{"id":29135899,"url":"https://github.com/appugouda-architect/ai-webscraper-agent","last_synced_at":"2025-07-13T22:06:53.985Z","repository":{"id":300529040,"uuid":"1005916532","full_name":"appugouda-architect/ai-webscraper-agent","owner":"appugouda-architect","description":"AI-powered web-scraping agent that uses the Brightdata MCP Server, Fast API, Python, Streamlit UI, Anthropic LLM","archived":false,"fork":false,"pushed_at":"2025-06-24T07:00:36.000Z","size":51,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-30T10:47:34.760Z","etag":null,"topics":["anthropic","fastapi","mcp","python","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/appugouda-architect.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-21T04:46:58.000Z","updated_at":"2025-06-24T07:00:39.000Z","dependencies_parsed_at":"2025-06-22T08:36:59.536Z","dependency_job_id":null,"html_url":"https://github.com/appugouda-architect/ai-webscraper-agent","commit_stats":null,"previous_names":["appugouda-architect/ai-webscraper-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/appugouda-architect/ai-webscraper-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/appugouda-architect%2Fai-webscraper-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/appugouda-architect%2Fai-webscraper-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/appugouda-architect%2Fai-webscraper-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/appugouda-architect%2Fai-webscraper-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/appugouda-architect","download_url":"https://codeload.github.com/appugouda-architect/ai-webscraper-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/appugouda-architect%2Fai-webscraper-agent/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265212407,"owners_count":23728529,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anthropic","fastapi","mcp","python","streamlit"],"created_at":"2025-06-30T10:37:33.573Z","updated_at":"2025-07-13T22:06:53.928Z","avatar_url":"https://github.com/appugouda-architect.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🕸️ AI Webscraper Agent\n\nAn AI-powered webscraping agent that uses the Brightdata MCP server to extract and summarize content from the web. Built with a modular architecture combining LLM reasoning, robust scraping, and a simple web interface.\n\n---\n\n## 🔧 Tech Stack\n\n- **Frontend**: [Streamlit](https://streamlit.io/)\n- **Backend**: [FastAPI](https://fastapi.tiangolo.com/)\n- **Language**: Python\n- **Scraping**: [Brightdata MCP Server](https://brightdata.com/)\n- **AI Model**: Anthropic LLM (Claude)\n\n---\n\n## 🚀 Features\n\n- Natural language interface to extract data from websites\n- Uses Brightdata MCP for reliable web scraping\n- LLM-powered summarization and reasoning\n- Streamlit-based interactive frontend\n- Async FastAPI backend integration\n\n---\n\n## Environment Variables\n\nCreate a .env file and configure the following:\n\n```dotenv\n# .env\n# Environment Variables for AI Webscraper Agent\n# Replace 'your_key_here' with your actual API keys\n\n# Bright Data\nAPI_TOKEN=your_key_here\nWEB_UNLOCKER_ZONE=your_key_here\nBROWSER_AUTH=\"your_browser_auth_token\"\n\n#Anthropic AI API KEY\nANTHROPIC_API_KEY=your_key_here\n```\n\n## 📦 Installation\n\n```bash\ngit clone https://github.com/yourusername/ai-webscraper-agent.git\ncd ai-webscraper-agent\n\nuv pip install -r requirements.txt\n```\n\n## RUN App\n\n### Start the FastAPI backend server and Streamlit app'\n\n### Start the backend FastAPI server\n\n```bash\nuv run backend.py\n```\n\n### Start frontend Streamlit app\n\n```bash\nstreamlit run frontend.py\n```\n\n## Example Usage\n\n## Ask:\n\n```\nScrape the top 5 news headlines from https://bbc.com and summarize them.\n```\n\n## Get Response:\n\n```\n1. Headline A - Summary\n2. Headline B - Summary\n3. Headline C - Summary\n4. Headline C - Summary\n...\n```\n\n## Agent Flow\n\n[User Prompt] ➡ [Streamlit UI] ➡ [FastAPI Router] ➡ [LLM Agent]\n➡ [Brightdata Tool via MCP] ➡ [LLM Summarization] ➡ [UI Response]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fappugouda-architect%2Fai-webscraper-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fappugouda-architect%2Fai-webscraper-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fappugouda-architect%2Fai-webscraper-agent/lists"}