如何用正则表达式去掉html代码里面的字体和字号

2019-03-26 11:07:56 534 阅读 AI 写同款 · GEO 优化AI 选题数据监测一键分发 ›

YOLO11实战第056期-基于yolo11的无人机航拍铁路障碍物检测实战-数据集&源码&系统召回率曲线帮助评估模型在目标检测任务中，检测到真正目标的能力。通过这条曲线，可以评估模型在目标检测任务中的整体性能，并找到合适的置信度阈值，以在精确率和召回率之间做出最佳平衡。PR曲线越接近右上角，模型性能越好，曲线下方的面积越大，说明模型在不同置信度下的。这条曲线显示了随着置信度的增加，每个类别的召回率先变化较小，然后在某个点之后迅速下降。通过这条曲线，可以选择合适的置信度阈值，以优化模型的检测结果，平衡精确率和召回率。曲线都显示了随着召回率的增加，精确度略有下降的趋势，但整体上精确度保持在很高的水平。阅读详情

<span style=\"font-size: 19px;line-height: 150%;font-family: 宋体;\">;aa </span>
如何用正则表达式去掉html代码里面的字体和字号，如上

...全文

UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount()【已解决】 UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount()【已解决】阅读详情

artak

.NET社区 62,273 成员 668,968 内容

+ 关注 + 加入社区

切换为时间正序

诺维斯基 2019-04-27

打赏
举报

结果请查看：http://www.regexp.cn/Regex/index/5

秋的红果实 2019-03-31

打赏
举报


string input = "<span style=\"font-size: 19px;line-height: 150%;font-family: 宋体;\">oooou;aa </span>";
input = Regex.Replace(input, @"font-size:\s*\d+px;|font-family:\s*.+?;", "");

Response.Write("output:"+input);

注意：在web下输出，只能看到oooou;aa ，原因是html标签不显示，右击网页，看html源代码

肖半仙丶1413 2019-03-29

打赏
举报



    //清理CSS样式

    function CleanWord(oNode) {

        var bIgnoreFont = true; //是否忽略font标签

        var bRemoveStyles = true; //是否清理CSS样式

        var html = oNode;



        var r = /style="[^"]*"/g;

        var r1 = /style='[^']*'/g;

        html = html.replace(r, '');

        html = html.replace(r1, '');





        html = html.replace(/<o:p>\s*<\/o:p>/g, '');

        html = html.replace(/<o:p>[\s\S]*?<\/o:p>/g, ' ');



        // Remove mso-xxx styles.

        html = html.replace(/\s*mso-[^:]+:[^;"]+;?/gi, '');



        // Remove margin styles.

        html = html.replace(/\s*MARGIN: 0(?:cm|in) 0(?:cm|in) 0pt\s*;/gi, '');

        html = html.replace(/\s*MARGIN: 0(?:cm|in) 0(?:cm|in) 0pt\s*"/gi, "\"");



        html = html.replace(/\s*TEXT-INDENT: 0(?:cm|in)\s*;/gi, '');

        html = html.replace(/\s*TEXT-INDENT: 0(?:cm|in)\s*"/gi, "\"");



        html = html.replace(/\s*TEXT-ALIGN: [^\s;]+;?"/gi, "\"");



        html = html.replace(/\s*PAGE-BREAK-BEFORE: [^\s;]+;?"/gi, "\"");



        html = html.replace(/\s*FONT-VARIANT: [^\s;]+;?"/gi, "\"");



        html = html.replace(/\s*tab-stops:[^;"]*;?/gi, '');

        html = html.replace(/\s*tab-stops:[^"]*/gi, '');



        // Remove FONT face attributes.

        if (bIgnoreFont) {

            //html = html.replace(/\s*face="[^"]*"/gi, '');

            //html = html.replace(/\s*face=[^ >]*/gi, '');

            //html = html.replace(/\s*size="[^"]*"/gi, '');

            //html = html.replace(/\s*size=[^ >]*/gi, '');

            html = html.replace(/<\/?font[^>]*>/gi, "");

            html = html.replace(/<\/?FONT[^>]*>/gi, "");



            //html = html.replace(/\s*FONT-FAMILY:[^;"]*;?/gi, '');

        }

        // Remove Class attributes

        html = html.replace(/<(\w[^>]*) class=([^ |>]*)([^>]*)/gi, "<$1$3");



        // Remove styles.

        if (bRemoveStyles) {

            html = html.replace(/<(\w[^>]*) style="([^\"]*)"([^>]*)/gi, "<$1$3");

        }



        // Remove style, meta and link tags

        html = html.replace(/<STYLE[^>]*>[\s\S]*?<\/STYLE[^>]*>/gi, '');

        html = html.replace(/<(?:META|LINK)[^>]*>\s*/gi, '');



        // Remove empty styles.

        html = html.replace(/\s*style="\s*"/gi, '');



        html = html.replace(/<SPAN\s*[^>]*>\s* \s*<\/SPAN>/gi, ' ');



        html = html.replace(/<SPAN\s*[^>]*><\/SPAN>/gi, '');



        // Remove Lang attributes

        html = html.replace(/<(\w[^>]*) lang=([^ |>]*)([^>]*)/gi, "<$1$3");



        html = html.replace(/<SPAN\s*>([\s\S]*?)<\/SPAN>/gi, '$1');



        html = html.replace(/<FONT\s*>([\s\S]*?)<\/FONT>/gi, '$1');



        // Remove XML elements and declarations

        html = html.replace(/<\\?\?xml[^>]*>/gi, '');



        // Remove w: tags with contents.

        html = html.replace(/<w:[^>]*>[\s\S]*?<\/w:[^>]*>/gi, '');



        // Remove Tags with XML namespace declarations: <o:p><\/o:p>

        html = html.replace(/<\/?\w+:[^>]*>/gi, '');



        // Remove comments [SF BUG-1481861].

        html = html.replace(/<\!--[\s\S]*?-->/g, '');



        html = html.replace(/<(U|I|STRIKE)> <\/\1>/g, ' ');



        html = html.replace(/<H\d>\s*<\/H\d>/gi, '');



        // Remove "display:none" tags.

        html = html.replace(/<(\w+)[^>]*\sstyle="[^"]*DISPLAY\s?:\s?none[\s\S]*?<\/\1>/ig, '');



        // Remove language tags

        html = html.replace(/<(\w[^>]*) language=([^ |>]*)([^>]*)/gi, "<$1$3");



        // Remove onmouseover and onmouseout events (from MS Word comments effect)

        html = html.replace(/<(\w[^>]*) onmouseover="([^\"]*)"([^>]*)/gi, "<$1$3");

        html = html.replace(/<(\w[^>]*) onmouseout="([^\"]*)"([^>]*)/gi, "<$1$3");



        //        if (FCKConfig.CleanWordKeepsStructure) {//是否设置直接粘贴为Word

        //            // The original <Hn> tag send from Word is something like this: <Hn style="margin-top:0px;margin-bottom:0px">

        //            html = html.replace(/<H(\d)([^>]*)>/gi, '<h$1>');



        //            // Word likes to insert extra <font> tags, when using MSIE. (Wierd).

        //            html = html.replace(/<(H\d)><FONT[^>]*>([\s\S]*?)<\/FONT><\/\1>/gi, '<$1>$2<\/$1>');

        //            html = html.replace(/<(H\d)><EM>([\s\S]*?)<\/EM><\/\1>/gi, '<$1>$2<\/$1>');

        //        }

        //        else {

        //html = html.replace(/<H1([^>]*)>/gi, '<div$1><b><font size="6">');

        //html = html.replace(/<H2([^>]*)>/gi, '<div$1><b><font size="5">');

        //html = html.replace(/<H3([^>]*)>/gi, '<div$1><b><font size="4">');

        //html = html.replace(/<H4([^>]*)>/gi, '<div$1><b><font size="3">');

        //html = html.replace(/<H5([^>]*)>/gi, '<div$1><b><font size="2">');

        //html = html.replace(/<H6([^>]*)>/gi, '<div$1><b><font size="1">');

        html = html.replace(/<H1([^>]*)>/gi, '<div$1><b><font>');

        html = html.replace(/<H2([^>]*)>/gi, '<div$1><b><font>');

        html = html.replace(/<H3([^>]*)>/gi, '<div$1><b><font>');

        html = html.replace(/<H4([^>]*)>/gi, '<div$1><b><font>');

        html = html.replace(/<H5([^>]*)>/gi, '<div$1><b><font>');

        html = html.replace(/<H6([^>]*)>/gi, '<div$1><b><font>');



        html = html.replace(/<\/H\d>/gi, '<\/font><\/b><\/div>');



        // Transform <P> to <DIV>

        var re = new RegExp('(<P)([^>]*>[\\s\\S]*?)(<\/P>)', 'gi'); // Different because of a IE 5.0 error

        html = html.replace(re, '<div$2<\/div>');



        // Remove empty tags (three times, just to be sure).

        // This also removes any empty anchor

        html = html.replace(/<([^\s>]+)(\s[^>]*)?>\s*<\/\1>/g, '');

        html = html.replace(/<([^\s>]+)(\s[^>]*)?>\s*<\/\1>/g, '');

        html = html.replace(/<([^\s>]+)(\s[^>]*)?>\s*<\/\1>/g, '');

        //}

        return html;

    }

这个亲测过的

月夜惹人醉 2019-03-27

打赏
举报

var data = $(".product_id");

            for (var i = 0; i < data.length; i++) {

                var a = document.getElementById(data[i].id).innerHTML;

                a = a.replace(/(\n)/g, "");

                a = a.replace(/(\t)/g, "");

                a = a.replace(/(\r)/g, "");

                a = a.replace(/<\/?[^>]*>/g, "");

                a = a.replace(/\s*/g, "");

                if (a.length > 102) {

                    document.getElementById(data[i].id).innerHTML = a.substring(0, 102) + "...";

                }

                else {

                    document.getElementById(data[i].id).innerHTML = a;

                }

            }

最近写的一个去处富文本的内容，也是结合网上查到的内容写得，希望对你有帮助

以专业开发人员为伍 2019-03-26

打赏
举报

正则只能匹配简单的几个字母，又不懂语法分析、更不懂语义分析，怎么可能真正搞这类开发？

jianghupt 2019-03-26

打赏
举报

^font-size\d+\:\s\d+\;

如何用正则表达式去掉html代码里面的字体和字号

相关推荐