{"id":15451480,"url":"https://github.com/davidar/oai-sync","last_synced_at":"2025-04-04T14:14:41.212Z","repository":{"id":36652162,"uuid":"40958460","full_name":"davidar/oai-sync","owner":"davidar","description":"Simple script for syncing with OAI repositories","archived":false,"fork":false,"pushed_at":"2015-08-25T09:57:24.000Z","size":128,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-09T23:47:56.401Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Perl","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/davidar.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":"2015-08-18T07:53:10.000Z","updated_at":"2015-08-18T08:07:56.000Z","dependencies_parsed_at":"2022-09-13T05:14:10.407Z","dependency_job_id":null,"html_url":"https://github.com/davidar/oai-sync","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davidar%2Foai-sync","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davidar%2Foai-sync/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davidar%2Foai-sync/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davidar%2Foai-sync/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/davidar","download_url":"https://codeload.github.com/davidar/oai-sync/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247190253,"owners_count":20898702,"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":[],"created_at":"2024-10-01T21:26:00.515Z","updated_at":"2025-04-04T14:14:41.193Z","avatar_url":"https://github.com/davidar.png","language":"Perl","funding_links":[],"categories":[],"sub_categories":[],"readme":"This is a quick and dirty script for harvesting metadata from an [OAI-PMH](https://en.wikipedia.org/wiki/Open_Archives_Initiative_Protocol_for_Metadata_Harvesting) enabled repository.\n\nIt relies on the `Net::OAI::Harvester` perl module, and is derived from the\n`oai-listrecords` script provided in the examples for that library.\n\nExample for harvesting arXiv metadata (honouring flow control directives):\n\n```bash\nmkdir arxiv{0,1,2}\n\n# initial sync\n./oai-sync.pl --baseURL=http://export.arxiv.org/oai2 --metadataPrefix=arXiv \\\n              --dumpDir=./arxiv0/\n\n# resume an interrupted sync with the given token\n./oai-sync.pl --baseURL=http://export.arxiv.org/oai2 --metadataPrefix=arXiv \\\n              --dumpDir=./arxiv1/ --resumptionToken='XXXXXX|XXXXXX'\n\n# sync any new changes since the date of the last sync\n./oai-sync.pl --baseURL=http://export.arxiv.org/oai2 --metadataPrefix=arXiv \\\n              --dumpDir=./arxiv2/ --from='2015-03-14'\n\n# split into individual records\nfor F in ./arxiv*/*.xml; do [ -s $F ] \u0026\u0026 ./oai-split.sh \u003c $F; done\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavidar%2Foai-sync","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdavidar%2Foai-sync","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavidar%2Foai-sync/lists"}