php 將 HTML 轉換成文本

<?php
// $document 應包含一個 HTML 文檔。

// 本例將去掉 HTML 標記，javascript 代碼

// 和空白字符。還會將一些通用的

// HTML 實體轉換成相應的文本。


$search = array ("'<script[^>]*?>.*?</script>'si", // 去掉 javascript
                 "'<[/!]*?[^<>]*?>'si", // 去掉 HTML 標記
                 "'([rn])[s]+'", // 去掉空白字符
                 "'&(quot|#34);'i", // 替換 HTML 實體
                 "'&(amp|#38);'i",
                 "'&(lt|#60);'i",
                 "'&(gt|#62);'i",
                 "'&(nbsp|#160);'i",
                 "'&(iexcl|#161);'i",
                 "'&(cent|#162);'i",
                 "'&(pound|#163);'i",
                 "'&(copy|#169);'i",
                 "'&#(d+);'e"); // 作為 PHP 代碼運行

$replace = array ("",
                  "",
                  "1",
                  """,
                  "&",
                  "<",
                  ">",
                  " ",
                   chr(161),
                   chr(162),
                   chr(163),
                   chr(169),
                  "chr(1)");

$text = preg_replace ($search, $replace, $document);
?>