大規模言語モデルとグラフロジックを使ってWebサイトやローカルドキュメントからデータを抽出するPythonライブラリです。

pip install scrapegraphai

playwright install

from scrapegraphai.graphs import SmartScraperGraph

graph_config = {
    "llm": {
        "model": "ollama/llama3.2",
        "model_tokens": 8192,
        "format": "json",
    },
    "verbose": True,
    "headless": False,
}

smart_scraper_graph = SmartScraperGraph(
    prompt="Extract useful information from the webpage, including a description of what the company does, founders and social media links",
    source="https://scrapegraphai.com/",
    config=graph_config
)

result = smart_scraper_graph.run()
import json
print(json.dumps(result, indent=4))