Extract at ease

Extract information from web with little code at scale.

import httpx
import numenor

numenor.api_key = "n_test_4eC39HqLyjWDarjtT1zdp7dc"

extractor = numenor.HTMLExtractor(name="Hacker News")
extractor.train(
    [
        [
            httpx.get("https://news.ycombinator.com/item?id=38521822").text,
            {"title": "Music from Outer Space", "creator": "brudgers"},
        ],
        [
            httpx.get("https://news.ycombinator.com/item?id=38533869").text,
            {"title": "What it takes to save the axolotl", "creator": "samclemens"},
        ],
    ]
)

# {'title': 'What Is a Hessenberg Matrix?', 'creator': 'jjgreen'}
extractor.extract(httpx.get("https://news.ycombinator.com/item?id=40888085").text)

Easy Integration

Our API seamlessly integrates with your existing crawlers, making data extraction a breeze for your team.

Risk-Free

Pay only for successful extractions.

Advanced Parsing

Intelligent parsing algorithms ensure you get clean, structured data from complex web pages.