{"id":24224606,"url":"https://github.com/ms10596/scrape","last_synced_at":"2025-07-27T07:36:27.413Z","repository":{"id":37061248,"uuid":"234290322","full_name":"ms10596/scrape","owner":"ms10596","description":null,"archived":false,"fork":false,"pushed_at":"2023-02-08T00:44:46.000Z","size":124,"stargazers_count":1,"open_issues_count":5,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-04T02:44:19.302Z","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/ms10596.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":"2020-01-16T10:03:25.000Z","updated_at":"2021-12-20T10:47:15.000Z","dependencies_parsed_at":"2023-01-24T08:15:37.569Z","dependency_job_id":null,"html_url":"https://github.com/ms10596/scrape","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ms10596/scrape","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ms10596%2Fscrape","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ms10596%2Fscrape/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ms10596%2Fscrape/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ms10596%2Fscrape/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ms10596","download_url":"https://codeload.github.com/ms10596/scrape/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ms10596%2Fscrape/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267324943,"owners_count":24069401,"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":"2025-07-27T02:00:11.917Z","response_time":82,"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":"2025-01-14T07:17:51.399Z","updated_at":"2025-07-27T07:36:27.393Z","avatar_url":"https://github.com/ms10596.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Scrapest\nscraping engine that is contenraized and deployed in a kubernetes cluster. It scrapes and sends articles to an elasticsearch instance in the cloud.\n\n## Main Blocks\n1. __scraper__: a python program built on the SCRAPY framework. It consists of several spiders that are invoked using a post request.\n2. __elasticsearch__: t3.micro instance of elastic search that presents in AWS cloud service.\n\n## Monitored via cloudwatch\n![image](images/cloudwatch.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fms10596%2Fscrape","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fms10596%2Fscrape","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fms10596%2Fscrape/lists"}