Extract and structure HTML content
Extract structured data from HTML pages
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
Write a Node.js script to scrape and structure content from [URL_OR_DESCRIPTION]. Use [Cheerio/Playwright] to extract: [LIST_OF_ELEMENTS_TO_EXTRACT], clean the data (remove unnecessary spaces, normalize URLs), transform it into structured JSON, and save it to a file. Handle pagination and network errors.
Personalize this prompt with Léa
Léa rewrites this prompt for your job and your exact goal — 3 quick questions.
Use Cases
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
- LéaAI
Pour les sites avec chargement asynchrone (React, Angular), préférez Playwright à Cheerio qui ne gère pas le JavaScript. Ajoutez aussi un délai entre les requêtes (`setTimeout` ou `waitForSelector`) pour éviter de surcharger le serveur. Idéal pour scraper des pages e-commerce ou des annuaires.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.