{"id":29998117,"url":"https://github.com/grll/http-use","last_synced_at":"2026-01-20T16:39:53.739Z","repository":{"id":301430108,"uuid":"1009241861","full_name":"grll/http-use","owner":"grll","description":null,"archived":false,"fork":false,"pushed_at":"2025-06-26T20:53:08.000Z","size":30,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-24T18:29:08.010Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/grll.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":"2025-06-26T20:07:03.000Z","updated_at":"2025-07-01T07:11:27.000Z","dependencies_parsed_at":"2025-06-26T21:25:55.596Z","dependency_job_id":"8c5a7364-cbd9-459f-8fce-3105fd234774","html_url":"https://github.com/grll/http-use","commit_stats":null,"previous_names":["grll/http-use"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/grll/http-use","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grll%2Fhttp-use","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grll%2Fhttp-use/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grll%2Fhttp-use/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grll%2Fhttp-use/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/grll","download_url":"https://codeload.github.com/grll/http-use/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grll%2Fhttp-use/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279177292,"owners_count":26119932,"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","status":"online","status_checked_at":"2025-10-16T02:00:06.019Z","response_time":53,"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":[],"created_at":"2025-08-05T03:37:26.944Z","updated_at":"2025-10-16T10:17:21.665Z","avatar_url":"https://github.com/grll.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HTTP-USE\n\n![HTTP-USE](assets/http-use.svg)\n\nUltra efficient web scrapers AI developed on demand.\n\n## How it Works\n\nHTTP-USE is an intelligent web scraping system that creates lightweight, deterministic HTTP-based scrapers on demand. The workflow consists of three main stages:\n\n1. **User Request \u0026 Clarification**: Users specify what data they want to extract (e.g., articles about machine learning from HackerNews). The system clarifies requirements including:\n   - Frequency of scraping needed\n   - Target website URL\n   - Early result validation criteria\n\n2. **Web Agent \u0026 Browser Interaction**: A web agent powered by Playwright MCP navigates the target website, captures screenshots, and generates test cases. This stage produces:\n   - Navigation traces\n   - Element confirmations\n   - Validated test scenarios\n\n3. **Code Generation**: A coding agent uses the traces and confirmed test cases to generate a lightweight, deterministic, and tested HTTP-based scraping script tailored to the specific requirements.\n\nThe system ensures efficient scraping by converting browser-based interactions into optimized HTTP requests, resulting in faster and more reliable data extraction.\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrll%2Fhttp-use","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgrll%2Fhttp-use","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrll%2Fhttp-use/lists"}