在chrome浏览器上下载txt小说的Javascript代码

在chrome浏览器上下载txt小说的Javascript代码

前段时间在追一部网络小说，想把小说下载到本地离线阅读，利用chrome浏览器开发模式，编写了一段下载小说页面中所有章节内容，并合并为一个文本文件的Javascript代码。

//章节目录所在的标签ID
var txtListID = "list";
//小说章节正文所在的标签ID
var txtContentID = "content";

function syncSleep(time) {
    return new Promise((resolve)=>setTimeout(resolve, time));
}

//网页链接文档列表
var docLst = [];

//XmlHttpReauest
var XMLHttp = {
    _getInstance: function() {
                return this._createObj();
    },
    _createObj: function() {
        if (window.XMLHttpRequest) {
            // code for IE7, Firefox, Opera, etc.
            objXMLHttp = new XMLHttpRequest();
        } else if (window.ActiveXObject) {
            // code for IE6, IE5
            objXMLHttp = new ActiveXObject("Microsoft.XMLHTTP");
        }
        return objXMLHttp;
    },
    // 发送请求(方法[post,get], 地址, 数据, 回调函数)  
    sendReq: function(method, url, data, callback) {
        var objXMLHttp = this._getInstance();
        with (objXMLHttp) {
            try {
                // 加随机数防止缓存  
                if (url.indexOf("?") > 0) {
                    url += "&randnum=" + Math.random();
                } else {
                    url += "?randnum=" + Math.random();
                }
                open(method, url, true);
                // 设定请求编码方式  
                setRequestHeader('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8');
                send(data);
                onreadystatechange = function() {
                    if (objXMLHttp.readyState == 4 && (objXMLHttp.status == 200 || objXMLHttp.status == 304)) {
                        callback(objXMLHttp);
                    }
                }
            } catch (e) {
                alert(e);
            }
        }
    }
}

//Xml文档Parser
function Parser() {
    if (window.DOMParser) {
        return new DOMParser();
    } else // Internet Explorer
    {
        xmlDoc = new ActiveXObject("Microsoft.XMLDOM");
        xmlDoc.async = "false";
        return xmlDoc;
    }
}

var promises = [];
//下一行代码是关键，用于生成小说页面上所有章节链接网页列表。这需要根据不同小说网站的章节目录页面布局，选择不同的ID或者CLASS。
var srcDoc = document.getElementById(txtListID).children[0];

var ad = Array.prototype.slice.call(srcDoc.children);
var txtListCount = 0;
ad.forEach(function(item, idx) {
    var tmpd = item.children[0];
    if (tmpd != undefined) {
        if (tmpd.nodeName === "A") {
            promises.push(new Promise(resolve=>{
                XMLHttp.sendReq("GET", tmpd.href, null, function(xhttp) {
                    var parser = Parser();
                    var doc = parser.parseFromString(xhttp.responseText, "text/html");
                    var ct = doc.getElementById(txtContentID).innerHTML;
                    docLst.push({
                        "idx": idx,
                        "url": tmpd.href,
                        "section": tmpd.innerText,
                        "txt": ct
                    });
                    console.log(idx, tmpd.innerText, tmpd.href);
                    resolve();
                });
            }
            ));
        }
    }
})

function SaveToFile(data, filename) {
    if (!data) {
        console.error('Console.save: No data')
        return;
    }
    if (!filename)
        filename = 'console.json';
    if (typeof data === "object") {
        data = JSON.stringify(data, undefined, 4)
    }
    var blob = new Blob([data],{
        type: 'text/json'
    });
    e = document.createEvent("MouseEvents");
    a = document.createElement("a");
    a.download = filename;
    a.href = window.URL.createObjectURL(blob);
    a.dataset.downloadurl = ["text/json", a.download, a.href].join(':');
    e.initMouseEvent("click", true, false, window, 0, 0, 0, 0, 0, false, false, false, false, 0, null);
    a.dispatchEvent(e);
    window.URL.revokeObjectURL(a.href);
}

//小说的书名
var txtTitle=document.getElementById("info").innerText
var txtUrl=document.URL

var docStr = "\n"+txtTitle+"\n"+txtUrl+"\n";
Promise.all(promises).then(function() {
    docLst.sort((a,b)=>{
        return a.idx - b.idx
    }
    );
    docLst.forEach(function(item) {
        docStr = docStr + "\n第"+item.section +"\n"+ item.txt+"\n"
    });
    [{
        in: "<br>",
        to: " "
    }, {
        in: "&nbsp;",
        to: " "
    },{
        in:"XX小说网",
        to:"\n"
    }].forEach(item=>{
        var rg = new RegExp(item.in,"g");
        docStr = docStr.replace(rg, item.to);
    }
    )
    //console.log(docStr);
    SaveToFile(docStr,"docStr.txt");
});

上述代码需要在chrome开发模式下，新建snippet代码片段，复制粘贴到代码片段中运行。由说小说网站页面布局存在差异，需要针对性的分析页面布局，生成正确的章节网址列表。由于个人水平限制，代码中有不足或错漏之处，还请方家指正。