基于 AI 的 Python 爬虫框架:用自然语言描述要抽取的数据结构,由 LLM 自动生成抓取图谱并完成解析,省去手写 CSS/XPath 选择器。支持多页、多站点任务、本地文件,以及 OpenAI、Ollama、Groq 等多种模型后端。 ⭐ GitHub Stars: 32k+ | 🔗 仓库: https://github.com/ScrapeGraphAI/Scrapegraph-ai
A Python scraper based on AI. You describe the target data structure in natural language and the framework has an LLM generate the scraping graph and run the extraction, skipping hand-written CSS/XPath selectors. Supports multi-page and multi-site jobs, local files and multiple model backends. ⭐ GitHub Stars: 32k+ | 🔗 Repo: https://github.com/ScrapeGraphAI/Scrapegraph-ai
ScrapeGraphAI belongs to the Developer Tools category on hedirbase. Tagged with: web-scraping,llm,python,automation,open-source.
A Python scraper based on AI. You describe the target data structure in natural language and the framework has an LLM generate the scraping graph and run the extraction, skipping hand-written CSS/XPat