To set up:
npm install
Modify function _cleanClasses(node) in node_modules/readability/Readability.js
To run:
node test.js
Last active
December 2, 2017 11:10
-
-
Save bittlingmayer/15dfeb44e8b5108d1a3f5107d4adc50d to your computer and use it in GitHub Desktop.
mozilla/Readability #412
This file contains hidden or 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
| { | |
| "name": "test", | |
| "dependencies": { | |
| "jsdom": "^11.5.1", | |
| "node-fetch": "^1.7.3", | |
| "readability": "github:mozilla/readability" | |
| }, | |
| } |
This file contains hidden or 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
| const { JSDOM } = require("jsdom"); | |
| const Readability = require("readability"); | |
| const OPTIONS = {features: { | |
| FetchExternalResources: false, | |
| ProcessExternalResources: false | |
| }}; | |
| // ... fetch the article's HTML with node-fetch and call _parse | |
| function _parse(url, html) { | |
| console.log("Parsing", url); | |
| console.log('html:', html); | |
| const dom = new JSDOM(html, OPTIONS); | |
| const doc = dom.window.document; | |
| Node = dom.window.Node; | |
| const reader = new Readability(url, doc); | |
| const result = reader.parse(); | |
| } | |
| const fetch = require('node-fetch'); | |
| const URL = 'https://www.cnet.com/es/noticias/twitter-lite-america-latina/#ftag=ESPdf5230a'; | |
| fetch(URL) | |
| .then(function(res) { | |
| return res.text(); | |
| }) | |
| .then(function(html) { | |
| return _parse(URL, html); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment