去除html中的标签

1 function convertHtmlToText(inputText) { 
2      var returnText = "" + inputText; 
returnText = returnText.replace(/<\/div>/ig, '\r\n');
returnText = returnText.replace(/<\/li>/ig, '\r\n');
returnText = returnText.replace(//ig, ' * ');
returnText = returnText.replace(/<\/ul>/ig, '\r\n'); // -- remove BR tags and replace them with line break
returnText = returnText.replace(/<br\s*[\/]?>/gi, "\r\n"); // -- remove P and A tags but preserve what's inside of them
returnText = returnText.replace(/<p.*?>/gi, "\r\n");
returnText = returnText.replace(/<a.*href="(.*?)".*>(.*?)<\/a>/gi, " $2 ($1)"); // -- remove all inside SCRIPT and STYLE tags
returnText = returnText.replace(/<script.*>[\w\W]{1,}(.*?)[\w\W]{1,}<\/script>/gi, "");
returnText = returnText.replace(/<style.*>[\w\W]{1,}(.*?)[\w\W]{1,}<\/style>/gi, ""); //-- remove all else
returnText = returnText.replace(/<(?:.|\s)*?>/g, ""); //-- get rid of more than 2 multiple line breaks:
returnText = returnText.replace(/(?:(?:\r\n|\r|\n)\s*){2,}/gim, "\r\n\r\n"); //-- get rid of more than 2 spaces:
returnText = returnText.replace(/ +(?= )/g,''); //-- get rid of html-encoded characters:
returnText = returnText.replace(/ /gi," ");
returnText = returnText.replace(/&/gi,"&");
returnText = returnText.replace(/"/gi,'"');
returnText = returnText.replace(//gi,'>');
return returnText;
}

 

posted @ 2018-07-24 11:12  上海-乐海  阅读(359)  评论(0)    收藏  举报

如果想如我交流欢迎加入我建立前端qq讨论群:上海前端JS 招聘 求职