{"id":26535928,"url":"https://github.com/cecile-hirschauer/ai_web_scraper","last_synced_at":"2026-06-08T16:04:46.056Z","repository":{"id":283673957,"uuid":"952168467","full_name":"Cecile-Hirschauer/AI_Web_Scraper","owner":"Cecile-Hirschauer","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-24T10:47:44.000Z","size":31,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-08T21:53:07.713Z","etag":null,"topics":["ollama-api","python3","scraping-websites","selenium-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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Cecile-Hirschauer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-03-20T20:58:24.000Z","updated_at":"2025-03-24T11:07:01.000Z","dependencies_parsed_at":"2025-03-21T14:23:19.460Z","dependency_job_id":"d8a51bd7-fa97-4840-a01a-bd95d16a48a1","html_url":"https://github.com/Cecile-Hirschauer/AI_Web_Scraper","commit_stats":null,"previous_names":["cecile-hirschauer/ai_web_scraper"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Cecile-Hirschauer/AI_Web_Scraper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cecile-Hirschauer%2FAI_Web_Scraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cecile-Hirschauer%2FAI_Web_Scraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cecile-Hirschauer%2FAI_Web_Scraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cecile-Hirschauer%2FAI_Web_Scraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cecile-Hirschauer","download_url":"https://codeload.github.com/Cecile-Hirschauer/AI_Web_Scraper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cecile-Hirschauer%2FAI_Web_Scraper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34069500,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ollama-api","python3","scraping-websites","selenium-python","streamlit"],"created_at":"2025-03-21T21:16:54.055Z","updated_at":"2026-06-08T16:04:46.040Z","avatar_url":"https://github.com/Cecile-Hirschauer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Web Scraper\n\nAn intelligent web scraping solution that combines automated browser-based scraping with AI-powered content parsing and Google Sheets integration.\n\n## Overview\n\nAI Web Scraper is a Streamlit-based application that handles the complete web scraping workflow:\n\n1. **Automated Scraping**: Uses Selenium with Bright Data proxy to handle anti-bot measures and CAPTCHAs\n2. **Intelligent Parsing**: Leverages Ollama LLM (Large Language Model) to extract specific information from web content\n3. **Result Storage**: Stores results in both local cache and Google Sheets for easy access and sharing\n4. **User-Friendly Interface**: Provides a clean web interface for all scraping operations\n\n## Features\n\n- **CAPTCHA Handling**: Automatically solves CAPTCHAs using Bright Data's Scraping Browser\n- **Intelligent Content Extraction**: Uses local LLM to extract exactly what you need from scraped content\n- **Caching System**: Efficiently caches scraped content to minimize redundant requests\n- **Google Sheets Integration**: Stores and indexes scraped data for collaborative access\n- **Search \u0026 Retrieve**: Find previously parsed content through text search\n\n## Requirements\n\n- Python 3.8+\n- Ollama with the Llama3 model installed locally\n- Bright Data account with Scraping Browser access\n- Google Cloud Platform account (for Google Sheets integration)\n\n## Installation\n\n1. Clone this repository:\n\n   ```\n   git clone https://github.com/yourusername/AI_Web_Scraper.git\n   cd AI_Web_Scraper\n   ```\n\n2. Install dependencies:\n\n   ```\n   pip install -r requirements.txt\n   ```\n\n3. Create a `.env` file in the project root with the following variables:\n\n   ```\n   BRD_AUTH=your_bright_data_auth_key\n   GOOGLE_CREDENTIALS_FILE=credentials.json\n   ```\n\n4. For Google Sheets integration:\n   - Follow instructions in the Google Cloud Console to create a service account\n   - Download the credentials JSON file and save as `credentials.json` in the project root\n\n## Usage\n\n1. Start the Streamlit app:\n\n   ```\n   streamlit run main.py\n   ```\n\n2. Access the web interface at `http://localhost:8501`\n\n3. Enter a URL to scrape\n\n4. Describe the information you want to extract\n\n5. View and search parsed results in the app or Google Sheets\n\n## Project Structure\n\n- `main.py`: Streamlit web interface\n- `scrape.py`: Web scraping functionality using Selenium\n- `parse.py`: Content parsing using Ollama LLM\n- `cache_manager.py`: Local caching system\n- `gsheets_storage.py`: Google Sheets integration\n- `find_sheet.py`: Utility to find available Google Sheets\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Acknowledgments\n\n- Uses [Bright Data](https://brightdata.com/) for CAPTCHA solving and proxy services\n- Powered by [Ollama](https://ollama.ai/) for local LLM inference\n- Built with [Streamlit](https://streamlit.io/) for the web interface\n- Integrates with [Google Sheets API](https://developers.google.com/sheets/api) for data storage\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcecile-hirschauer%2Fai_web_scraper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcecile-hirschauer%2Fai_web_scraper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcecile-hirschauer%2Fai_web_scraper/lists"}