{"id":19038650,"url":"https://github.com/devramsean0/wikipedia-crawler","last_synced_at":"2025-08-22T07:40:37.359Z","repository":{"id":198430778,"uuid":"700320623","full_name":"devramsean0/wikipedia-crawler","owner":"devramsean0","description":"A robots.txt respecting web crawler to track how big the Wikipedia network of linked domains goes.","archived":false,"fork":false,"pushed_at":"2025-08-19T13:27:02.000Z","size":43,"stargazers_count":1,"open_issues_count":11,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-19T15:29:56.080Z","etag":null,"topics":["wikipedia-scraper"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/devramsean0.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":"2023-10-04T11:26:13.000Z","updated_at":"2024-09-24T11:07:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"7ecd8d3d-6a42-47cb-a942-2ac4fa7941a1","html_url":"https://github.com/devramsean0/wikipedia-crawler","commit_stats":{"total_commits":12,"total_committers":2,"mean_commits":6.0,"dds":"0.16666666666666663","last_synced_commit":"8836262ba455f1b2553062944ba021e819783b35"},"previous_names":["devramsean0/web-crawler"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/devramsean0/wikipedia-crawler","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devramsean0%2Fwikipedia-crawler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devramsean0%2Fwikipedia-crawler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devramsean0%2Fwikipedia-crawler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devramsean0%2Fwikipedia-crawler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/devramsean0","download_url":"https://codeload.github.com/devramsean0/wikipedia-crawler/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devramsean0%2Fwikipedia-crawler/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271605958,"owners_count":24788968,"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":"2025-08-22T02:00:08.480Z","response_time":65,"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":["wikipedia-scraper"],"created_at":"2024-11-08T22:04:40.279Z","updated_at":"2025-08-22T07:40:37.331Z","avatar_url":"https://github.com/devramsean0.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# wikipedia-crawler\nThis is a robots.txt compliant crawler to try and find out how deep the network of links and pages that stem from \"https://wikipedia.org/\"\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevramsean0%2Fwikipedia-crawler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevramsean0%2Fwikipedia-crawler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevramsean0%2Fwikipedia-crawler/lists"}