├── .gitignore
├── package.json
├── README.md
└── index.js


/.gitignore:
--------------------------------------------------------------------------------
1 | node_modules
2 | 


--------------------------------------------------------------------------------
/package.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "url-to-markdown",
 3 |   "version": "0.0.1",
 4 |   "description": "",
 5 |   "type": "module",
 6 |   "main": "index.js",
 7 |   "scripts": {
 8 |     "test": "echo \"Error: no test specified\" && exit 1"
 9 |   },
10 |   "author": "Tomas Vik (viktomas)",
11 |   "license": "MIT",
12 |   "devDependencies": {
13 |     "jest": "^28.1.1"
14 |   },
15 |   "dependencies": {
16 |     "@mozilla/readability": "^0.4.2",
17 |     "jsdom": "^20.0.0",
18 |     "node-fetch": "^3.2.6",
19 |     "turndown": "^7.1.1",
20 |     "yargs": "^17.5.1"
21 |   }
22 | }
23 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # url-to-markdown: Parse webpages to Markdown from your shell
 2 | 
 3 | `url-to-markdown` is a script that combines [mozilla/readability](https://github.com/mozilla/readability) with [mixmark-io/turndown](https://github.com/mixmark-io/turndown) to let you parse an article on the web into markdown with one command.
 4 | 
 5 | 1. Install [Node](https://nodejs.org/en/) > 12
 6 | 1. Install [Git](https://git-scm.com/)
 7 | 1. Checkout this repo `git checkout https://github.com/viktomas/url-to-markdown.git`
 8 | 1. Enter the folder `cd url-to-markdown`
 9 | 1. Install dependencies `npm i`
10 | 1. Run the script:
11 | 
12 |     ```sh
13 |     ❯❯❯ node index.js https://example.com
14 |     ```
15 |     ```md
16 |     This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.
17 | 
18 |     [More information...](https://www.iana.org/domains/example)
19 |     ```
20 | 


--------------------------------------------------------------------------------
/index.js:
--------------------------------------------------------------------------------
 1 | import { Readability } from '@mozilla/readability';
 2 | import { JSDOM } from 'jsdom';
 3 | import TurndownService from 'turndown';
 4 | import fetch from 'node-fetch';
 5 | import yargs from 'yargs';
 6 | import { hideBin } from 'yargs/helpers';
 7 | 
 8 | const argv = yargs(hideBin(process.argv)).argv;
 9 | 
10 | if (argv._.length !== 1) {
11 |   console.error('You need to pass URL as the only argument');
12 |   process.exit(1);
13 | }
14 | const url = process.argv[2];
15 | 
16 | const makeMarkdownFromUrl = async (url) => {
17 |   const downloadedPage = await (await fetch(url)).text();
18 |   const doc = new JSDOM(downloadedPage, {
19 |     url,
20 |   });
21 |   const reader = new Readability(doc.window.document);
22 |   const article = reader.parse();
23 |   const html = article.content;
24 |   const turndownService = new TurndownService({
25 |     headingStyle: 'atx',
26 |   });
27 |   return turndownService.turndown(html);
28 | };
29 | makeMarkdownFromUrl(url).then(console.log);
30 | 


--------------------------------------------------------------------------------