mishushakov / llm-scraper
Turn any webpage into structured data using LLMs
Why this job: says: scraper; topics: browser-automation, playwright, scraper
What it does
- Supports GPT, Sonnet, Gemini, Llama, Qwen model series
- Schemas defined with Zod or JSON Schema
- Full type-safety with TypeScript
- Based on Playwright framework
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 months ago
- Stars
- 6,953
- +4 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- TypeScript
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 92% closed
- 3 still open
- Pull requests
- 11 merged
- 7 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Skyvern-AI / skyvern | 23,367 | today | AGPL-3.0 | No downloads |
| nanobrowser / nanobrowser | 14,265 | yesterday | Apache-2.0 | No downloads |
| steel-dev / steel-browser | 7,939 | yesterday | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- TypeScript 100%
Topics
- ai
- artificial-intelligence
- browser
- browser-automation
- gpt
- gpt-4
- langchain
- llama
- llm
- openai
- playwright
- puppeteer
Project record
- JobAutomation and scraping
- StatusListed
- Commits108
- Forks451
- Watching34
- Stars in 28 days+27
- CreatedApr 20, 2024
- First seen by usNov 7, 2026
- CheckedNov 7, 2026