# ScrapeGraphAI/Scrapegraph-ai

> Python web scraping library powered by LLMs: describe in a prompt what data you need, and graph pipelines extract it from websites and local documents (HTML, XML, JSON, Markdown).

- Magnitude: 3.2 out of 10 — Steady
- Stars: 32,016 total · +4 stars measured 2026-10-20, 10:54–12:27 UTC, ≈ 20 by evening
- Star trust: star growth looks organic
- Category: Data & analytics · Language: Python · License: MIT · Created: 2024-01-27 · Last push: 2026-10-06
- GitHub: https://github.com/ScrapeGraphAI/Scrapegraph-ai · Homepage: https://scrapegraphai.com · Page: https://gitnova.dev/en/r/ScrapeGraphAI/Scrapegraph-ai

## Useful for

- Extract structured company data from a single page with SmartScraperGraph
- Collect data from multiple pages with one prompt via SmartScraperMultiGraph
- Generate a reusable Python scraping script with ScriptCreatorGraph

## Why it’s here

- Star-counter measurements on 2026-10-20 (UTC), 10:54–12:27: 32012 → 32016 stars (+4). This is the change over that interval.
- Estimated end-of-day forecast: about +20 stars, using observed gains and the previous day.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #15, +57 stars.
- About 60 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,432
- Issues and pull requests: 1,074
- Watchers: 181
- Average over the last week: 40 per day
- Usual pace: 30 per day
- Stars in the last hour (measured): 3
- Latest release: v2.3.1 (2026-10-06)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-21 … 2026-10-20: 35, 28, 32, 36, 33, 30, 29, 44, 30, 29, 33, 21, 20, 18, 18, 45, 28, 27, 32, 20, 30, 29, 23, 33, 19, 32, 48, 65, 65, 4

## Spotted in now

- GitHub Trending Python today: #15, +57 stars

## Similar by description

1. **77777R7/Octocrawl** — 0.0 · Quiet · AI agents · TypeScript · Not enough measurements today
   Open-source scraping and crawling toolkit that turns web pages into Markdown and structured data for AI agents, RAG and research, with source records and explicit failure reasons.
   Full card: https://gitnova.dev/en/r/77777R7/Octocrawl.md
2. **RayenMlayeh/jevcrawl** — 0.7 · Steady · AI agents · Python · +1 star measured 2026-10-20, 00:32–12:36 UTC, ≈ 2 by evening
   MCP server and CLI that crawls websites for AI agents: a small decision model picks links and passages so the LLM reads only what answers the question. Works in Claude Code, Claude Desktop, Cursor.
   Full card: https://gitnova.dev/en/r/RayenMlayeh/jevcrawl.md
3. **apify/apify-mcp-server** — 4.0 · Steady · AI agents · TypeScript · +89 stars measured 2026-10-20, 00:24–12:26 UTC, ≈ 177 by evening
   Apify MCP server that gives AI agents access to thousands of ready-made scrapers and crawlers from Apify Store to extract data from websites, social media, and maps.
   Full card: https://gitnova.dev/en/r/apify/apify-mcp-server.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-20 12:38 UTC, updated every 30 minutes.