Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mishushakov/llm-scraper
Turn any webpage into structured data using LLMs
https://github.com/mishushakov/llm-scraper
ai artificial-intelligence browser browser-automation gpt gpt-4 langchain llama llm openai playwright puppeteer scraper
Last synced: about 1 month ago
JSON representation
Turn any webpage into structured data using LLMs
- Host: GitHub
- URL: https://github.com/mishushakov/llm-scraper
- Owner: mishushakov
- License: mit
- Created: 2024-04-20T17:06:57.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-07-25T06:20:35.000Z (about 2 months ago)
- Last Synced: 2024-07-31T00:24:15.015Z (about 1 month ago)
- Topics: ai, artificial-intelligence, browser, browser-automation, gpt, gpt-4, langchain, llama, llm, openai, playwright, puppeteer, scraper
- Language: TypeScript
- Homepage:
- Size: 171 KB
- Stars: 1,947
- Watchers: 14
- Forks: 134
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome - mishushakov/llm-scraper - Turn any webpage into structured data using LLMs (TypeScript)
- AiTreasureBox - mishushakov/llm-scraper - 09-08_2139_1](https://img.shields.io/github/stars/mishushakov/llm-scraper.svg)|Turn any webpage into structured data using LLMs| (Repos)
- StarryDivineSky - mishushakov/llm-scraper
- my-awesome-list - llm-scraper
README
# LLM Scraper
LLM Scraper is a TypeScript library that allows you to extract structured data from **any** webpage using LLMs.
> [!IMPORTANT]
> [Code-generation](#code-generation) is now supported in LLM Scraper.
> [!TIP]
> Under the hood, it uses function calling to convert pages to structured data. You can find more about this approach [here](https://til.simonwillison.net/gpt3/openai-python-functions-data-extraction).
### Features
- Supports **Local (Ollama, GGUF)**, OpenAI, Vercel AI SDK Providers
- Schemas defined with Zod
- Full type-safety with TypeScript
- Based on Playwright framework
- Streaming objects
- **NEW** [Code-generation](#code-generation)
- Supports 4 formatting modes:
- `html` for loading raw HTML
- `markdown` for loading markdown
- `text` for loading extracted text (using [Readability.js](https://github.com/mozilla/readability))
- `image` for loading a screenshot (multi-modal only)
**Make sure to give it a star!**
## Getting started
1. Install the required dependencies from npm:
```
npm i zod playwright llm-scraper
```
2. Initialize your LLM:
**OpenAI**
```
npm i @ai-sdk/openai
```
```js
import { openai } from '@ai-sdk/openai'
const llm = openai.chat('gpt-4o')
```
**Groq**
```
npm i @ai-sdk/openai
```
```js
import { createOpenAI } from '@ai-sdk/openai'
const groq = createOpenAI({
baseURL: 'https://api.groq.com/openai/v1',
apiKey: process.env.GROQ_API_KEY,
})
const llm = groq('llama3-8b-8192')
```
**Ollama**
```
npm i ollama-ai-provider
```
```js
import { ollama } from 'ollama-ai-provider'
const llm = ollama('llama3')
```
**GGUF**
```js
import { LlamaModel } from 'node-llama-cpp'
const llm = new LlamaModel({ modelPath: 'model.gguf' })
```
3. Create a new scraper instance provided with the llm:
```js
import LLMScraper from 'llm-scraper'
const scraper = new LLMScraper(llm)
```
## Example
In this example, we're extracting top stories from HackerNews:
```ts
import { chromium } from 'playwright'
import { z } from 'zod'
import { openai } from '@ai-sdk/openai'
import LLMScraper from 'llm-scraper'
// Launch a browser instance
const browser = await chromium.launch()
// Initialize LLM provider
const llm = openai.chat('gpt-4o')
// Create a new LLMScraper
const scraper = new LLMScraper(llm)
// Open new page
const page = await browser.newPage()
await page.goto('https://news.ycombinator.com')
// Define schema to extract contents into
const schema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe('Top 5 stories on Hacker News'),
})
// Run the scraper
const { data } = await scraper.run(page, schema, {
format: 'html',
})
// Show the result from LLM
console.log(data.top)
await page.close()
await browser.close()
```
## Streaming
Replace your `run` function with `stream` to get a partial object stream (Vercel AI SDK only).
```ts
// Run the scraper in streaming mode
const { stream } = await scraper.stream(page, schema)
// Stream the result from LLM
for await (const data of stream) {
console.log(data.top)
}
```
## Code-generation
Using the `generate` function you can generate re-usable playwright script that scrapes the contents according to a schema.
```ts
// Generate code and run it on the page
const { code } = await scraper.generate(page, schema)
const result = await page.evaluate(code)
const data = schema.parse(result)
// Show the parsed result
console.log(data.news)
```
## Contributing
As an open-source project, we welcome contributions from the community. If you are experiencing any bugs or want to add some improvements, please feel free to open an issue or pull request.