Skip to content

This is a template repository for building a web scraper with OpenAI support. The repository provides a basic project structure with TypeScript and Puppeteer pre-configured, as well as OpenAI's GPT-3 API integration. With this template, you can easily build a scraper that uses machine learning to analyze and extract insights from the scraped data.

Notifications You must be signed in to change notification settings

that-scientist/openai-scraper

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TypeScript Openai Puppeteer Web Scraper Template

This is a template repository for building a web scraper using Openai, TypeScript and Puppeteer. With this template, you can quickly set up a project structure to scrape data, save it to a MySQL database and send emails with the data. This template is designed to be used with the Openai platform, but can be used with any other platform that supports TypeScript.

Getting Started

To use this template, you can simply click the "Use this template" button on GitHub, or fork the repository to your own account.

Once you have the repository on your local machine, you can install the dependencies using Yarn or npm:

yarn install
# or
npm install

To compile the scraper, you can use the start command:

npm run compile
# or
npm run dev-compile

To run the scraper, you can use the start command:

yarn start
# or
npm start

This will run the scraper.ts file, which contains the basic code to launch a headless browser and navigate to a web page. You can modify this file to add your own scraping logic.

TypeScript Support

This template includes TypeScript support out of the box. You can write your scraping code in TypeScript and run it using the ts-node package.

Puppeteer

This template includes the Puppeteer package, which provides a high-level API for controlling headless Chrome or Chromium. You can use Puppeteer to navigate web pages, interact with DOM elements, and extract data.

Contributing

If you find any issues with this template, or have suggestions for improvement, please feel free to open an issue or a pull request. We welcome contributions from the community!

About

This is a template repository for building a web scraper with OpenAI support. The repository provides a basic project structure with TypeScript and Puppeteer pre-configured, as well as OpenAI's GPT-3 API integration. With this template, you can easily build a scraper that uses machine learning to analyze and extract insights from the scraped data.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TypeScript 71.4%
  • Dockerfile 28.6%