raznem/parsera
Lightweight library for scraping web-sites with LLMs
Extracts structured data from websites by describing desired fields in natural language, with Playwright integration for dynamic content and JavaScript-heavy sites. Supports both synchronous and asynchronous execution, custom LLM models, and includes CLI/Docker deployment options. The library delegates parsing logic to LLMs via API, eliminating need for CSS selectors or XPath expressions.
1,272 stars.
Stars
1,272
Forks
74
Language
Python
License
GPL-2.0
Category
Last pushed
Dec 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/raznem/parsera"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
carlosplanchon/spidercreator
Automated web scraping spider generation using Browser Use and LLMs. Streamline the creation of...
Riddhish1/CogniScrape
Intelligent Web Scraping Library with LLMs
poodle64/supacrawl
Zero-infrastructure web scraping for the terminal
yeahhe365/JustSearch
基于 Playwright 的自主 AI 搜索智能体。支持迭代式任务规划、深度网页爬取，以及带引用来源的多源知识整合。
rednafi/html-to-text
Extract pure text from any webpage