Export from GitHub to DuckDB

brew install cloudquery/tap/cloudquery

kind: source
spec:
  # Source spec section
  name: github
  path: cloudquery/github
  registry: cloudquery
  version: "v9.3.0"
  tables: ["github_issues"]
  destinations: ["duckdb"]
  spec:
    access_token: "${GITHUB_PERSONAL_ACCESS_TOKEN}" # Personal Access Token, required if not using App Authentication.
    # # App Authentication (one per org):
    # app_auth:
    # - org: cloudquery
    #   private_key: <PRIVATE_KEY> # Private key as a string
    #   private_key_path: <PATH_TO_PRIVATE_KEY> # Path to private key file
    #   app_id: <YOUR_APP_ID> # App ID, required for App Authentication.
    #   installation_id: <ORG_INSTALLATION_ID> # Installation ID for this org
    # # List of organizations to sync from. You must specify either orgs or repos in the configuration.
    # orgs: []
    # # List of repositories to sync from. The format is `owner/repo` (e.g. `cloudquery/cloudquery`). You must specify either `orgs` or `repos` in the configuration.
    # repos: ["cloudquery/cloudquery"]
    # # GitHub Enterprise
    # # In order to enable GHE you have to provide two urls, the base url of the server and the upload url.
    # # Quote from GitHub's client:
    # #   If the base URL does not have the suffix "/api/v3/", it will be added automatically. If the upload URL does not have the suffix "/api/uploads", it will be added automatically.
    # #   Another important thing is that by default, the GitHub Enterprise URL format should be http(s)://[hostname]/api/v3/ or you will always receive the 406 status code. The upload URL format should be http(s)://[hostname]/api/uploads/"
    # # If you are not configuring against an enterprise server please omit the enterprise configuration bellow
    # enterprise:
    #     base_url: "http(s)://[your-ghe-hostname]/api/v3/"
    #     upload_url: "http(s)://[your-ghe-hostname]/api/uploads/"
    # # Optional parameters
    # concurrency: 1500 # Optional. The best effort maximum number of Go routines to use. Lower this number to reduce memory usage or to avoid hitting GitHub API rate limits. Default 1500.
    # discovery_concurrency: 1 # Optional. Number of concurrent requests to GitHub API during discovery phase. Default 1.
    # include_archived_repos: false # Optional. Include archived repositories in the sync. Default false.
    # local_cache_path: "" # Optional. Path to a local directory that will hold the cache. If set, the plugin will cache the GitHub API responses in this directory. Defaults to an empty string (no cache).

kind: destination
spec:
  name: duckdb
  path: cloudquery/duckdb
  registry: cloudquery
  version: "v5.5.5"
  write_mode: "overwrite-delete-stale"
  spec:
    connection_string: /path/to/example.db
    # Optional parameters
    # batch_size: 1000
    # batch_size_bytes: 4194304 # 4 MiB
    # debug: false

cloudquery sync github.yml duckdb.yml