Get download metadata from GBIF, write doi/licence to datasette metadata

Dockerfile

@@ -25,6 +25,6 @@ RUN sqlite-utils enable-fts /code/gbifocc.db gbifocc collectorNameAndNumber
 
 RUN chmod 755 /code/gbifocc.db
 
-COPY ./metadata.json /code/metadata.json
+RUN python getDownloadMetadata.py ./metadata.json /code/metadata.json --download_id=$GBIF_DOWNLOAD_ID
 
 CMD ["datasette", "/code/gbifocc.db", "-m", "/code/metadata.json", "--host", "0.0.0.0", "--port", "7860"]

getdDownloadMetadata.py

@@ -0,0 +1,23 @@
+import argparse
+from pygbif import occurrences as occ
+import json
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("inputfile")
+    parser.add_argument("--download_id", type=str)
+    parser.add_argument("outputfile")    
+
+    args = parser.parse_args()
+
+    datasette_metadata = None
+    with open(args.inputfile, 'r') as f_in:
+        datasette_metadata = json.load(f_in)
+ 
+    gbif_metadata = occ.download_meta(key = args.download_id)
+    datasette_metadata['licence'] = gbif_metadata['license']
+    datasette_metadata['source_url'] = 'https://doi.org{}'.format(gbif_metadata['doi'])
+
+    datasette_metadata_json = json.dumps(datasette_metadata)
+    with open(args.outputfile, 'w') as f_out:
+        f_out.write(datasette_metadata_json)

metadata.json

@@ -1,5 +1,7 @@
 {
-    "title": "gbifocc-reconcile",
+    "title": "GBIF-mediated specimen occurrences",
+    "description": "This is a datasette instance containing GBIF-mediated specimen occurrences. It can be used to browse specimen records (with options to filter and facet records) and to run SQL queries. It is also configured to run an Open Refine compatible reconciliation service on collector name and number, allowing a user to easily link specimen references (as found in taxonomic literature) to these specimen records.",
+    "source": "Global Biodiversity Information Facility (GBIF)",
     "databases": {
         "gbifocc": {
             "tables": {

requirements.txt

@@ -6,4 +6,5 @@ csvs-to-sqlite
 pandas==1.5.3
 bananompy
 datasette-jellyfish
-tqdm
+tqdm
+pygbif