├── .gitignore
├── Dockerfile
├── package.json
├── index.js
└── scrapeLogic.js


/.gitignore:
--------------------------------------------------------------------------------
1 | /node_modules
2 | .env


--------------------------------------------------------------------------------
/Dockerfile:
--------------------------------------------------------------------------------
 1 | FROM ghcr.io/puppeteer/puppeteer:19.7.2
 2 | 
 3 | ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=true \
 4 |     PUPPETEER_EXECUTABLE_PATH=/usr/bin/google-chrome-stable
 5 | 
 6 | WORKDIR /usr/src/app
 7 | 
 8 | COPY package*.json ./
 9 | RUN npm ci
10 | COPY . .
11 | CMD [ "node", "index.js" ]
12 | 
13 | 


--------------------------------------------------------------------------------
/package.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "puppeteer-render",
 3 |   "version": "1.0.0",
 4 |   "description": "",
 5 |   "main": "index.js",
 6 |   "scripts": {
 7 |     "test": "echo \"Error: no test specified\" && exit 1",
 8 |     "start": "node index"
 9 |   },
10 |   "keywords": [],
11 |   "author": "",
12 |   "license": "ISC",
13 |   "dependencies": {
14 |     "dotenv": "^16.0.3",
15 |     "express": "^4.18.2",
16 |     "puppeteer": "^19.7.2"
17 |   }
18 | }
19 | 


--------------------------------------------------------------------------------
/index.js:
--------------------------------------------------------------------------------
 1 | const express = require("express");
 2 | const { scrapeLogic } = require("./scrapeLogic");
 3 | const app = express();
 4 | 
 5 | const PORT = process.env.PORT || 4000;
 6 | 
 7 | app.get("/scrape", (req, res) => {
 8 |   scrapeLogic(res);
 9 | });
10 | 
11 | app.get("/", (req, res) => {
12 |   res.send("Render Puppeteer server is up and running!");
13 | });
14 | 
15 | app.listen(PORT, () => {
16 |   console.log(`Listening on port ${PORT}`);
17 | });
18 | 


--------------------------------------------------------------------------------
/scrapeLogic.js:
--------------------------------------------------------------------------------
 1 | const puppeteer = require("puppeteer");
 2 | require("dotenv").config();
 3 | 
 4 | const scrapeLogic = async (res) => {
 5 |   const browser = await puppeteer.launch({
 6 |     args: [
 7 |       "--disable-setuid-sandbox",
 8 |       "--no-sandbox",
 9 |       "--single-process",
10 |       "--no-zygote",
11 |     ],
12 |     executablePath:
13 |       process.env.NODE_ENV === "production"
14 |         ? process.env.PUPPETEER_EXECUTABLE_PATH
15 |         : puppeteer.executablePath(),
16 |   });
17 |   try {
18 |     const page = await browser.newPage();
19 | 
20 |     await page.goto("https://developer.chrome.com/");
21 | 
22 |     // Set screen size
23 |     await page.setViewport({ width: 1080, height: 1024 });
24 | 
25 |     // Type into search box
26 |     await page.type(".search-box__input", "automate beyond recorder");
27 | 
28 |     // Wait and click on first result
29 |     const searchResultSelector = ".search-box__link";
30 |     await page.waitForSelector(searchResultSelector);
31 |     await page.click(searchResultSelector);
32 | 
33 |     // Locate the full title with a unique string
34 |     const textSelector = await page.waitForSelector(
35 |       "text/Customize and automate"
36 |     );
37 |     const fullTitle = await textSelector.evaluate((el) => el.textContent);
38 | 
39 |     // Print the full title
40 |     const logStatement = `The title of this blog post is ${fullTitle}`;
41 |     console.log(logStatement);
42 |     res.send(logStatement);
43 |   } catch (e) {
44 |     console.error(e);
45 |     res.send(`Something went wrong while running Puppeteer: ${e}`);
46 |   } finally {
47 |     await browser.close();
48 |   }
49 | };
50 | 
51 | module.exports = { scrapeLogic };
52 | 


--------------------------------------------------------------------------------