>
二、Python
复制代码 代码如下:
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import os
def delBOM():
file_count = 0
bom_files = []
for dirpath, dirnames, filenames in os.walk('.'):
if(len(filenames)):
for filename in filenames:
file_count += 1
file = open(dirpath + "/" + filename, 'r+')
file_contents = file.read()
if(len(file_contents) > 3):
if(ord(file_contents[0]) == 239 and ord(file_contents[1]) == 187 and ord(file_contents[2]) == 191):
bom_files.append(dirpath + "/" + filename)
file.seek(0)
file.write(file_contents[3:])
print bom_files[-1], "BOM found. Deleted."
file.close()
print file_count, "file(s) found.", len(bom_files), "file(s) have a bom. Deleted."
if __name__ == "__main__":
delBOM()