将HTML导出生成word文档

时间:2024-03-10 17:43:29

 

前言:

项目开发中遇到了需要将HTML页面的内容导出为一个word文档,所以有了这边随笔。

当然,项目开发又时间有点紧迫,第一时间想到的是用插件,所以百度了下。下面就介绍两个导出word文档的方法。

法一: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

  1 /* FileSaver.js
  2  * A saveAs() FileSaver implementation.
  3  * 1.3.2
  4  * 2016-06-16 18:25:19
  5  *
  6  * By Eli Grey, http://eligrey.com
  7  * License: MIT
  8  *   See https://github.com/eligrey/FileSaver.js/blob/master/LICENSE.md
  9  */
 10 
 11 /*global self */
 12 /*jslint bitwise: true, indent: 4, laxbreak: true, laxcomma: true, smarttabs: true, plusplus: true */
 13 
 14 /*! @source http://purl.eligrey.com/github/FileSaver.js/blob/master/FileSaver.js */
 15 
 16 var saveAs = saveAs || (function(view) {
 17         "use strict";
 18         // IE <10 is explicitly unsupported
 19         if (typeof view === "undefined" || typeof navigator !== "undefined" && /MSIE [1-9]\./.test(navigator.userAgent)) {
 20             return;
 21         }
 22         var
 23             doc = view.document
 24         // only get URL when necessary in case Blob.js hasn\'t overridden it yet
 25             , get_URL = function() {
 26                 return view.URL || view.webkitURL || view;
 27             }
 28             , save_link = doc.createElementNS("http://www.w3.org/1999/xhtml", "a")
 29             , can_use_save_link = "download" in save_link
 30             , click = function(node) {
 31                 var event = new MouseEvent("click");
 32                 node.dispatchEvent(event);
 33             }
 34             , is_safari = /constructor/i.test(view.HTMLElement)
 35             , is_chrome_ios =/CriOS\/[\d]+/.test(navigator.userAgent)
 36             , throw_outside = function(ex) {
 37                 (view.setImmediate || view.setTimeout)(function() {
 38                     throw ex;
 39                 }, 0);
 40             }
 41             , force_saveable_type = "application/octet-stream"
 42         // the Blob API is fundamentally broken as there is no "downloadfinished" event to subscribe to
 43             , arbitrary_revoke_timeout = 1000 * 40 // in ms
 44             , revoke = function(file) {
 45                 var revoker = function() {
 46                     if (typeof file === "string") { // file is an object URL
 47                         get_URL().revokeObjectURL(file);
 48                     } else { // file is a File
 49                         file.remove();
 50                     }
 51                 };
 52                 setTimeout(revoker, arbitrary_revoke_timeout);
 53             }
 54             , dispatch = function(filesaver, event_types, event) {
 55                 event_types = [].concat(event_types);
 56                 var i = event_types.length;
 57                 while (i--) {
 58                     var listener = filesaver["on" + event_types[i]];
 59                     if (typeof listener === "function") {
 60                         try {
 61                             listener.call(filesaver, event || filesaver);
 62                         } catch (ex) {
 63                             throw_outside(ex);
 64                         }
 65                     }
 66                 }
 67             }
 68             , auto_bom = function(blob) {
 69                 // prepend BOM for UTF-8 XML and text/* types (including HTML)
 70                 // note: your browser will automatically convert UTF-16 U+FEFF to EF BB BF
 71                 if (/^\s*(?:text\/\S*|application\/xml|\S*\/\S*\+xml)\s*;.*charset\s*=\s*utf-8/i.test(blob.type)) {
 72                     return new Blob([String.fromCharCode(0xFEFF), blob], {type: blob.type});
 73                 }
 74                 return blob;
 75             }
 76             , FileSaver = function(blob, name, no_auto_bom) {
 77                 if (!no_auto_bom) {
 78                     blob = auto_bom(blob);
 79                 }
 80                 // First try a.download, then web filesystem, then object URLs
 81                 var
 82                     filesaver = this
 83                     , type = blob.type
 84                     , force = type === force_saveable_type
 85                     , object_url
 86                     , dispatch_all = function() {
 87                         dispatch(filesaver, "writestart progress write writeend".split(" "));
 88                     }
 89                 // on any filesys errors revert to saving with object URLs
 90                     , fs_error = function() {
 91                         if ((is_chrome_ios || (force && is_safari)) && view.FileReader) {
 92                             // Safari doesn\'t allow downloading of blob urls
 93                             var reader = new FileReader();
 94                             reader.onloadend = function() {
 95                                 var url = is_chrome_ios ? reader.result : reader.result.replace(/^data:[^;]*;/, \'data:attachment/file;\');
 96                                 var popup = view.open(url, \'_blank\');
 97                                 if(!popup) view.location.href = url;
 98                                 url=undefined; // release reference before dispatching
 99                                 filesaver.readyState = filesaver.DONE;
100                                 dispatch_all();
101                             };
102                             reader.readAsDataURL(blob);
103                             filesaver.readyState = filesaver.INIT;
104                             return;
105                         }
106                         // don\'t create more object URLs than needed
107                         if (!object_url) {
108                             object_url = get_URL().createObjectURL(blob);
109                         }
110                         if (force) {
111                             view.location.href = object_url;
112                         } else {
113                             var opened = view.open(object_url, "_blank");
114                             if (!opened) {
115                                 // Apple does not allow window.open, see https://developer.apple.com/library/safari/documentation/Tools/Conceptual/SafariExtensionGuide/WorkingwithWindowsandTabs/WorkingwithWindowsandTabs.html
116                                 view.location.href = object_url;
117                             }
118                         }
119                         filesaver.readyState = filesaver.DONE;
120                         dispatch_all();
121                         revoke(object_url);
122                     }
123                     ;
124                 filesaver.readyState = filesaver.INIT;
125 
126                 if (can_use_save_link) {
127                     object_url = get_URL().createObjectURL(blob);
128                     setTimeout(function() {
129                         save_link.href = object_url;
130                         save_link.download = name;
131                         click(save_link);
132                         dispatch_all();
133                         revoke(object_url);
134                         filesaver.readyState = filesaver.DONE;
135                     });
136                     return;
137                 }
138 
139                 fs_error();
140             }
141             , FS_proto = FileSaver.prototype
142             , saveAs = function(blob, name, no_auto_bom) {
143                 return new FileSaver(blob, name || blob.name || "download", no_auto_bom);
144             }
145             ;
146         // IE 10+ (native saveAs)
147         if (typeof navigator !== "undefined" && navigator.msSaveOrOpenBlob) {
148             return function(blob, name, no_auto_bom) {
149                 name = name || blob.name || "download";
150 
151                 if (!no_auto_bom) {
152                     blob = auto_bom(blob);
153                 }
154                 return navigator.msSaveOrOpenBlob(blob, name);
155             };
156         }
157 
158         FS_proto.abort = function(){};
159         FS_proto.readyState = FS_proto.INIT = 0;
160         FS_proto.WRITING = 1;
161         FS_proto.DONE = 2;
162 
163         FS_proto.error =
164             FS_proto.onwritestart =
165                 FS_proto.onprogress =
166                     FS_proto.onwrite =
167                         FS_proto.onabort =
168                             FS_proto.onerror =
169                                 FS_proto.onwriteend =
170                                     null;
171 
172         return saveAs;
173     }(
174         typeof self !== "undefined" && self
175         || typeof window !== "undefined" && window
176         || this.content
177     ));
178 // `self` is undefined in Firefox for Android content script context
179 // while `this` is nsIContentFrameMessageManager
180 // with an attribute `content` that corresponds to the window
181 
182 if (typeof module !== "undefined" && module.exports) {
183     module.exports.saveAs = saveAs;
184 } else if ((typeof define !== "undefined" && define !== null) && (define.amd !== null)) {
185     define([], function() {
186         return saveAs;
187     });
188 }
View Code

jquery.wordexport.js

 1 if (typeof jQuery !== "undefined" && typeof saveAs !== "undefined") {
 2     (function($) {
 3         $.fn.wordExport = function(fileName) {
 4             fileName = typeof fileName !== \'undefined\' ? fileName : "jQuery-Word-Export";
 5             var static = {
 6                 mhtml: {
 7                     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>",
 8                     head: "<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">\n<style>\n_styles_\n</style>\n</head>\n",
 9                     body: "<body>_body_</body>"
10                 }
11             };
12             var options = {
13                 maxWidth: 624
14             };
15             // Clone selected element before manipulating it
16             var markup = $(this).clone();
17 
18             // Remove hidden elements from the output
19             markup.each(function() {
20                 var self = $(this);
21                 if (self.is(\':hidden\'))
22                     self.remove();
23             });
24 
25             // Embed all images using Data URLs
26             var images = Array();
27             var img = markup.find(\'img\');
28             for (var i = 0; i < img.length; i++) {
29                 // Calculate dimensions of output image
30                 var w = Math.min(img[i].width, options.maxWidth);
31                 var h = img[i].height * (w / img[i].width);
32                 // Create canvas for converting image to data URL
33                 var canvas = document.createElement("CANVAS");
34                 canvas.width = w;
35                 canvas.height = h;
36                 // Draw image to canvas
37                 var context = canvas.getContext(\'2d\');
38                 context.drawImage(img[i], 0, 0, w, h);
39                 // Get data URL encoding of image
40                 var uri = canvas.toDataURL("image/png/jpg");
41                 $(img[i]).attr("src", img[i].src);
42                 img[i].width = w;
43                 img[i].height = h;
44                 // Save encoded image to array
45                 images[i] = {
46                     type: uri.substring(uri.indexOf(":") + 1, uri.indexOf(";")),
47                     encoding: uri.substring(uri.indexOf(";") + 1, uri.indexOf(",")),
48                     location: $(img[i]).attr("src"),
49                     data: uri.substring(uri.indexOf(",") + 1)
50                 };
51             }
52 
53             // Prepare bottom of mhtml file with image data
54             var mhtmlBottom = "\n";
55             for (var i = 0; i < images.length; i++) {
56                 mhtmlBottom += "--NEXT.ITEM-BOUNDARY\n";
57                 mhtmlBottom += "Content-Location: " + images[i].location + "\n";
58                 mhtmlBottom += "Content-Type: " + images[i].type + "\n";
59                 mhtmlBottom += "Content-Transfer-Encoding: " + images[i].encoding + "\n\n";
60                 mhtmlBottom += images[i].data + "\n\n";
61             }
62             mhtmlBottom += "--NEXT.ITEM-BOUNDARY--";
63 
64             //TODO: load css from included stylesheet
65 
66             //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;}\';
67 
68             var styles="";
69 
70             // Aggregate parts of the file together
71             var fileContent = static.mhtml.top.replace("_html_", static.mhtml.head.replace("_styles_", styles) + static.mhtml.body.replace("_body_", markup.html())) + mhtmlBottom;
72 
73             // Create a Blob with the file contents
74             var blob = new Blob([fileContent], {
75                 type: "application/msword;charset=utf-8"
76             });
77             saveAs(blob, fileName + ".doc");
78         };
79     })(jQuery);
80 } else {
81     if (typeof jQuery === "undefined") {
82         console.error("jQuery Word Export: missing dependency (jQuery)");
83     }
84     if (typeof saveAs === "undefined") {
85         console.error("jQuery Word Export: missing dependency (FileSaver.js)");
86     }
87 }
View Code

插件调用:

 1 <!DOCTYPE html>
 2 <html>
 3 <head lang="en">
 4     <meta charset="UTF-8">
 5     <title>生成word文档</title>
 6 </head>
 7 <body lang=ZH-CN style=\'tab-interval:21.0pt\'>
 8 <div class="word">
 9     <p align="center" style="font-size:20pt;font-weight:bold;">JS导出Word文档</p>
10 </div>
11 <input type="button" value="导出word">
12 <script src="https://cdn.bootcss.com/jquery/2.2.4/jquery.js"></script>
13 <script type="text/javascript" src="js/FileSaver.js"></script>
14 <script type="text/javascript" src="js/jquery.wordexport.js"></script>
15 <script>
16     $(function(){
17         $("input[type=\'button\']").click(function(event) {
18             $(".word").wordExport(\'生成word文档\');
19         });
20     })
21 </script>
22 </body>
23 </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:

法二:通过百度js模板引擎生成word文档

主要是通过js模板设置对应的标签,然后XDoc.to(baidu.template())导出word,而通过百度js模板引擎的好处是也可以导出PDF文件。

完整demo:

 1 <!DOCTYPE html>
 2 <html>
 3 <head>
 4     <meta charset="UTF-8">
 5     <script type="text/javascript" src="http://www.xdocin.com/xdoc.js"></script>
 6     <script type="text/javascript" src="http://www.xdocin.com/baiduTemplate.js"></script>
 7     <style>
 8         .head{
 9             font-size: 29px;
10             display: block;
11         }
12         .content{
13             display: block;
14         }
15     </style>
16 </head>
17 <body>
18 <input type="button" onclick="gen(\'pdf\')" value="生成PDF"/>
19 <input type="button" onclick="gen(\'docx\')" value="生成Word"/>
20 <br/>
21 <script id="tmpl" type="text/html">
22     <xdoc version="A.3.0">
23         <body>
24         <para heading="1" lineSpacing="28">
25             <text class="head" valign="center" fontName="标宋" fontSize="29"><%=title%></text>
26         </para>
27         <para>
28             <img  src="<%=img%>" sizeType="autosize"/>
29         </para>
30         <para lineSpacing="9">
31             <text class="content" fontName="仿宋" fontSize="18"><%=content%></text>
32         </para>
33         </body>
34     </xdoc>
35 </script>
36 <script src="https://cdn.bootcss.com/jquery/2.2.4/jquery.js"></script>
37 <script type="text/javascript">
38     var type="docx";//pdf
39     var data = {
40         title: "导出"+type+"文件",
41         img: "http://www.wordlm.com/uploads/allimg/130101/1_130101000405_1.jpg",
42         content: "我这样就可以导出"+type+"格式的文件了,是不是很方便",
43     };
44     function renderTemplate(){
45         var template=$("#tmpl").html();
46         var html=template.replace(/<%=title%>/,data.title)
47                 .replace(/<%=img%>/,data.img)
48                 .replace(/<%=content%>/,data.content);
49         $("body").append(html);
50     }
51     renderTemplate();
52     function gen(type) {
53         XDoc.to(baidu.template(\'tmpl\', data), type, {}, "_blank");
54     }
55     console.log(\'http://www.xdocin.com/xml.html\');
56 </script>
57 </body>
58 </html>  

这里我通过renderTemplate函数叫js模板渲染到HTML中,实现了文本的展示和导出内容的结合。而因为这里导出的word文档是需要特别设置样式的,所以在页面样式展示下我们可以通过添加.class的方式设置。

附部分导出word文档样式设置:

 

截图:

 

更多参考:

FileSave.js:https://github.com/eligrey/FileSaver.js

百度导出文档模板:http://www.xdocin.com/xml.html