smyja/blackmaria
Python package for webscraping in Natural language
This tool helps developers quickly extract specific information from any webpage by simply describing what you want in plain English. You provide a web address and a natural language request, and it returns the requested data in a structured format like JSON. It's designed for Python developers who need to pull targeted content from websites for various applications.
150 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a Python developer who needs to programmatically extract structured data from diverse web pages using natural language prompts.
Not ideal if you need a no-code solution for web scraping or if your primary need is general-purpose web crawling rather than targeted data extraction.
Stars
150
Forks
11
Language
Python
License
MIT
Category
Last pushed
Oct 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/smyja/blackmaria"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
flairNLP/fundus
A very simple news crawler with a funny name
fhamborg/news-please
news-please - an integrated web crawler and information extractor for news that just works
affjljoo3581/canrevan
대량의 네이버 뉴스 기사를 수집하는 라이브러리입니다.
FreeDiscovery/FreeDiscovery
Web Service for E-Discovery Analytics
tirthajyoti/Web-Database-Analytics
Web scrapping and related analytics using Python tools