富文本样式文字图片处理

Moran墨染

已于 2022-07-25 08:42:34 修改

阅读量436

点赞数 1

文章标签：前端 javascript html

于 2022-07-25 08:41:40 首次发布

本文链接：https://blog.csdn.net/weixin_46824709/article/details/125967738

版权

export default const clearStyle = (input) => {
	var stringStripper = /(\n|\r| class=(")?Mso[a-zA-Z]+(")? ^p)/g;
	var output = input.replace(stringStripper, ' ');

	// 2. strip Word generated HTML comments
	var commentSripper = new RegExp('<!--(.*?)-->','g');
	var output = output.replace(commentSripper, '');

	// 3. remove tags leave content if any
	var tagStripper = new RegExp('<(/)*(meta|link|span|\\?xml:|st1:|o:|font)(.*?)>','gi');
	output = output.replace(tagStripper, '');

	// 4. Remove everything in between and including tags '<style(.)style(.)>'
	var badTags = ['style', 'script','applet','embed','noframes','noscript'];

	for (var i=0; i< badTags.length; i++) {
			tagStripper = new RegExp('<'+badTags[i]+'.*?'+badTags[i]+'(.*?)>', 'gi');
			output = output.replace(tagStripper, '');
	}

	// 5. remove attributes ' style="..."'
	var badAttributes = ['style', 'start'];
	for (var i=0; i< badAttributes.length; i++) {
			var attributeStripper = new RegExp(' ' + badAttributes[i] + '="(.*?)"','gi');
			output = output.replace(attributeStripper, '');
	}

	
	output = output.replace(/<\/?html.*?>/ig,'')
	output = output.replace(/<\/?body.*?>/ig,'')
	output = output.replace(/<\/?title.*?>/ig,'')
	output = output.replace(/<\/?head.*?>/ig,'')
	output = output.replace(/<\/?b>/ig,'')
	output = output.replace(/<\/?i.*?>/ig,'')
	output = output.replace(/[\s]+class=MsoNormal/ig,'')
	output = output.replace(/&#[0-9]+;/ig,'')
	output = output.replace(/&nbsp;/ig,'')
	output = output.replace(/<p\s+><\/p>/ig,'')
	// output = output.replace(/<a .*?>/ig,'')
	output = output.replace(/<\/a.*?>/ig,'')
	output = output.replace(/<\/?u>/ig,'')
	output = output.replace(/<\/pre>/ig,'')
	output = output.replace(/<\/?divcourier.*?>?/ig,'')
	return output;
}