-
-
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', '', $content, 'm');
- }
- //introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be
- //'$content = preg_replace(array('/
$content = strip_tags($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)>#isu', '#]*>(.*?)(em|i)>#isu', '#]*>(.*?)#isu');
- $replace = array('$2', '$2', '$1');
- $content = preg_replace($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 */
- $num_matches = preg_match_all("/\
-
《优伴户外旅行》——让旅行成为习惯! 越发忙碌的你,是否想给自己放个假?专注工作的你,是否还记得上一次锻炼是什么时候?优伴户外旅行,给你不一样的旅行体验:给心*,便处处都是风景!';
- echo ClearHtml($content,'
');
/*
- 得到的结果:
-
《优伴户外旅行》--让旅行成为习惯! 越发忙碌的你,是否想给自己放个假?专注工作的你,是否还记得上一次锻炼是什么时候?优伴户外旅行,给你不一样的旅行体验:给心*,便处处都是风景!
- */
- ?>
-
复制代码
|