{"id":50720015,"url":"https://github.com/fn-devx/crawler-ai-task","last_synced_at":"2026-06-09T23:01:16.922Z","repository":{"id":361500820,"uuid":"1254703534","full_name":"fn-devX/crawler-ai-task","owner":"fn-devX","description":null,"archived":false,"fork":false,"pushed_at":"2026-05-30T22:50:46.000Z","size":28,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-31T00:14:48.946Z","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/fn-devX.png","metadata":{"files":{"readme":"README.md","changelog":"newskg/__init__.py","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-30T22:48:01.000Z","updated_at":"2026-05-30T22:50:49.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/fn-devX/crawler-ai-task","commit_stats":null,"previous_names":["fn-devx/crawler-ai-task"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/fn-devX/crawler-ai-task","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fn-devX%2Fcrawler-ai-task","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fn-devX%2Fcrawler-ai-task/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fn-devX%2Fcrawler-ai-task/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fn-devX%2Fcrawler-ai-task/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fn-devX","download_url":"https://codeload.github.com/fn-devX/crawler-ai-task/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fn-devX%2Fcrawler-ai-task/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34129072,"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":"2026-06-09T02:00:06.510Z","response_time":63,"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":"2026-06-09T23:01:16.086Z","updated_at":"2026-06-09T23:01:16.916Z","avatar_url":"https://github.com/fn-devX.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n---\n\n## How it works\n\n```\n                        topic listing + article pages\n                                    │\n   ┌───────────┐      ┌──────────────┐     ┌────────────────┐     ┌────────────┐\n   │  Crawler  │────\u003e │    Source    │────\u003e│   Extractor    │────\u003e│   Store    │\n   │ async I/O │      │  TechCrunch  │     │  Claude tool-  │     │  SQLite    │\n   │  + retry  │      │    parser    │     │  use  /  LLM   │     │   graph    │\n   └───────────┘      └──────────────┘     └────────────────┘     └─────┬──────┘\n                                                                        │\n                              fetch → parse → extract → resolve → store │\n                                                                        ▼\n                                                                  ┌────────────┐\n                                                                  │  FastAPI   │\n                                                                  │    API     │\n                                                                  └────────────┘\n```\n\nFive stages run end to end: **crawl** the pages, **parse** them into clean articles,\n**extract** people and relationships with the LLM, **resolve** duplicate names into one\nentity, then **store and serve** the graph. Each layer talks to the next through a small\ninterface, so sources, extractors, and storage are all swappable.\n\n---\n\n## Run it\n\n```bash\n# Python 3.10+\npython -m venv .venv \u0026\u0026 source .venv/bin/activate   # Windows: .venv\\Scripts\\activate\npip install -e \".[dev]\"\n\ncp .env.example .env          # then set ANTHROPIC_API_KEY\n# no key? run fully offline:  export NEWSKG_EXTRACTOR=heuristic\n\nuvicorn newskg.api:app --reload\n```\n\nThen open **http://localhost:8000/docs** — the interactive Swagger UI documents every\nendpoint, with request/response shapes and examples. (ReDoc is at `/redoc`.)\n\n---\n\n## Test it\n\n```bash\npytest\n```\n\nTests run fully offline — no network and no API key required — and cover entity\nresolution, the store's merge/dedup logic, the TechCrunch parser, the API, and the\nevaluation metrics.\n\n\n\n\n# P.S. \n# good joke with apple :)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffn-devx%2Fcrawler-ai-task","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffn-devx%2Fcrawler-ai-task","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffn-devx%2Fcrawler-ai-task/lists"}