1. 转码

使用getDict工具转码mdx为HTML或者xml， 编码格式为utf-8
转换好之后

2. 正则表达式匹配移除标签

/([!a-zA-Z-_ ’'‘ÆÐƎƏƐƔIJŊŒẞÞǷȜæðǝəɛɣijŋœĸſßþƿȝĄƁÇĐƊĘĦĮƘŁØƠŞȘŢȚŦŲƯY̨Ƴąɓçđɗęħįƙłøơşșţțŧųưy̨ƴÁÀÂÄǍĂĀÃÅǺĄÆǼǢƁĆĊĈČÇĎḌĐƊÐÉÈĖÊËĚĔĒĘẸƎƏƐĠĜǦĞĢƔáàâäǎăāãåǻąæǽǣɓćċĉčçďḍđɗðéèėêëěĕēęẹǝəɛġĝǧğģɣĤḤĦIÍÌİÎÏǏĬĪĨĮỊIJĴĶƘĹĻŁĽĿʼNŃN̈ŇÑŅŊÓÒÔÖǑŎŌÕŐỌØǾƠŒĥḥħıíìiîïǐĭīĩįịijĵķƙĸĺļłľŀʼnńn̈ňñņŋóòôöǒŏōõőọøǿơœŔŘŖŚŜŠŞȘṢẞŤŢṬŦÞÚÙÛÜǓŬŪŨŰŮŲỤƯẂẀŴẄǷÝỲŶŸȲỸƳŹŻŽẒŕřŗſśŝšşșṣßťţṭŧþúùûüǔŭūũűůųụưẃẁŵẅƿýỳŷÿȳỹƴźżžẓ]+)</font>/

const express = require('express');
const fs = require('fs');
let path = require('path');

fs.readFile('./dic_dhz.txt', 'utf-8', (err, data) => {
    if (err) {
        console.log(err);
    } else {
        // 将MDX 词典分条处理
        let arr = data.split('\r\n');
        arr.forEach((ele, index) => {
            arr[index] = ele + "_end"
        })
        // 每一条转换为固定的数据结构
        let dic_fixed_structure = {};
        console.log('********分割线********');
        arr.forEach((ele, index, self) => {
            let item = {};
            
            //获取单词名称
            let wordName = ele.match(/<font color=blue size=4>([!a-zA-Z\-_ ’‘ÆÐƎƏƐƔIJŊŒẞÞǷȜæðǝəɛɣijŋœĸſßþƿȝĄƁÇĐƊĘĦĮƘŁØƠŞȘŢȚŦŲƯY̨Ƴąɓçđɗęħįƙłøơşșţțŧųưy̨ƴÁÀÂÄǍĂĀÃÅǺĄÆǼǢƁĆĊĈČÇĎḌĐƊÐÉÈĖÊËĚĔĒĘẸƎƏƐĠĜǦĞĢƔáàâäǎăāãåǻąæǽǣɓćċĉčçďḍđɗðéèėêëěĕēęẹǝəɛġĝǧğģɣĤḤĦIÍÌİÎÏǏĬĪĨĮỊIJĴĶƘĹĻŁĽĿʼNŃN̈ŇÑŅŊÓÒÔÖǑŎŌÕŐỌØǾƠŒĥḥħıíìiîïǐĭīĩįịijĵķƙĸĺļłľŀʼnńn̈ňñņŋóòôöǒŏōõőọøǿơœŔŘŖŚŜŠŞȘṢẞŤŢṬŦÞÚÙÛÜǓŬŪŨŰŮŲỤƯẂẀŴẄǷÝỲŶŸȲỸƳŹŻŽẒŕřŗſśŝšşșṣßťţṭŧþúùûüǔŭūũűůųụưẃẁŵẅƿýỳŷÿȳỹƴźżžẓ]+)<\/font>/);
            
            // 截取字符串， 分类处理
            let types = ele.split(`<font color=red>`);
            
            // 如果单词存在的情况下
            if (wordName) {
            
                // 如果是动词
                if (ele.indexOf('v.t.') !== -1 || ele.indexOf('v.r.') !== -1) {
                    item.word = wordName[0].match(/>([\d\D]+)</)[1];
                    let attrName = item.word.trim()
                    dic_fixed_structure[attrName] = {};
                    
                    /***
                     * @该单词是主动词
                     * */
                    if (ele.indexOf('v.t.') !== -1) {
                    
                        // 单词赋值
                        item.word = wordName[0].match(/>([\d\D]+)</)[1];
                        item.index = index;
                        var itemStr = ''
                        
                        // 获取v.t.
                        for (let i = 0; i < types.length; i++) {
                            if (types[i].indexOf('v.t.') !== -1) {
                                itemStr = types[i];
                            }
                        }
                        
                        // 获取意思数组
                        var meaningsArr = itemStr.split(`<font color=darkblue>`);
                        // console.log(meaningsArr);
                        var newArr = [];
                        meaningsArr.forEach((ele, index) => {
                            var str = ele.replace(/<[\d\D]+?>/g, '').replace('\\n_end', '').replace('v.t.', '').split("\\n").join('');
                            // console.log(str);
                            if (str !== '') {
                                newArr.push(str)
                            }
                        });
                        if (newArr.length === 1) {
                            newArr[0] = "(1)" + newArr[0]
                        }

                        dic_fixed_structure[attrName].vt = newArr;
                    }
                    /**
                     * @该单词是反身动词
                     * */
                    if (ele.indexOf('v.r.') !== -1) {
                    
                        // 单词赋值
                        item.word = wordName[0].match(/>([\d\D]+)</)[1];
                        item.index = index;
                        var itemStr = '';
                        
                        // 获取v.r.
                        for (let i = 0; i < types.length; i++) {
                            if (types[i].indexOf('v.r.') !== -1) {
                                itemStr = types[i];
                            }
                        }
                        
                        // 获取意思数组
                        var meaningsArr = itemStr.split(`<font color=darkblue>`);
                        var newArr = [];
                        meaningsArr.forEach((ele, index) => {
                            var str = ele.replace(/<[\d\D]+?>/g, '').replace('\\n_end', '').replace('v.r.', '').split("\\n").join('');
                            if (str !== '') {
                                newArr.push(str)
                            }
                        });
                        if (newArr.length === 1) {
                            newArr[0] = "(1)" + newArr[0]
                        }
                        dic_fixed_structure[attrName].vr = newArr;
                    }
                }
            }
        });
        console.log(dic_fixed_structure);

        fs.writeFile('./dic/dic' + new Date().getTime() + '.json', JSON.stringify(dic_fixed_structure), (err, data) => {
            if (err) console.log(err)
        })
    }
})

生成JSON文件，用于后续写入word。

3. json写入word

下载officegen生成器

const officegen = require('officegen')
const fs = require('fs')

// Create an empty Word object:
let docx = officegen('docx')

// 完成监听:
docx.on('finalize', function (written) {
    console.log('Finish to create a Microsoft Word document.')
})

// 错误监听:
docx.on('error', function (err) {
    console.log(err)
})

// 创建段落

var data = fs.readFileSync('./dic/dic1569026153874.json', 'utf-8');
var num = 0;
var frequent1720 = fs.readFileSync('./1700frequentWord.json', 'utf-8');
let genWord = (data) => {
    let pObj = docx.createP();
    // A-Z排序的全部单词
    var keys = Object.keys(data);

    // 1720排序的全部单词
    // var keys = JSON.parse(frequent1720);

    console.log(keys)
    // console.log(keys);
    for (var i = 0; i < keys.length; i++) {
        var word = keys[i];
        if (data[word]) {
            num = num + 1;
            pObj.addText(word + "\r\n", { font_size: 16, color: '0022aa', link: 'https://dicionario.priberam.org/' + word });
        }
        // if (data[word] && data[word].vt) {
        //     let arr = data[word].vt;
        //     pObj.addText('[v.t.] : ', { font_size: 10, bold: true, color: '881100', })
        //     for (var j = 0; j < arr.length; j++) {
        //         pObj.addText(arr[j] + "\r\n", { font_size: 10, color: '000000' })
        //     }
        // }
        // if (data[word] && data[word].vr) {
        //     let arr = data[word].vr;
        //     pObj.addText('[v.r.] : ', { font_size: 10, bold: true, color: '881100' })
        //     for (var x = 0; x < arr.length; x++) {
        //         pObj.addText(arr[x] + "\r\n", { font_size: 10, color: '000000' })
        //     }
        // }
        // if (data[word]) {
        //     pObj.addLineBreak()
        // }
    }
}

genWord(JSON.parse(data));

// Let's generate the Word document into a file:
let out = fs.createWriteStream('exampleWord.docx')
out.on('error', function (err) {
    console.log(err)
});

// Async call to generate the output file:
docx.generate(out);
console.log(num)

// pObj.options.align = 'right'
// pObj = docx.createP()
// pObj.addLineBreak()
// docx.putPageBreak()
// docx.putPageBreak()
// pObj = docx.createP()
// pObj.addImage('some-image.png');

MDX生成word词典大功告成，耶✌！