html解析到word并支持数学公式的解决方式？

Question

现在遇到个难解的问题，我们项目中使用三方题库试题时，线下教师有个需求，就是将题目导出到word（本质就是html导出到word），详细要求要在Java后端支持图片（自动下载）、数学公式（也包括化学和物理等公式，基础是“LeteX”）、html的所有样式，我们之前使用过“spire.doc”，但是它除了对解析公式不支持外，收费还真是挺贵的，后来用的“XWPFDocument”这一系列的方式解析的，但是它对html原有内嵌样式无法支持，图片位置也基本无法还原，综上所述，各位朋友有没有更成熟的方式，希望赐教下。

Answer 1

精心整理了两种方法，希望您能采纳

方法一

1. 打开网页后单击浏览器菜单栏的“文件”-->另存为，然后选择“网页，全部htm，html”格式；

1. 我们打开Word，然后选择Word菜单栏的“文件”-->打开，找到刚才保存文件的地方，选择打开；

1. 打开以后我们删除一些不需要的地方，比如：顶部和底部的，那些对于我们来说都没什么用，我们要主要就是要内容。然后打开菜单栏的“表格”-->转换-->表格转换为文本，将一些文档中的表格一一去掉。

方法二：通过jquery.wordexport.js导出word

备注：兼容IE9以上

大概浏览了下jquery.wordexport.js插件的代码，了解到了通过该插件可以导出文本和图片，而图片首先通过canvas的形式

绘制，文本则需要再依赖FileSaver.js插件，FileSaver.js插件则主要通过H5的文件操作新特性new Blob()和new FileReader()

来实现文本的导出。

插件源码：

FileSaver.js

/* FileSaver.js
 * A saveAs() FileSaver implementation.
 * 1.3.2
 * 2016-06-16 18:25:19
 *
 * By Eli Grey, http://eligrey.com
 * License: MIT
 *   See https://github.com/eligrey/FileSaver.js/blob/master/LICENSE.md
 */

/*global self */
/*jslint bitwise: true, indent: 4, laxbreak: true, laxcomma: true, smarttabs: true, plusplus: true */

/*! @source http://purl.eligrey.com/github/FileSaver.js/blob/master/FileSaver.js */

var saveAs = saveAs || (function(view) {
        "use strict";
        // IE <10 is explicitly unsupported
        if (typeof view === "undefined" || typeof navigator !== "undefined" && /MSIE [1-9]\./.test(navigator.userAgent)) {
            return;
        }
        var
            doc = view.document
        // only get URL when necessary in case Blob.js hasn't overridden it yet
            , get_URL = function() {
                return view.URL || view.webkitURL || view;
            }
            , save_link = doc.createElementNS("http://www.w3.org/1999/xhtml", "a")
            , can_use_save_link = "download" in save_link
            , click = function(node) {
                var event = new MouseEvent("click");
                node.dispatchEvent(event);
            }
            , is_safari = /constructor/i.test(view.HTMLElement)
            , is_chrome_ios =/CriOS\/[\d]+/.test(navigator.userAgent)
            , throw_outside = function(ex) {
                (view.setImmediate || view.setTimeout)(function() {
                    throw ex;
                }, 0);
            }
            , force_saveable_type = "application/octet-stream"
        // the Blob API is fundamentally broken as there is no "downloadfinished" event to subscribe to
            , arbitrary_revoke_timeout = 1000 * 40 // in ms
            , revoke = function(file) {
                var revoker = function() {
                    if (typeof file === "string") { // file is an object URL
                        get_URL().revokeObjectURL(file);
                    } else { // file is a File
                        file.remove();
                    }
                };
                setTimeout(revoker, arbitrary_revoke_timeout);
            }
            , dispatch = function(filesaver, event_types, event) {
                event_types = [].concat(event_types);
                var i = event_types.length;
                while (i--) {
                    var listener = filesaver["on" + event_types[i]];
                    if (typeof listener === "function") {
                        try {
                            listener.call(filesaver, event || filesaver);
                        } catch (ex) {
                            throw_outside(ex);
                        }
                    }
                }
            }
            , auto_bom = function(blob) {
                // prepend BOM for UTF-8 XML and text/* types (including HTML)
                // note: your browser will automatically convert UTF-16 U+FEFF to EF BB BF
                if (/^\s*(?:text\/\S*|application\/xml|\S*\/\S*\+xml)\s*;.*charset\s*=\s*utf-8/i.test(blob.type)) {
                    return new Blob([String.fromCharCode(0xFEFF), blob], {type: blob.type});
                }
                return blob;
            }
            , FileSaver = function(blob, name, no_auto_bom) {
                if (!no_auto_bom) {
                    blob = auto_bom(blob);
                }
                // First try a.download, then web filesystem, then object URLs
                var
                    filesaver = this
                    , type = blob.type
                    , force = type === force_saveable_type
                    , object_url
                    , dispatch_all = function() {
                        dispatch(filesaver, "writestart progress write writeend".split(" "));
                    }
                // on any filesys errors revert to saving with object URLs
                    , fs_error = function() {
                        if ((is_chrome_ios || (force && is_safari)) && view.FileReader) {
                            // Safari doesn't allow downloading of blob urls
                            var reader = new FileReader();
                            reader.onloadend = function() {
                                var url = is_chrome_ios ? reader.result : reader.result.replace(/^data:[^;]*;/, 'data:attachment/file;');
                                var popup = view.open(url, '_blank');
                                if(!popup) view.location.href = url;
                                url=undefined; // release reference before dispatching
                                filesaver.readyState = filesaver.DONE;
                                dispatch_all();
                            };
                            reader.readAsDataURL(blob);
                            filesaver.readyState = filesaver.INIT;
                            return;
                        }
                        // don't create more object URLs than needed
                        if (!object_url) {
                            object_url = get_URL().createObjectURL(blob);
                        }
                        if (force) {
                            view.location.href = object_url;
                        } else {
                            var opened = view.open(object_url, "_blank");
                            if (!opened) {
                                // Apple does not allow window.open, see https://developer.apple.com/library/safari/documentation/Tools/Conceptual/SafariExtensionGuide/WorkingwithWindowsandTabs/WorkingwithWindowsandTabs.html
                                view.location.href = object_url;
                            }
                        }
                        filesaver.readyState = filesaver.DONE;
                        dispatch_all();
                        revoke(object_url);
                    }
                    ;
                filesaver.readyState = filesaver.INIT;

                if (can_use_save_link) {
                    object_url = get_URL().createObjectURL(blob);
                    setTimeout(function() {
                        save_link.href = object_url;
                        save_link.download = name;
                        click(save_link);
                        dispatch_all();
                        revoke(object_url);
                        filesaver.readyState = filesaver.DONE;
                    });
                    return;
                }

                fs_error();
            }
            , FS_proto = FileSaver.prototype
            , saveAs = function(blob, name, no_auto_bom) {
                return new FileSaver(blob, name || blob.name || "download", no_auto_bom);
            }
            ;
        // IE 10+ (native saveAs)
        if (typeof navigator !== "undefined" && navigator.msSaveOrOpenBlob) {
            return function(blob, name, no_auto_bom) {
                name = name || blob.name || "download";

                if (!no_auto_bom) {
                    blob = auto_bom(blob);
                }
                return navigator.msSaveOrOpenBlob(blob, name);
            };
        }

        FS_proto.abort = function(){};
        FS_proto.readyState = FS_proto.INIT = 0;
        FS_proto.WRITING = 1;
        FS_proto.DONE = 2;

        FS_proto.error =
            FS_proto.onwritestart =
                FS_proto.onprogress =
                    FS_proto.onwrite =
                        FS_proto.onabort =
                            FS_proto.onerror =
                                FS_proto.onwriteend =
                                    null;

        return saveAs;
    }(
        typeof self !== "undefined" && self
        || typeof window !== "undefined" && window
        || this.content
    ));
// `self` is undefined in Firefox for Android content script context
// while `this` is nsIContentFrameMessageManager
// with an attribute `content` that corresponds to the window

if (typeof module !== "undefined" && module.exports) {
    module.exports.saveAs = saveAs;
} else if ((typeof define !== "undefined" && define !== null) && (define.amd !== null)) {
    define([], function() {
        return saveAs;
    });
}

jquery.wordexport.js

if (typeof jQuery !== "undefined" && typeof saveAs !== "undefined") {
    (function($) {
        $.fn.wordExport = function(fileName) {
            fileName = typeof fileName !== 'undefined' ? fileName : "jQuery-Word-Export";
            var static = {
                mhtml: {
                    top: "Mime-Version: 1.0\nContent-Base: " + location.href + "\nContent-Type: Multipart/related; boundary=\"NEXT.ITEM-BOUNDARY\";type=\"text/html\"\n\n--NEXT.ITEM-BOUNDARY\nContent-Type: text/html; charset=\"utf-8\"\nContent-Location: " + location.href + "\n\n<!DOCTYPE html>\n<html>\n_html_</html>",
                    head: "<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">\n<style>\n_styles_\n</style>\n</head>\n",
                    body: "<body>_body_</body>"
                }
            };
            var options = {
                maxWidth: 624
            };
            // Clone selected element before manipulating it
            var markup = $(this).clone();

            // Remove hidden elements from the output
            markup.each(function() {
                var self = $(this);
                if (self.is(':hidden'))
                    self.remove();
            });

            // Embed all images using Data URLs
            var images = Array();
            var img = markup.find('img');
            for (var i = 0; i < img.length; i++) {
                // Calculate dimensions of output image
                var w = Math.min(img[i].width, options.maxWidth);
                var h = img[i].height * (w / img[i].width);
                // Create canvas for converting image to data URL
                var canvas = document.createElement("CANVAS");
                canvas.width = w;
                canvas.height = h;
                // Draw image to canvas
                var context = canvas.getContext('2d');
                context.drawImage(img[i], 0, 0, w, h);
                // Get data URL encoding of image
                var uri = canvas.toDataURL("image/png/jpg");
                $(img[i]).attr("src", img[i].src);
                img[i].width = w;
                img[i].height = h;
                // Save encoded image to array
                images[i] = {
                    type: uri.substring(uri.indexOf(":") + 1, uri.indexOf(";")),
                    encoding: uri.substring(uri.indexOf(";") + 1, uri.indexOf(",")),
                    location: $(img[i]).attr("src"),
                    data: uri.substring(uri.indexOf(",") + 1)
                };
            }

            // Prepare bottom of mhtml file with image data
            var mhtmlBottom = "\n";
            for (var i = 0; i < images.length; i++) {
                mhtmlBottom += "--NEXT.ITEM-BOUNDARY\n";
                mhtmlBottom += "Content-Location: " + images[i].location + "\n";
                mhtmlBottom += "Content-Type: " + images[i].type + "\n";
                mhtmlBottom += "Content-Transfer-Encoding: " + images[i].encoding + "\n\n";
                mhtmlBottom += images[i].data + "\n\n";
            }
            mhtmlBottom += "--NEXT.ITEM-BOUNDARY--";

            //TODO: load css from included stylesheet

            //var styles=' /* Font Definitions */@font-face{font-family:宋体;panose-1:2 1 6 0 3 1 1 1 1 1;mso-font-alt:SimSun;mso-font-charset:134;mso-generic-font-family:auto;mso-font-pitch:variable;mso-font-signature:3 680460288 22 0 262145 0;}  @font-face{font-family:"Cambria Math";panose-1:2 4 5 3 5 4 6 3 2 4;mso-font-charset:1;mso-generic-font-family:roman;mso-font-format:other;mso-font-pitch:variable;mso-font-signature:0 0 0 0 0 0;}  @font-face{font-family:"\@宋体";panose-1:2 1 6 0 3 1 1 1 1 1;mso-font-charset:134;mso-generic-font-family:auto;mso-font-pitch:variable;mso-font-signature:3 680460288 22 0 262145 0;}/* Style Definitions */p.MsoNormal, li.MsoNormal, div.MsoNormal{mso-style-unhide:no;mso-style-qformat:yes;mso-style-parent:"";margin:0cm;margin-bottom:.0001pt;mso-pagination:widow-orphan;font-size:14.0pt;font-family:宋体;mso-bidi-font-family:宋体;}p.MsoHeader, li.MsoHeader, div.MsoHeader{mso-style-noshow:yes;mso-style-priority:99;mso-style-link:"页眉 Char";margin:0cm;margin-bottom:.0001pt;text-align:center;mso-pagination:widow-orphan;layout-grid-mode:char;font-size:9.0pt;font-family:宋体;mso-bidi-font-family:宋体;}p.MsoFooter, li.MsoFooter, div.MsoFooter{mso-style-noshow:yes;mso-style-priority:99;mso-style-link:"页脚 Char";margin:0cm;margin-bottom:.0001pt;mso-pagination:widow-orphan;layout-grid-mode:char;font-size:9.0pt;font-family:宋体;mso-bidi-font-family:宋体;}p.MsoAcetate, li.MsoAcetate, div.MsoAcetate{mso-style-noshow:yes;mso-style-priority:99;mso-style-link:"批注框文本 Char";margin:0cm;margin-bottom:.0001pt;mso-pagination:widow-orphan;font-size:9.0pt;font-family:宋体;mso-bidi-font-family:宋体;}span.Char{mso-style-name:"页眉 Char";mso-style-noshow:yes;mso-style-priority:99;mso-style-unhide:no;mso-style-locked:yes;mso-style-link:页眉;font-family:宋体;mso-ascii-font-family:宋体;mso-fareast-font-family:宋体;mso-hansi-font-family:宋体;}span.Char0{mso-style-name:"页脚 Char";mso-style-noshow:yes;mso-style-priority:99;mso-style-unhide:no;mso-style-locked:yes;mso-style-link:页脚;font-family:宋体;mso-ascii-font-family:宋体;mso-fareast-font-family:宋体;mso-hansi-font-family:宋体;}span.Char1{mso-style-name:"批注框文本 Char";mso-style-noshow:yes;mso-style-priority:99;mso-style-unhide:no;mso-style-locked:yes;mso-style-link:批注框文本;font-family:宋体;mso-ascii-font-family:宋体;mso-fareast-font-family:宋体;mso-hansi-font-family:宋体;}p.msochpdefault, li.msochpdefault, div.msochpdefault{mso-style-name:msochpdefault;mso-style-unhide:no;mso-margin-top-alt:auto;margin-right:0cm;mso-margin-bottom-alt:auto;margin-left:0cm;mso-pagination:widow-orphan;font-size:10.0pt;font-family:宋体;mso-bidi-font-family:宋体;}span.msonormal0{mso-style-name:msonormal;mso-style-unhide:no;}.MsoChpDefault{mso-style-type:export-only;mso-default-props:yes;font-size:10.0pt;mso-ansi-font-size:10.0pt;mso-bidi-font-size:10.0pt;mso-ascii-font-family:"Times New Roman";mso-hansi-font-family:"Times New Roman";mso-font-kerning:0pt;}/* Page Definitions */  @page WordSection1{size:595.3pt 841.9pt;margin:72.0pt 90.0pt 72.0pt 90.0pt;mso-header-margin:42.55pt;mso-footer-margin:49.6pt;mso-paper-source:0;}div.WordSection1{page:WordSection1;}';

            var styles="";

            // Aggregate parts of the file together
            var fileContent = static.mhtml.top.replace("_html_", static.mhtml.head.replace("_styles_", styles) + static.mhtml.body.replace("_body_", markup.html())) + mhtmlBottom;

            // Create a Blob with the file contents
            var blob = new Blob([fileContent], {
                type: "application/msword;charset=utf-8"
            });
            saveAs(blob, fileName + ".doc");
        };
    })(jQuery);
} else {
    if (typeof jQuery === "undefined") {
        console.error("jQuery Word Export: missing dependency (jQuery)");
    }
    if (typeof saveAs === "undefined") {
        console.error("jQuery Word Export: missing dependency (FileSaver.js)");
    }
}

插件调用

index.html

<!DOCTYPE html>
<html>
<head lang="en">
    <meta charset="UTF-8">
    <title>生成word文档</title>
</head>
<body lang=ZH-CN style='tab-interval:21.0pt'>
<div class="word">
    <p align="center" style="font-size:20pt;font-weight:bold;">JS导出Word文档</p>
</div>
<input type="button" value="导出word">
<script src="https://cdn.bootcss.com/jquery/2.2.4/jquery.js"></script>
<script type="text/javascript" src="js/FileSaver.js"></script>
<script type="text/javascript" src="js/jquery.wordexport.js"></script>
<script>
    $(function(){
        $("input[type='button']").click(function(event) {
            $(".word").wordExport('生成word文档');
        });
    })
</script>
</body>
</html>

直接调用wordExport()接口就可以导出word文档，传的参数为导出的word文件名。

补充

通过我们常规写的外联样式设置样式是无效的，通过个人的实践发现需要写内联样式才能生效，而单位也需要按照word的配置

单位pt设置。

而jquery.wordexport.js插件是要配置了个style样式让我们补充样式设置的：

但是个人实践了下，设置的样式却无法生效，只能通过内联设置才生效。

截图：