# oxylabs/ai-crawler-py

Crawl a website starting from a URL, find relevant pages, and extract data – all guided by your natural language prompt.

Repository: https://github.com/oxylabs/ai-crawler-py
Canonical: https://ross.abutalabs.com/products/ai-crawler-py
Homepage: https://aistudio.oxylabs.io/apps/crawl
License Family: other
Topics: ai, ai-agents, ai-crawler, ai-studio, web-crawler, ai-web-crawler, crawl-agent, ai-scraping
Last push: 2026-08-21T11:42:16+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 25
- inputs: {"age_days": 350, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3218, forks 11 (observed 2026-08-28T04:07:49.679774+00:00)

## What it is
A Python client library for Oxylabs AI Studio's AI-Crawler, a commercial service that crawls websites from a starting URL, uses natural language prompts to find relevant pages, and extracts structured JSON or Markdown data. It wraps a paid API (with a free trial of 1,000 credits) rather than performing crawling locally.

## Use cases
- crawl a website and extract data using a natural language prompt
- find relevant pages on a domain without writing custom scrapers
- extract structured JSON from websites using a schema
- convert website content to markdown for LLM pipelines
- feed crawled web data into AI agents or automation workflows

## When to choose
- you want prompt-driven crawling without building or maintaining scrapers
- you need schema-based structured extraction from websites
- you already use Oxylabs AI Studio or want managed crawling infrastructure

## When to avoid
- you need a fully free, self-hosted crawler with no API costs
- you want full control over crawl logic, politeness, or proxies
- your project cannot depend on a third-party commercial service

## Facets
- artifact type: library
- maturity: active
- function: web-scraping, nlp, etl, data-generation
- domain: crawlers, artificial-intelligence
- platform: python, cloud
- tags: ai-crawler, web-crawler, ai-scraping, oxylabs, api-client, low-code, commercial-service, prompt-driven, data-engineering, automation, web-server

## Member repositories
- oxylabs/ai-crawler-py (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.679774+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:44:54.736931+00:00, confidence not recorded.
  - readme: https://github.com/oxylabs/ai-crawler-py (fetched 2026-08-28T04:07:49.679774+00:00, sha 7c2c2a5e4c10)
  - homepage: https://aistudio.oxylabs.io/apps/crawl (fetched 2026-08-29T09:38:18.944914+00:00, sha 816b67fd1a58)
  - site_page: https://aistudio.oxylabs.io/pricing (fetched 2026-08-29T09:38:18.953741+00:00, sha 9226846bdd8d)
  - site_page: https://aistudio.oxylabs.io/releases (fetched 2026-08-29T09:38:18.955702+00:00, sha 2807647bbec5)
- Data as of 2026-08-30T08:39:29.467469+00:00.