Created
March 19, 2018 16:42
-
-
Save MrOrz/fb48f27f0f21846d0df521728fda19ce to your computer and use it in GitHub Desktop.
Test web page summarization with Mozilla/Readability.js and puppeteer
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 DOC_URL = process.argv[2]; | |
const puppeteer = require('puppeteer'); | |
const fs = require('fs'); | |
const readabilityJsStr = fs.readFileSync('node_modules/readability/Readability.js', {encoding: 'utf-8'}) | |
function executor() { | |
return new Readability({}, document).parse(); | |
} | |
async function main(){ | |
const browser = await puppeteer.launch(); | |
const page = await browser.newPage(); | |
page.setDefaultNavigationTimeout(5000); | |
console.log('Loading', DOC_URL); | |
try { | |
await page.goto(DOC_URL); | |
} catch(e) { | |
console.error(e); | |
} | |
console.log('Extracting...'); | |
const canonicalUrl = await page.evaluate(() => { | |
const canonicalLink = document.querySelector('link[rel=canonical]'); | |
if(canonicalLink) return canonicalLink.href; | |
const ogUrlMeta = document.querySelector('meta[property="og:url"]'); | |
if(ogUrlMeta) return ogUrlMeta.content; | |
return window.location.href; | |
}); | |
const resultArticle = await page.evaluate(` | |
(function(){ | |
${readabilityJsStr} | |
${executor} | |
return executor(); | |
}()) | |
`); | |
const imageUrl = await page.evaluate(contentHTML => { | |
const ogImageMeta = document.querySelector('meta[property="og:image"], meta[property="og:image:url"]'); | |
if(ogImageMeta) return ogImageMeta.content; | |
const containerDiv = document.createElement('div'); | |
containerDiv.innerHTML = contentHTML; | |
const contentImgs = Array.from(containerDiv.querySelectorAll('img')); | |
if(contentImgs.length === 0) return ''; | |
const largestImg = contentImgs.slice(1).reduce((largestImage, img) => { | |
return largestImage.width * largestImage.height >= img.width * img.height ? largestImage : img | |
}, contentImgs[0]); | |
// src may be relative URL, resolve with current location. | |
return new URL(largestImg.src, location.href).href; | |
}, resultArticle.content); | |
browser.close(); | |
console.log('====='); | |
console.log(canonicalUrl); | |
console.log('====='); | |
console.log(resultArticle.title) | |
console.log('====='); | |
console.log(resultArticle.textContent.trim()) | |
console.log('====='); | |
console.log(imageUrl); | |
console.log('====='); | |
} | |
main(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment