Last active
June 10, 2021 19:33
-
-
Save sloonz/59428ec747e0f36dd81ac5fc47b242f2 to your computer and use it in GitHub Desktop.
Create epub from a list of URLs, using mozilla/readability to extract just the text
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/node | |
| // Install dependencies: npm install @mozilla/readability jsdom got argparse | |
| // Usage: node mkebook.js --title Test url1 url2 > test.epub | |
| const fs = require('fs').promises; | |
| const { spawn } = require('child_process'); | |
| const { JSDOM } = require('jsdom'); | |
| const { Readability } = require('@mozilla/readability'); | |
| const got = require("got"); | |
| const { ArgumentParser } = require('argparse'); | |
| const parser = new ArgumentParser(); | |
| parser.add_argument('-t', '--title', { required: true }); | |
| parser.add_argument('urls', { nargs: '*' }); | |
| async function main(args) { | |
| const { title, urls } = args; | |
| const files = await Promise.all(urls.map(async (url, i) => { | |
| const filename = (i + 1).toString().padStart(3, '0') + '.html'; | |
| const { body } = await got(url); | |
| const { title, content } = new Readability((new JSDOM(body)).window.document).parse(); | |
| const doc = new JSDOM('<html><head><title></title></head><body><h1></h1><div></div></body></html>'); | |
| doc.window.document.querySelector('title').textContent = title; | |
| doc.window.document.querySelector('h1').textContent = title; | |
| doc.window.document.querySelector('div').innerHTML = content; | |
| await fs.writeFile(filename, doc.serialize()); | |
| return filename; | |
| })); | |
| await new Promise((resolve, reject) => { | |
| spawn('pandoc', [`-Mtitle=${title}`, '-t', 'epub', '-o', '-', ...files], { stdio: 'inherit' }) | |
| .on('error', reject) | |
| .on('exit', resolve); | |
| }); | |
| await Promise.all(files.map(file => fs.unlink(file))); | |
| } | |
| main(parser.parse_args()).catch(console.error); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment