Update README

README.md

@@ -73,4 +73,77 @@ STATUS_UPDATE_INTERVAL = 1000
 SENTRY_DSN = <sentry-dsn-for-oai-pmh-harvester>
 ```
 
+## CLI commands
+
+All CLI commands can be run with pipenv run <COMMAND>.
+
+### `oai`
+
+```text
+Usage: -c [OPTIONS] COMMAND [ARGS]...
+
+Options:
+  -h, --host TEXT         Hostname of OAI-PMH server to harvest from, e.g.
+                          https://dspace.mit.edu/oai/request.  [required]
+  -o, --output-file TEXT  Filepath to write output to. Can be a local filepath
+                          or an S3 URI, e.g. S3://bucketname/filename.xml.
+                          [required]
+  -v, --verbose           Optional: enable debug output.
+  --help                  Show this message and exit.
+
+Commands:
+  harvest  Harvest command to retrieve records from an OAI-PMH compliant source.
+  setlist  Create a JSON file describing the set structure of an OAI-PMH compliant source.
+```
+
+### `oai harvest`
+
+```text
+Usage: -c harvest [OPTIONS]
+
+  Harvest command to retrieve records from an OAI-PMH compliant source.
+
+Options:
+  --method [get|list]         Record retrieval method to use. Default 'list'
+                              method is faster and should be used in most
+                              cases; 'get' method should be used for
+                              ArchivesSpace due to errors retrieving a full
+                              record set with the 'list' method.  [default:
+                              list]
+  -m, --metadata-format TEXT  Optional: specify alternate metadata format for
+                              harvested records (e.g. mods, mets, oai_dc, qdc,
+                              ore).  [default: oai_dc]
+  -f, --from-date TEXT        Optional: starting date to harvest records from,
+                              in format YYYY-MM-DD. Limits harvest to records
+                              added/updated on or after the provided date.
+  -u, --until-date TEXT       Optional: ending date to harvest records from,
+                              in format YYYY-MM-DD. Limits harvest to records
+                              added/updated on or before the provided date.
+  -s, --set-spec TEXT         Optional: SetSpec of set to be harvested. Limits
+                              harvest to records in the provided set.
+  -sr, --skip-record TEXT     Optional: OAI-PMH identifier of record to skip
+                              during harvest. Only works if the harvest method
+                              used is 'get'. Can be repeated to skip multiple
+                              records, e.g. '-sr oai:12345 -sr oai:67890'. Can
+                              also be set via ENV variable, see README for
+                              details.
+  --exclude-deleted           Optional: exclude deleted records from harvest.
+  --help                      Show this message and exit.
+```
+
+### `oai setlist`
+```
+Usage: -c setlist [OPTIONS]
+
+  Create a JSON file describing the set structure of an OAI-PMH compliant
+  source.
+
+  Uses the OAI-PMH ListSets verbs to retrieve all sets from a repository, and
+  writes the set names and specs to a JSON output file.
+
+Options:
+  --help  Show this message and exit.
+```
+
+
 

harvester/cli.py

@@ -111,7 +111,7 @@ def harvest(
     skip_record: tuple[str] | None,
     exclude_deleted: bool,
 ) -> None:
-    """Harvest records from an OAI-PMH compliant source and write to an output file."""
+    """Harvest command to retrieve records from an OAI-PMH compliant source."""
     logger.info(
         "OAI-PMH harvesting from source %s with parameters: method=%s, "
         "metadata_format=%s, from_date=%s, until_date=%s, set=%s, skip_record=%s, "
@@ -162,7 +162,7 @@ def harvest(
 @main.command()
 @click.pass_context
 def setlist(ctx: click.Context) -> None:
-    """Get set info from an OAI-PMH compliant source and write to an output file.
+    """Create a JSON file describing the set structure of an OAI-PMH compliant source.
 
     Uses the OAI-PMH ListSets verbs to retrieve all sets from a repository, and writes
     the set names and specs to a JSON output file.