3.0.1

.gitignore

@@ -1,3 +1,2 @@
 /node_modules
-/built
 npm-debug.log

built/general.d.ts

@@ -0,0 +1,4 @@
+import * as URL from 'node:url';
+import Summary from './summary.js';
+declare const _default: (url: URL.Url, lang?: string | null) => Promise<Summary | null>;
+export default _default;

built/general.js

@@ -0,0 +1,98 @@
+import * as URL from 'node:url';
+import clip from './utils/clip.js';
+import cleanupTitle from './utils/cleanup-title.js';
+import { decode as decodeHtml } from 'html-entities';
+import { head, scpaping } from './utils/got.js';
+export default async (url, lang = null) => {
+    if (lang && !lang.match(/^[\w-]+(\s*,\s*[\w-]+)*$/))
+        lang = null;
+    const res = await scpaping(url.href, { lang: lang || undefined });
+    const $ = res.$;
+    const twitterCard = $('meta[property="twitter:card"]').attr('content');
+    let title = $('meta[property="og:title"]').attr('content') ||
+        $('meta[property="twitter:title"]').attr('content') ||
+        $('title').text();
+    if (title === undefined || title === null) {
+        return null;
+    }
+    title = clip(decodeHtml(title), 100);
+    let image = $('meta[property="og:image"]').attr('content') ||
+        $('meta[property="twitter:image"]').attr('content') ||
+        $('link[rel="image_src"]').attr('href') ||
+        $('link[rel="apple-touch-icon"]').attr('href') ||
+        $('link[rel="apple-touch-icon image_src"]').attr('href');
+    image = image ? URL.resolve(url.href, image) : null;
+    const playerUrl = (twitterCard !== 'summary_large_image' && $('meta[property="twitter:player"]').attr('content')) ||
+        (twitterCard !== 'summary_large_image' && $('meta[name="twitter:player"]').attr('content')) ||
+        $('meta[property="og:video"]').attr('content') ||
+        $('meta[property="og:video:secure_url"]').attr('content') ||
+        $('meta[property="og:video:url"]').attr('content');
+    const playerWidth = parseInt($('meta[property="twitter:player:width"]').attr('content') ||
+        $('meta[name="twitter:player:width"]').attr('content') ||
+        $('meta[property="og:video:width"]').attr('content') ||
+        '');
+    const playerHeight = parseInt($('meta[property="twitter:player:height"]').attr('content') ||
+        $('meta[name="twitter:player:height"]').attr('content') ||
+        $('meta[property="og:video:height"]').attr('content') ||
+        '');
+    let description = $('meta[property="og:description"]').attr('content') ||
+        $('meta[property="twitter:description"]').attr('content') ||
+        $('meta[name="description"]').attr('content');
+    description = description
+        ? clip(decodeHtml(description), 300)
+        : null;
+    if (title === description) {
+        description = null;
+    }
+    let siteName = $('meta[property="og:site_name"]').attr('content') ||
+        $('meta[name="application-name"]').attr('content') ||
+        url.hostname;
+    siteName = siteName ? decodeHtml(siteName) : null;
+    const favicon = $('link[rel="shortcut icon"]').attr('href') ||
+        $('link[rel="icon"]').attr('href') ||
+        '/favicon.ico';
+    const sensitive = $('.tweet').attr('data-possibly-sensitive') === 'true';
+    const find = async (path) => {
+        const target = URL.resolve(url.href, path);
+        try {
+            await head(target);
+            return target;
+        }
+        catch (e) {
+            return null;
+        }
+    };
+    // 相対的なURL (ex. test) を絶対的 (ex. /test) に変換
+    const toAbsolute = (relativeURLString) => {
+        const relativeURL = URL.parse(relativeURLString);
+        const isAbsolute = relativeURL.slashes || relativeURL.path !== null && relativeURL.path[0] === '/';
+        // 既に絶対的なら、即座に値を返却
+        if (isAbsolute) {
+            return relativeURLString;
+        }
+        // スラッシュを付けて返却
+        return '/' + relativeURLString;
+    };
+    const icon = await find(favicon) ||
+        // 相対指定を絶対指定に変換し再試行
+        await find(toAbsolute(favicon)) ||
+        null;
+    // Clean up the title
+    title = cleanupTitle(title, siteName);
+    if (title === '') {
+        title = siteName;
+    }
+    return {
+        title: title || null,
+        icon: icon || null,
+        description: description || null,
+        thumbnail: image || null,
+        player: {
+            url: playerUrl || null,
+            width: Number.isNaN(playerWidth) ? null : playerWidth,
+            height: Number.isNaN(playerHeight) ? null : playerHeight
+        },
+        sitename: siteName || null,
+        sensitive,
+    };
+};

built/index.d.ts

@@ -0,0 +1,39 @@
+/**
+ * summaly
+ * https://github.com/syuilo/summaly
+ */
+import Summary from './summary.js';
+import type { IPlugin as _IPlugin } from './iplugin.js';
+export declare type IPlugin = _IPlugin;
+import * as Got from 'got';
+import type { FastifyInstance } from 'fastify';
+declare type Options = {
+    /**
+     * Accept-Language for the request
+     */
+    lang?: string | null;
+    /**
+     * Whether follow redirects
+     */
+    followRedirects?: boolean;
+    /**
+     * Custom Plugins
+     */
+    plugins?: IPlugin[];
+    /**
+     * Custom HTTP agent
+     */
+    agent?: Got.Agents;
+};
+declare type Result = Summary & {
+    /**
+     * The actual url of that web page
+     */
+    url: string;
+};
+/**
+ * Summarize an web page
+ */
+export declare const summaly: (url: string, options?: Options | undefined) => Promise<Result>;
+export default function (fastify: FastifyInstance, options: Options, done: (err?: Error) => void): void;
+export {};

built/index.js

@@ -0,0 +1,68 @@
+/**
+ * summaly
+ * https://github.com/syuilo/summaly
+ */
+import * as URL from 'node:url';
+import tracer from 'trace-redirect';
+import general from './general.js';
+import { setAgent } from './utils/got.js';
+import { plugins as builtinPlugins } from './plugins/index.js';
+const defaultOptions = {
+    lang: null,
+    followRedirects: true,
+    plugins: [],
+};
+/**
+ * Summarize an web page
+ */
+export const summaly = async (url, options) => {
+    if (options?.agent)
+        setAgent(options.agent);
+    const opts = Object.assign(defaultOptions, options);
+    const plugins = builtinPlugins.concat(opts.plugins || []);
+    let actualUrl = url;
+    if (opts.followRedirects) {
+        // .catch(() => url)にすればいいけど、jestにtrace-redirectを食わせるのが面倒なのでtry-catch
+        try {
+            actualUrl = await tracer(url);
+        }
+        catch (e) {
+            actualUrl = url;
+        }
+    }
+    const _url = URL.parse(actualUrl, true);
+    // Find matching plugin
+    const match = plugins.filter(plugin => plugin.test(_url))[0];
+    // Get summary
+    const summary = await (match ? match.summarize : general)(_url, opts.lang || undefined);
+    if (summary == null) {
+        throw 'failed summarize';
+    }
+    return Object.assign(summary, {
+        url: actualUrl
+    });
+};
+export default function (fastify, options, done) {
+    fastify.get('/url', async (req, reply) => {
+        const url = req.query.url;
+        if (url == null) {
+            return reply.status(400).send({
+                error: 'url is required'
+            });
+        }
+        try {
+            const summary = await summaly(url, {
+                lang: req.query.lang,
+                followRedirects: false,
+                ...options,
+            });
+            return summary;
+        }
+        catch (e) {
+            return reply.status(500).send({
+                error: e
+            });
+        }
+    });
+    done();
+}

built/iplugin.d.ts

@@ -0,0 +1,7 @@
+/// <reference types="node" />
+import * as URL from 'node:url';
+import Summary from './summary.js';
+export interface IPlugin {
+    test: (url: URL.Url) => boolean;
+    summarize: (url: URL.Url, lang?: string) => Promise<Summary>;
+}

built/iplugin.js

@@ -0,0 +1 @@
+export {};

built/plugins/amazon.d.ts

@@ -0,0 +1,5 @@
+/// <reference types="node" />
+import * as URL from 'node:url';
+import summary from '../summary.js';
+export declare function test(url: URL.Url): boolean;
+export declare function summarize(url: URL.Url): Promise<summary>;

built/plugins/amazon.js

@@ -0,0 +1,43 @@
+import { scpaping } from '../utils/got.js';
+export function test(url) {
+    return url.hostname === 'www.amazon.com' ||
+        url.hostname === 'www.amazon.co.jp' ||
+        url.hostname === 'www.amazon.ca' ||
+        url.hostname === 'www.amazon.com.br' ||
+        url.hostname === 'www.amazon.com.mx' ||
+        url.hostname === 'www.amazon.co.uk' ||
+        url.hostname === 'www.amazon.de' ||
+        url.hostname === 'www.amazon.fr' ||
+        url.hostname === 'www.amazon.it' ||
+        url.hostname === 'www.amazon.es' ||
+        url.hostname === 'www.amazon.nl' ||
+        url.hostname === 'www.amazon.cn' ||
+        url.hostname === 'www.amazon.in' ||
+        url.hostname === 'www.amazon.au';
+}
+export async function summarize(url) {
+    const res = await scpaping(url.href);
+    const $ = res.$;
+    const title = $('#title').text();
+    const description = $('#productDescription').text() ||
+        $('meta[name="description"]').attr('content');
+    const thumbnail = $('#landingImage').attr('src');
+    const playerUrl = $('meta[property="twitter:player"]').attr('content') ||
+        $('meta[name="twitter:player"]').attr('content');
+    const playerWidth = $('meta[property="twitter:player:width"]').attr('content') ||
+        $('meta[name="twitter:player:width"]').attr('content');
+    const playerHeight = $('meta[property="twitter:player:height"]').attr('content') ||
+        $('meta[name="twitter:player:height"]').attr('content');
+    return {
+        title: title ? title.trim() : null,
+        icon: 'https://www.amazon.com/favicon.ico',
+        description: description ? description.trim() : null,
+        thumbnail: thumbnail ? thumbnail.trim() : null,
+        player: {
+            url: playerUrl || null,
+            width: playerWidth ? parseInt(playerWidth) : null,
+            height: playerHeight ? parseInt(playerHeight) : null
+        },
+        sitename: 'Amazon'
+    };
+}

built/plugins/index.d.ts

@@ -0,0 +1,2 @@
+import { IPlugin } from '@/iplugin.js';
+export declare const plugins: IPlugin[];

built/plugins/index.js

@@ -0,0 +1,6 @@
+import * as amazon from './amazon.js';
+import * as wikipedia from './wikipedia.js';
+export const plugins = [
+    amazon,
+    wikipedia,
+];

built/plugins/wikipedia.d.ts

@@ -0,0 +1,5 @@
+/// <reference types="node" />
+import * as URL from 'node:url';
+import summary from '../summary.js';
+export declare function test(url: URL.Url): boolean;
+export declare function summarize(url: URL.Url): Promise<summary>;

built/plugins/wikipedia.js

@@ -0,0 +1,36 @@
+import { get } from '../utils/got.js';
+import debug from 'debug';
+import clip from './../utils/clip.js';
+const log = debug('summaly:plugins:wikipedia');
+export function test(url) {
+    if (!url.hostname)
+        return false;
+    return /\.wikipedia\.org$/.test(url.hostname);
+}
+export async function summarize(url) {
+    const lang = url.host ? url.host.split('.')[0] : null;
+    const title = url.pathname ? url.pathname.split('/')[2] : null;
+    const endpoint = `https://${lang}.wikipedia.org/w/api.php?format=json&action=query&prop=extracts&exintro=&explaintext=&titles=${title}`;
+    log(`lang is ${lang}`);
+    log(`title is ${title}`);
+    log(`endpoint is ${endpoint}`);
+    let body = await get(endpoint);
+    body = JSON.parse(body);
+    log(body);
+    if (!('query' in body) || !('pages' in body.query)) {
+        throw 'fetch failed';
+    }
+    const info = body.query.pages[Object.keys(body.query.pages)[0]];
+    return {
+        title: info.title,
+        icon: 'https://wikipedia.org/static/favicon/wikipedia.ico',
+        description: clip(info.extract, 300),
+        thumbnail: `https://wikipedia.org/static/images/project-logos/${lang}wiki.png`,
+        player: {
+            url: null,
+            width: null,
+            height: null
+        },
+        sitename: 'Wikipedia'
+    };
+}

built/server/index.d.ts

@@ -0,0 +1 @@
+export {};

built/server/index.js

@@ -0,0 +1,22 @@
+import * as http from 'http';
+import * as Koa from 'koa';
+import summaly from '../';
+const app = new Koa();
+app.use(async (ctx) => {
+    if (!ctx.query.url) {
+        ctx.status = 400;
+        return;
+    }
+    try {
+        const summary = await summaly(ctx.query.url, {
+            lang: ctx.query.lang,
+            followRedirects: false
+        });
+        ctx.body = summary;
+    }
+    catch (e) {
+        ctx.status = 500;
+    }
+});
+const server = http.createServer(app.callback());
+server.listen(process.env.PORT || 80);