frenzy-readability/index.js

55 lines
1.3 KiB
JavaScript

import { Readability } from "@mozilla/readability";
import { JSDOM } from "jsdom";
import express from "express";
import morgan from "morgan";
import bodyParser from "body-parser";
import createDOMPurify from "dompurify";
import * as Sentry from "@sentry/node";
import * as Tracing from "@sentry/tracing";
const app = express();
app.use(morgan('combined'));
app.use(bodyParser.text({
type: "text/html",
limit: '1mb',
}));
if (process.env.SENTRY_DSN) {
Sentry.init({
dsn: process.env.SENTRY_DSN,
integrations: [
new Sentry.Integrations.Http({tracing: true}),
new Tracing.Integrations.Express({app}),
],
tracesSampleRate: 0.2
});
app.use(Sentry.Handlers.requestHandler());
app.use(Sentry.Handlers.tracingHandler());
}
app.get('/status', (req, res) => {
res.type('text/plain').send('OK');
});
app.post('/readability', (req, res) => {
const doc = new JSDOM(req.body, {
url: req.params.url,
});
const reader = new Readability(doc.window.document);
const article = reader.parse();
const purifier = createDOMPurify(doc.window);
const cleaned = purifier.sanitize(article.content);
res.send(cleaned);
});
if (process.env.SENTRY_DSN) {
app.use(Sentry.Handlers.errorHandler());
}
const port = process.env.PORT || 4001;
// only accept local requests
app.listen(port, "localhost", () => {
console.log(`listening on port ${port}`);
});