npm install hatenadiary-downloader -g
# or
npx hatenadiary-downloader [option]

Usage
  $ hatenadiary-downloader <URL>

Options:
  --sortOrder "ascending" or "descending" (default: ascending)
  --output -o  output path

Examples
  $ hatenadiary-downloader "http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]" -o ./index.html

hatenadiary-downloader "http://d.hatena.ne.jp/hatenadiary/" -o ./index.html

hatenadiary-downloader "http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]" -o ./index.html

hatenadiary-downloader "http://d.hatena.ne.jp/t-wada/" -o ./t-wada.html

// それぞれ空の関数をexportした
module.exports.parseContent = parseContent;
module.exports.fetchPrevioutArticle = fetchPrevioutArticle;
module.exports.fetchArticle = fetchArticle;

// URLからdocumentオブジェクトを取得する
const fetchDocument = (URL) => {};
// documentからcontents(それぞれの記事のHTML)を返す
const parseContents = (document) => {};
// documentから前の記事リスト(前の記事)のURLを取得する
const getPrevArticleListURL = (document) => { };
module.exports.fetchDocument = fetchDocument;
module.exports.parseContents = parseContents;
module.exports.getPrevArticleListURL = getPrevArticleListURL;

// こんな感じでOKだった
const fetchDocument = (URL) => {
    return JSDOM.fromURL(URL, {
        userAgent: "hatenadiary-downloader+",
    }).then(dom => {
        return dom.window.document;
    });
};

const assert = require("assert").strict;
const { fetchDocument, parseContents, getPrevArticleListURL } = require("../src/hatenadiary-downloader.js");

describe("hatenadiary-downloader", () => {
    it("should fetch article list and prev url", async () => {
        const document = await fetchDocument("http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]");
        const prevURL = getPrevArticleListURL(document);
        assert.equal(prevURL, "http://d.hatena.ne.jp/t-wada/searchdiary?of=3&word=%2A%5BXP%5D");
    });
});

    it("should fetch and parse contents", async () => {
        const document = await fetchDocument("http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]");
        const contents = parseContents(document);
        contents.forEach(content => {
            assert.ok(content.includes(`div class="day"`));
        });
    });

const allContents = [];
// いい感じのAsyncIteatorオブジェクト作って返す
// ReaderといってたのはFetch with Streamを思い浮かべたから
const fetchAsyncIterator = createFetchReader();
// このasync iteratorはnext()するたびに、次のページのdocumentを返す
for await (const document of fetchAsyncIterator)  {
    // documentからcontentsを取り出して貯める
   allContents.push(...parseContents(document));
}
// 最後にHTMLにまとめて出力

    it("should async iterator for createFetchReader", async () => {
        const iterator = createFetchReader("http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]");
        let count = 0;
        const URLs = [];
        for await (const document of iterator) {
            count++;
            URLs.push(document.location.href);
            if (count > 3) {
                break;
            }
        }
        assert.ok(count, 3);
        assert.deepEqual(URLs, [
            'http://d.hatena.ne.jp/t-wada/searchdiary?word=*[XP]',
            'http://d.hatena.ne.jp/t-wada/searchdiary?of=3&word=%2A%5BXP%5D',
            'http://d.hatena.ne.jp/t-wada/searchdiary?of=6&word=%2A%5BXP%5D',
            'http://d.hatena.ne.jp/t-wada/searchdiary?of=9&word=%2A%5BXP%5D'
        ]);
    });

const createFetchReader = (URL, { intervalTimeMs }) => {
    let prevURL = URL;
    return {
        [Symbol.asyncIterator]: () => {
            return {
                async next() {
                    const currentURL = prevURL;
                    if (!currentURL) {
                        return { done: true }
                    }
                    const document = await fetchDocument(currentURL);
                    prevURL = getPrevArticleListURL(document);
                    return {
                        done: false,
                        value: document
                    }
                }
            }
        }
    }
};

// neue cc - はてなダイアリー to HTMLから抜粋
            retry:
                try
                {
                    var url = HatenaUrl + prev.Attribute("href").Value;
                    Console.WriteLine(url); // こういうの挟むのビミョーではある
                    return XElement.Load(new SgmlReader { Href = url });
                }
                catch (WebException) // タイムアウトするので
                {
                    Console.WriteLine("Timeout at " + DateTime.Now.ToString() + " wait 15 seconds...");
                    Thread.Sleep(TimeSpan.FromSeconds(15)); // とりあえず15秒待つ
                    goto retry; // 何となくGOTO使いたい人
                }

// MIT © 2018 azu
"use strict";
const { createFetchReader, parseContents, joinArticleContents, getPrevArticleListURL } = require("./hatenadiary-downloader.js");
const fs = require("fs");
const path = require("path");
const assert = require("assert");
const cli = {
    /**
     * @param {string} URL hatena diary URL
     * @param {string } outputPath output Ptah
     * @param {string } [sortOrder] ascending or descending
     */
    async run(URL, outputPath, sortOrder = "ascending") {
        assert.ok(URL !== undefined, "URL needed");
        assert.ok(outputPath !== undefined, "--output is needed");
        const allContents = [];
        let lastDocument = null;
        const fetchAsyncIterator = createFetchReader(URL, {
            intervalTimeMs: 1000
        });
        for await (const document of fetchAsyncIterator) {
            console.log("Process: " + document.location.href);
            lastDocument = document;
            if (sortOrder === "ascending") {
                allContents.push(...parseContents(document).reverse());
            } else {
                allContents.push(...parseContents(document));
            }

        }
        if (sortOrder === "ascending") {
            allContents.reverse();
        }
        const indexContent = joinArticleContents(lastDocument, allContents);
        fs.writeFileSync(path.resolve(process.cwd(), outputPath), indexContent, "utf-8");
    }
};
module.exports.cli = cli;