Last active
April 20, 2023 16:23
-
-
Save dnicolson/165168672b52bac2a3ff82199c4392db to your computer and use it in GitHub Desktop.
Lambda to provide an RSS feed of Exberliner's daily news blog
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
const { parse } = require('node-html-parser'); | |
const { Feed } = require('feed'); | |
const fetch = require('node-fetch'); | |
const BERLIN_DAILY_NEWS_URL = 'https://www.exberliner.com/english-news-berlin/'; | |
const parseHomeHtml = (html) => { | |
const root = parse(html); | |
const [description, title] = root.querySelector('title').rawText.split(' - '); | |
const nodes = root.querySelectorAll('.hero-head__box'); | |
const articleLinks = nodes.map((node) => node.getAttribute('href')); | |
return { title, description, articleLinks }; | |
}; | |
const parseArticleHtml = (html) => { | |
const root = parse(html); | |
const headerNodes = root.querySelectorAll('.entry-header > h1, .entry-header > div, .entry-header > p'); | |
const articleHeader = headerNodes.reduce((acc, node) => { | |
if (node.rawTagName === 'h1') { | |
acc.title = node.rawText; | |
} | |
if (node.classNames === 'user-actions') { | |
const tempDate = node.childNodes[1].innerText.replace(' -', '').replace(' Uhr', ''); | |
const d = tempDate.match(/(\d\d)\.(\d\d)\.(\d\d\d\d)(.*)/); | |
acc.date = new Date(Date.parse(`${d[3]}.${d[2]}.${d[1]}${d[4]}`)); | |
} | |
if (node.rawTagName === 'p' && node.classList.contains('single-excerpt')) { | |
acc.headline = `<p>${node.rawText}</p>`; | |
} | |
return acc; | |
}, {}); | |
const bodyNodes = root.querySelectorAll('.entry-content > figure, .entry-content > p'); | |
const article = bodyNodes.reduce((acc, node) => { | |
if (node.rawTagName === 'p') { | |
if (node.childNodes[0] && !node.childNodes[0].rawTagName) { | |
if (!Date.parse(node.innerText)) { | |
acc.body += node.toString(); | |
} | |
} | |
} else if (node.rawTagName === 'figure') { | |
acc.image = node.toString().replace(/src=.*data-src\="(.*?)"/, 'src="$1"'); | |
} | |
return acc; | |
}, Object.assign(articleHeader, {body: ''})); | |
return article; | |
}; | |
const generateRssFeed = (title, description, link, articles) => { | |
const feed = new Feed({ | |
title, | |
description, | |
link, | |
}); | |
articles.forEach((article) => { | |
feed.addItem({ | |
title: article.title, | |
description: article.headline + article.image + article.body, | |
date: article.date, | |
link: article.link, | |
}); | |
}); | |
return feed.rss2(); | |
}; | |
exports.handler = async (_event) => { | |
const date = new Date(); | |
if (date.getHours() < 8 || date.getHours() > 16 || date.getDay() === 0 || date.getDay() === 6) { | |
const response = { | |
statusCode: 503, | |
}; | |
return response; | |
} | |
const news = await fetch(BERLIN_DAILY_NEWS_URL); | |
const html = await news.text(); | |
const { title, description, articleLinks } = parseHomeHtml(html); | |
const articles = await Promise.all(articleLinks.map(async (link) => { | |
const article = await fetch(link); | |
const html = await article.text(); | |
return Object.assign(parseArticleHtml(html), { link }); | |
})); | |
const rss = generateRssFeed(title, description, BERLIN_DAILY_NEWS_URL, articles); | |
const response = { | |
statusCode: 200, | |
body: rss, | |
}; | |
return response; | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment