[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2284":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},2284,"Scrapegraph-ai","ScrapeGraphAI\u002FScrapegraph-ai","ScrapeGraphAI","Python scraper based on AI","https:\u002F\u002Fscrapegraphai.com",null,"Python",27080,2543,153,1,0,43,368,2102,241,45,"MIT License",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"ai-crawler","ai-scraping","ai-search","crawler","data-extraction","firecrawl-alternative","large-language-model","llm","markdown","rag","scraping","scraping-python","web-crawler","web-crawlers","web-data","web-data-extraction","web-scraper","web-scraping","web-search","webscraping","2026-06-12 02:00:39","## 🚀 **Looking for an even faster and simpler way to scrape at scale (only 5 lines of code)?** Check out our enhanced version at [**ScrapeGraphAI.com**](https:\u002F\u002Fscrapegraphai.com\u002F?utm_source=github&utm_medium=readme&utm_campaign=oss_cta&ut#m_content=top_banner)! 🚀\n\n---\n\n# 🕷️ ScrapeGraphAI: You Only Scrape Once\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fscrapegraphai.com\">\n    \u003Cimg src=\"media\u002Fbanner.png\" alt=\"ScrapeGraphAI\" style=\"width: 100%;\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n[English](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002FREADME.md) | [中文](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Fchinese.md) | [日本語](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Fjapanese.md)\n| [한국어](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Fkorean.md)\n| [Русский](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Frussian.md) | [Türkçe](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Fturkish.md)\n| [Deutsch](https:\u002F\u002Fwww.readme-i18n.com\u002FScrapeGraphAI\u002FScrapegraph-ai?lang=de)\n| [Español](https:\u002F\u002Fwww.readme-i18n.com\u002FScrapeGraphAI\u002FScrapegraph-ai?lang=es)\n| [français](https:\u002F\u002Fwww.readme-i18n.com\u002FScrapeGraphAI\u002FScrapegraph-ai?lang=fr)\n| [Português](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002Fdocs\u002Fportuguese.md)\n\n[![PyPI Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fpersonalized-badge\u002Fscrapegraphai?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https:\u002F\u002Fpepy.tech\u002Fprojects\u002Fscrapegraphai)\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg?style=for-the-badge)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002FgkxQDAjfeX)](https:\u002F\u002Fdiscord.gg\u002FgkxQDAjfeX)\n\n\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F9761\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F9761\" alt=\"VinciGit00%2FScrapegraph-ai | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\u003Cp align=\"center\">\n\n[ScrapeGraphAI](https:\u002F\u002Fscrapegraphai.com) is a *web scraping* python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, Markdown, etc.).\n\nJust say which information you want to extract and the library will do it for you!\n\n## 🚀 Integrations\nScrapeGraphAI offers seamless integration with popular frameworks and tools to enhance your scraping capabilities. Whether you're building with Python or Node.js, using LLM frameworks, or working with no-code platforms, we've got you covered with our comprehensive integration options..\n\nYou can find more informations at the following [link](https:\u002F\u002Fscrapegraphai.com)\n\n**Integrations**:\n- **API**: [Documentation](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintroduction)\n- **SDKs**: [Python](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fsdks\u002Fpython), [Node](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fsdks\u002Fjavascript)\n- **LLM Frameworks**: [Langchain](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintegrations\u002Flangchain), [Llama Index](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintegrations\u002Fllamaindex), [Crew.ai](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintegrations\u002Fcrewai), [Agno](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintegrations\u002Fagno), [CamelAI](https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel)\n- **Low-code Frameworks**: [Pipedream](https:\u002F\u002Fpipedream.com\u002Fapps\u002Fscrapegraphai), [Bubble](https:\u002F\u002Fbubble.io\u002Fplugin\u002Fscrapegraphai-1745408893195x213542371433906180), [Zapier](https:\u002F\u002Fzapier.com\u002Fapps\u002Fscrapegraphai\u002Fintegrations), [n8n](http:\u002F\u002Flocalhost:5001\u002Fdashboard), [Dify](https:\u002F\u002Fdify.ai), [Toolhouse](https:\u002F\u002Fapp.toolhouse.ai\u002Fmcp-servers\u002Fscrapegraph_smartscraper)\n- **MCP server**:  [Link](https:\u002F\u002Fsmithery.ai\u002Fserver\u002F@ScrapeGraphAI\u002Fscrapegraph-mcp)\n\n## 🚀 Quick install\n\nThe reference page for Scrapegraph-ai is available on the official page of PyPI: [pypi](https:\u002F\u002Fpypi.org\u002Fproject\u002Fscrapegraphai\u002F).\n\n```bash\npip install scrapegraphai\n\n# IMPORTANT (for fetching websites content)\nplaywright install\n```\n\n**Note**: it is recommended to install the library in a virtual environment to avoid conflicts with other libraries 🐱\n\n\n## 💻 Usage\nThere are multiple standard scraping pipelines that can be used to extract information from a website (or local file).\n\nThe most common one is the `SmartScraperGraph`, which extracts information from a single page given a user prompt and a source URL.\n\n\n```python\nfrom scrapegraphai.graphs import SmartScraperGraph\n\n# Define the configuration for the scraping pipeline\ngraph_config = {\n    \"llm\": {\n        \"model\": \"ollama\u002Fllama3.2\",\n        \"model_tokens\": 8192,\n        \"format\": \"json\",\n    },\n    \"verbose\": True,\n    \"headless\": False,\n}\n\n# Create the SmartScraperGraph instance\nsmart_scraper_graph = SmartScraperGraph(\n    prompt=\"Extract useful information from the webpage, including a description of what the company does, founders and social media links\",\n    source=\"https:\u002F\u002Fscrapegraphai.com\u002F\",\n    config=graph_config\n)\n\n# Run the pipeline\nresult = smart_scraper_graph.run()\n\nimport json\nprint(json.dumps(result, indent=4))\n```\n\n> [!NOTE]\n> For OpenAI and other models you just need to change the llm config!\n> ```python\n>graph_config = {\n>    \"llm\": {\n>        \"api_key\": \"YOUR_OPENAI_API_KEY\",\n>        \"model\": \"openai\u002Fgpt-4o-mini\",\n>    },\n>    \"verbose\": True,\n>    \"headless\": False,\n>}\n>```\n\n\nThe output will be a dictionary like the following:\n\n```python\n{\n    \"description\": \"ScrapeGraphAI transforms websites into clean, organized data for AI agents and data analytics. It offers an AI-powered API for effortless and cost-effective data extraction.\",\n    \"founders\": [\n        {\n            \"name\": \"\",\n            \"role\": \"Founder & Technical Lead\",\n            \"linkedin\": \"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fperinim\u002F\"\n        },\n        {\n            \"name\": \"Marco Vinciguerra\",\n            \"role\": \"Founder & Software Engineer\",\n            \"linkedin\": \"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmarco-vinciguerra-7ba365242\u002F\"\n        },\n        {\n            \"name\": \"Lorenzo Padoan\",\n            \"role\": \"Founder & Product Engineer\",\n            \"linkedin\": \"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Florenzo-padoan-4521a2154\u002F\"\n        }\n    ],\n    \"social_media_links\": {\n        \"linkedin\": \"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002F101881123\",\n        \"twitter\": \"https:\u002F\u002Fx.com\u002Fscrapegraphai\",\n        \"github\": \"https:\u002F\u002Fgithub.com\u002FScrapeGraphAI\u002FScrapegraph-ai\"\n    }\n}\n```\nThere are other pipelines that can be used to extract information from multiple pages, generate Python scripts, or even generate audio files.\n\n| Pipeline Name           | Description                                                                                                      |\n|-------------------------|------------------------------------------------------------------------------------------------------------------|\n| SmartScraperGraph       | Single-page scraper that only needs a user prompt and an input source.                                           |\n| SearchGraph             | Multi-page scraper that extracts information from the top n search results of a search engine.                  |\n| SpeechGraph             | Single-page scraper that extracts information from a website and generates an audio file.                       |\n| ScriptCreatorGraph      | Single-page scraper that extracts information from a website and generates a Python script.                     |\n| SmartScraperMultiGraph  | Multi-page scraper that extracts information from multiple pages given a single prompt and a list of sources.    |\n| ScriptCreatorMultiGraph | Multi-page scraper that generates a Python script for extracting information from multiple pages and sources.     |\n\nFor each of these graphs there is the multi version. It allows to make calls of the LLM in parallel.\n\nIt is possible to use different LLM through APIs, such as **OpenAI**, **Groq**, **Azure**, **Gemini**, **MiniMax** and more, or local models using **Ollama**.\n\nRemember to have [Ollama](https:\u002F\u002Follama.com\u002F) installed and download the models using the **ollama pull** command, if you want to use local models.\n\n\n## 📖 Documentation\n\n[![Open In Colab](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1sEZBonBMGP44CtO6GQTwAlL0BGJXjtfd?usp=sharing)\n\nThe documentation for ScrapeGraphAI can be found [here](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintroduction).\n\n## 🤝 Contributing\n\nFeel free to contribute and join our Discord server to discuss with us improvements and give us suggestions!\n\nPlease see the [contributing guidelines](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002FCONTRIBUTING.md).\n\n[![My Skills](https:\u002F\u002Fskillicons.dev\u002Ficons?i=discord)](https:\u002F\u002Fdiscord.gg\u002FuJN7TYcpNa)\n[![My Skills](https:\u002F\u002Fskillicons.dev\u002Ficons?i=linkedin)](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fscrapegraphai\u002F)\n[![My Skills](https:\u002F\u002Fskillicons.dev\u002Ficons?i=twitter)](https:\u002F\u002Ftwitter.com\u002Fscrapegraphai)\n\n## 🔗 ScrapeGraph API & SDKs\nIf you are looking for a quick solution to integrate ScrapeGraph in your system, check out our powerful API [here!](https:\u002F\u002Fdashboard.scrapegraphai.com\u002Flogin)\n\n[![API Banner](https:\u002F\u002Fraw.githubusercontent.com\u002FScrapeGraphAI\u002FScrapegraph-ai\u002Fmain\u002Fdocs\u002Fassets\u002Fapi_banner.png)](https:\u002F\u002Fdashboard.scrapegraphai.com\u002Flogin)\n\nWe offer SDKs in both Python and Node.js, making it easy to integrate into your projects. Check them out below:\n\n| SDK       | Language | GitHub Link                                                                 |\n|-----------|----------|-----------------------------------------------------------------------------|\n| Python SDK | Python   | [scrapegraph-py](https:\u002F\u002Fgithub.com\u002FScrapeGraphAI\u002Fscrapegraph-sdk\u002Ftree\u002Fmain\u002Fscrapegraph-py) |\n| Node.js SDK | Node.js  | [scrapegraph-js](https:\u002F\u002Fgithub.com\u002FScrapeGraphAI\u002Fscrapegraph-sdk\u002Ftree\u002Fmain\u002Fscrapegraph-js) |\n\nThe Official API Documentation can be found [here](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintroduction).\n\n## 📈 Telemetry\nWe collect anonymous usage metrics to enhance our package's quality and user experience. The data helps us prioritize improvements and ensure compatibility. If you wish to opt-out, set the environment variable SCRAPEGRAPHAI_TELEMETRY_ENABLED=false. For more information, please refer to the documentation [here](https:\u002F\u002Fdocs.scrapegraphai.com\u002Fintroduction).\n\n## ❤️ Contributors\n[![Contributors](https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=VinciGit00\u002FScrapegraph-ai)](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fgraphs\u002Fcontributors)\n\n## 🎓 Citations\nIf you have used our library for research purposes please quote us with the following reference:\n```text\n  @misc{scrapegraph-ai,\n    author = {Lorenzo Padoan, Marco Vinciguerra},\n    title = {Scrapegraph-ai},\n    year = {2024},\n    url = {https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai},\n    note = {A Python library for scraping leveraging large language models}\n  }\n```\n## Authors\n\n|                    | Contact Info         |\n|--------------------|----------------------|\n| Marco Vinciguerra  | [![Linkedin Badge](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Linkedin-blue?style=flat&logo=Linkedin&logoColor=white)](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmarco-vinciguerra-7ba365242\u002F)    |\n| Lorenzo Padoan     | [![Linkedin Badge](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Linkedin-blue?style=flat&logo=Linkedin&logoColor=white)](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Florenzo-padoan-4521a2154\u002F)  |\n\n## 📜 License\n\nScrapeGraphAI is licensed under the MIT License. See the [LICENSE](https:\u002F\u002Fgithub.com\u002FVinciGit00\u002FScrapegraph-ai\u002Fblob\u002Fmain\u002FLICENSE) file for more information.\n\n## Acknowledgements\n\n- We would like to thank all the contributors to the project and the open-source community for their support.\n- ScrapeGraphAI is meant to be used for data exploration and research purposes only. We are not responsible for any misuse of the library.\n\nMade with ❤️ by [ScrapeGraph AI](https:\u002F\u002Fscrapegraphai.com)\n\n[Scarf tracking](https:\u002F\u002Fstatic.scarf.sh\u002Fa.png?x-pxid=102d4b8c-cd6a-4b9e-9a16-d6d141b9212d)\n","ScrapeGraphAI 是一个基于人工智能的 Python 网络爬虫库，用于从网页和本地文档（如 XML、HTML、JSON、Markdown 等）中提取信息。其核心功能包括利用大型语言模型（LLM）和直接图逻辑来构建高效的数据抓取流程，用户只需指定所需数据即可自动完成抓取任务。该项目支持与多种流行框架及工具无缝集成，包括 Python 和 Node.js 开发环境以及 LLM 框架等，极大提升了数据抓取的灵活性和适用范围。ScrapeGraphAI 适用于需要快速、简便地进行大规模网络数据采集的各种场景，尤其适合那些希望减少代码编写量同时提高数据获取效率的开发者或团队使用。",2,"2026-06-11 02:49:17","top_language"]