{"id":15173822,"url":"https://github.com/offthetab/vkapi-ml-dataharvester","last_synced_at":"2026-01-31T22:04:06.487Z","repository":{"id":251184008,"uuid":"833376458","full_name":"offthetab/VKAPI-ML-DataHarvester","owner":"offthetab","description":"Pipeline to harvest data via VK API for ML analysis with hadoop and spark","archived":false,"fork":false,"pushed_at":"2024-08-01T09:33:10.000Z","size":7017,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-30T14:50:29.263Z","etag":null,"topics":["hadoop","hdfs","hive","linux","mariadb","python","requests","spark","sqoop"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/offthetab.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}},"created_at":"2024-07-24T23:33:47.000Z","updated_at":"2024-08-29T05:23:14.000Z","dependencies_parsed_at":"2024-08-01T11:12:05.496Z","dependency_job_id":null,"html_url":"https://github.com/offthetab/VKAPI-ML-DataHarvester","commit_stats":null,"previous_names":["offthetab/vkapi-ml-dataharvester"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/offthetab/VKAPI-ML-DataHarvester","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/offthetab%2FVKAPI-ML-DataHarvester","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/offthetab%2FVKAPI-ML-DataHarvester/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/offthetab%2FVKAPI-ML-DataHarvester/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/offthetab%2FVKAPI-ML-DataHarvester/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/offthetab","download_url":"https://codeload.github.com/offthetab/VKAPI-ML-DataHarvester/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/offthetab%2FVKAPI-ML-DataHarvester/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260120515,"owners_count":22961743,"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":["hadoop","hdfs","hive","linux","mariadb","python","requests","spark","sqoop"],"created_at":"2024-09-27T11:02:59.836Z","updated_at":"2026-01-31T22:04:06.480Z","avatar_url":"https://github.com/offthetab.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VKAPI-ML-DataHarvester\n\nПроект автоматического сбора данных о постах в группе, пользователях группы и их постах. Конвейер обработки данных включает в себя Python-скрипт для сбора данных через VK API, HDFS, MariaDB, Sqoop и Spark.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foffthetab%2Fvkapi-ml-dataharvester","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foffthetab%2Fvkapi-ml-dataharvester","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foffthetab%2Fvkapi-ml-dataharvester/lists"}