{"id":18736981,"url":"https://github.com/darkdk123/ai-web-scraper","last_synced_at":"2026-04-10T21:04:14.783Z","repository":{"id":255966954,"uuid":"853610273","full_name":"DarkDk123/AI-Web-Scraper","owner":"DarkDk123","description":"AI Web Scraper to scrape simple webpages using an LLM.","archived":false,"fork":false,"pushed_at":"2024-09-10T12:06:29.000Z","size":26149,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-28T17:14:32.779Z","etag":null,"topics":["hugging","langchain","python","selenium"],"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/DarkDk123.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}},"created_at":"2024-09-07T03:10:59.000Z","updated_at":"2024-09-11T12:30:18.000Z","dependencies_parsed_at":"2024-09-10T13:30:48.349Z","dependency_job_id":null,"html_url":"https://github.com/DarkDk123/AI-Web-Scraper","commit_stats":null,"previous_names":["darkdk123/ai-web-scraper"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarkDk123%2FAI-Web-Scraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarkDk123%2FAI-Web-Scraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarkDk123%2FAI-Web-Scraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarkDk123%2FAI-Web-Scraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DarkDk123","download_url":"https://codeload.github.com/DarkDk123/AI-Web-Scraper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239611993,"owners_count":19668274,"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":["hugging","langchain","python","selenium"],"created_at":"2024-11-07T15:23:14.547Z","updated_at":"2025-11-17T06:30:16.540Z","avatar_url":"https://github.com/DarkDk123.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Web Scraper 🤖\n\nAn **AI Web Scraper** using LangChain, HuggingFace, selenium etc.\n## Usage\n\n1. Install the required packages: `pip install -r requirements.txt`.\n2. Set the environments variables as explained [below.](#environment-variables)\n3. Run the Streamlit app: `streamlit run streamlit_main.py`.\n4. Enter a URL and a description of what you want to parse from the website.\n5. The app will scrape the website, extract the relevant text, and use the HuggingFace model to parse the text.\n\n\n## Example: Scraping Github profiles\n\n* URL: `https://github.com/techwithtim`\n* query: `Provide info about the Github profile`\n\n![demo](./example.gif)\n\n## Environment Variables\n\nThe AI Web Scraper uses the following environment variables:\n\n* `HUGGINGFACE_MODEL_ID`: The ID of the HuggingFace model to use for parsing the text.\n* `UGGINGFACEHUB_API_TOKEN` : HuggingFace Hub API token.\n\n* `SBR_WEBDRIVER` (Optional for captcha support): The URL of the Bright Data Webdriver to use for solving captchas.\n\n## Development\n\nThe AI Web Scraper is built using the following technologies:\n\n* `streamlit`: The web app framework.\n* `langchain_huggingface`: The library for using HuggingFace models in langchain.\n* `langchain`: Main langchain library.\n* `selenium`: The library for interacting with the browser.\n* `bs4`: The library for parsing HTML.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdarkdk123%2Fai-web-scraper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdarkdk123%2Fai-web-scraper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdarkdk123%2Fai-web-scraper/lists"}