{"id":21715366,"url":"https://github.com/lewisakura/spiderboi","last_synced_at":"2025-04-12T19:35:14.414Z","repository":{"id":34220144,"uuid":"171895410","full_name":"lewisakura/spiderboi","owner":"lewisakura","description":"A web crawling library written in TypeScript.","archived":false,"fork":false,"pushed_at":"2023-01-03T16:35:09.000Z","size":385,"stargazers_count":7,"open_issues_count":12,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T10:00:32.644Z","etag":null,"topics":["spider","typescript","typescript3","web-crawler","web-crawling","web-spider","webcrawler"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/lewisakura.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}},"created_at":"2019-02-21T15:20:18.000Z","updated_at":"2025-01-07T15:02:19.000Z","dependencies_parsed_at":"2023-01-15T05:22:46.706Z","dependency_job_id":null,"html_url":"https://github.com/lewisakura/spiderboi","commit_stats":null,"previous_names":["lewistehminerz/spiderboi"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewisakura%2Fspiderboi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewisakura%2Fspiderboi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewisakura%2Fspiderboi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewisakura%2Fspiderboi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lewisakura","download_url":"https://codeload.github.com/lewisakura/spiderboi/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248622269,"owners_count":21135006,"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":["spider","typescript","typescript3","web-crawler","web-crawling","web-spider","webcrawler"],"created_at":"2024-11-26T00:44:35.219Z","updated_at":"2025-04-12T19:35:14.231Z","avatar_url":"https://github.com/lewisakura.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Spiderboi\n[![NPM](https://nodei.co/npm/spiderboi.png?downloads=true\u0026downloadRank=true\u0026stars=true)](https://nodei.co/npm/spiderboi/)\n\nA web crawling library written in TypeScript.\n\n# Example\n```typescript\nimport Crawler from 'spiderboi';\n\nasync function run() {\n    const crawler = new Crawler('https://google.com');\n\n    // this gets the site's robots.txt so that the crawler can respect it\n    await crawler.readyUp();\n\n    const out = await crawler.crawl('/search/about');\n    console.log(out);\n}\n\nrun();\n/**\n * above code should output:\n * [ 'https://google.com/search/about/',\n * 'https://google.com/search/about/',\n * 'https://google.com/#app-store',\n * 'https://google.com/#app-store',\n * 'https://google.com/#image-texts' ]\n * \n * unless of course google changes the /search/about page and ruins this example.\n */\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewisakura%2Fspiderboi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flewisakura%2Fspiderboi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewisakura%2Fspiderboi/lists"}