{"id":21614644,"url":"https://github.com/eea/eea-crawler","last_synced_at":"2026-05-20T03:13:02.965Z","repository":{"id":37827154,"uuid":"372486151","full_name":"eea/eea-crawler","owner":"eea","description":"EEA Crawler contains the tasks (DAGs) used by Apache Airflow to index content from various EEA-Eionet websites into a central Elasticsearch (aka content hub).","archived":false,"fork":false,"pushed_at":"2025-02-03T13:41:29.000Z","size":495,"stargazers_count":1,"open_issues_count":2,"forks_count":0,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-03T14:40:26.204Z","etag":null,"topics":["airflow-dags","crawler","elasticsearch","etl-pipeline","indexing"],"latest_commit_sha":null,"homepage":"","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/eea.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":"2021-05-31T11:41:24.000Z","updated_at":"2025-02-03T13:41:33.000Z","dependencies_parsed_at":"2023-12-06T14:29:31.838Z","dependency_job_id":"16e263b3-8ef4-4fb1-85e1-a4556afcdb45","html_url":"https://github.com/eea/eea-crawler","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eea%2Feea-crawler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eea%2Feea-crawler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eea%2Feea-crawler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eea%2Feea-crawler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eea","download_url":"https://codeload.github.com/eea/eea-crawler/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244266091,"owners_count":20425825,"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":["airflow-dags","crawler","elasticsearch","etl-pipeline","indexing"],"created_at":"2024-11-24T22:08:44.416Z","updated_at":"2026-05-20T03:12:57.945Z","avatar_url":"https://github.com/eea.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Airflow and Logstash configurations for EEA-Crawler\n\nSee https://github.com/eea/eea.docker.airflow for integration and deployment.\n\nBuilding this docker image will create a volume that contains the Python code\nDAGs required for the crawler operation.\n\n[Documentation for Airflow EEA Semantic Search Indexer](./DOCUMENTATION.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feea%2Feea-crawler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feea%2Feea-crawler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feea%2Feea-crawler/lists"}