|
|
復制代碼 代碼如下:
function ClearHtml($content,$allowtags='') {
mb_regex_encoding('UTF-8');
//replace MS special characters first
$search = array('/‘/u', '/’/u', '/“/u', '/”/u', '/—/u');
$replace = array('/'', '/'', '"', '"', '-');
$content = preg_replace($search, $replace, $content);
//make sure _all_ html entities are converted to the plain ascii equivalents - it appears
//in some MS headers, some html entities are encoded and some aren't
$content = html_entity_decode($content, ENT_QUOTES, 'UTF-8');
//try to strip out any C style comments first, since these, embedded in html comments, seem to
//prevent strip_tags from removing html comments (MS Word introduced combination)
if(mb_stripos($content, '/*') !== FALSE){
$content = mb_eregi_replace('#//*.*?/*/#s', '', $content, 'm');
}
//introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be
//'<1' becomes '< 1'(note: somewhat application specific)
$content = preg_replace(array('/<([0-9]+)/'), array('< $1'), $content);
$content = strip_tags($content, $allowtags);
//eliminate extraneous whitespace from start and end of line, or anywhere there are two or more spaces, convert it to one
$content = preg_replace(array('/^/s/s+/', '//s/s+$/', '//s/s+/u'), array('', '', ' '), $content);
//strip out inline css and simplify style tags
$search = array('#<(strong|b)[^>]*>(.*?)</(strong|b)>#isu', '#<(em|i)[^>]*>(.*?)</(em|i)>#isu', '#<u[^>]*>(.*?)</u>#isu');
$replace = array('<b>$2</b>', '<i>$2</i>', '<u>$1</u>');
$content = preg_replace($search, $replace, $content);
//on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears
//that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains
//some MS Style Definitions - this last bit gets rid of any leftover comments */
$num_matches = preg_match_all("http://<!--/u", $content, $matches);
if($num_matches){
$content = preg_replace('//<!--(.)*--/>/isu', '', $content);
}
return $content;
}
測試使用結果：
復制代碼 代碼如下:
<?php
$content = ' <!--[if gte mso 9]><xml><w:WordDocument><w:BrowserLevel>MicrosoftInterNETExplorer4</w:BrowserLevel><w:DisplayHorizontalDrawingGridEvery>0</w:DisplayHorizontalDrawingGridEvery><w:DisplayVerticalDrawingGridEvery>2</w:DisplayVerticalDrawingGridEvery><w:DocumentKind>DocumentNotSpecified</w:DocumentKind><w:DrawingGridVerticalSpacing>7.8</w:DrawingGridVerticalSpacing><w:View>Normal</w:View><w:Compatibility></w:Compatibility><w:Zoom>0</w:Zoom></w:WordDocument></xml><![endif]-->
<p class="p0" style="text-indent: 24.0000pt; margin-bottom: 0pt; margin-top: 0pt;"><span style="mso-spacerun: "yes"; font-size: 12.0000pt; font-family: "宋體";">《優伴戶外旅行》――讓旅行成為習慣！</span></p>越發忙碌的你，是否想給自己放個假？專注工作的你，是否還記得上一次鍛煉是什么時候？優伴戶外旅行，給你不一樣的旅行體驗：給心自由，便處處都是風景！</span></p>';
echo ClearHtml($content,'<p>');
/*
得到的結果：
<p >《優伴戶外旅行》--讓旅行成為習慣！</p>越發忙碌的你，是否想給自己放個假？專注工作的你，是否還記得上一次鍛煉是什么時候？優伴戶外旅行，給你不一樣的旅行體驗：給心自由，便處處都是風景！</p>
*/
?>
php技術：PHP去掉從word直接粘貼過來的沒有用格式的函數，轉載需保留來源！
鄭重聲明：本文版權歸原作者所有，轉載文章僅為傳播更多信息之目的，如作者信息標記有誤，請第一時間聯系我們修改或刪除，多謝。
