首頁  >  文章  >  後端開發  >  php去掉從word直接貼過來的無用格式的函數

php去掉從word直接貼過來的無用格式的函數

WBOY
WBOY原創
2016-07-25 09:08:10757瀏覽
  1. function ClearHtml($content,$allowtags='') {

  2. mb_regex_encoding('UTF-8');

  3. //replace MS special characters first
  4. $search = array('/‘/u', '/’/u', '/“/u', '/”/u', '/—/u');
  5. $replace = array(''', ''', '"', '"', '-');
  6. $content = preg_replace($search, $replace, $content);
  7. //make sure _all_ html entities are converted to the plain ascii equivalents - it appears
  8. //in some MS headers, some html entities are encoded and some aren't
  9. $content = html_entity_decode($content, ENT_QUOTES, 'UTF-8');
  10. //try to strip out any C style comments first, since these, embedded in html comments, seem to
  11. //prevent strip_tags from removing html comments (MS Word introduced combination)
  12. if(mb_stripos($content, '/*') !== FALSE){
  13. $content = mb_eregi_replace('#/*.*?*/#s', '', $content, 'm');
  14. }
  15. //introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be
  16. //'<1' becomes '< 1'(note: somewhat application specific)
  17. $content = preg_replace(array('/<([0-9]+)/'), array('< '), $content);

  18. $content = strip_tags($content, $allowtags);

  19. //eliminate extraneous whitespace from start and end of line, or anywhere there are two or more spaces, convert it to one
  20. $content = preg_replace(array('/^ss+/', '/ss+$/', '/ss+/u'), array('', '', ' '), $content);
  21. //strip out inline css and simplify style tags
  22. $search = array('#<(strong|b)[^>]*>(.*?)#isu', '#<(em|i)[^>]*>(.*?)#isu', '#]*>(.*?)#isu');
  23. $replace = array('', '', '');
  24. $content = preg_replace($search, $replace, $content);

  25. //on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears

  26. //that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains
  27. //some MS Style Definitions - this last bit gets rid of any leftover comments */
  28. $num_matches = preg_match_all("//isu', '', $content);
  29. }
  30. return $content;
  31. }
  32. ?>

复制代码

测试:

  1. $content = '

  2. 《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:给心自由,便处处都是风景!

    ';
  3. echo ClearHtml($content,'

    ');

  4. /*

  5. 得到的结果:
  6. 《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:给心自由,便处处都是风景!

  7. */
  8. ?>

复制代码


陳述:
本文內容由網友自願投稿,版權歸原作者所有。本站不承擔相應的法律責任。如發現涉嫌抄襲或侵權的內容,請聯絡admin@php.cn