1 files changed, 15 insertions, 0 deletions
diff --git a/scripts/parse_cord19_csv.py b/scripts/parse_cord19_csv.py
new file mode 100755
index 0000000..536e5d3
--- /dev/null
+++ b/scripts/parse_cord19_csv.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python3
+
+import sys
+import csv
+import json
+
+CSVFILE = sys.argv[1]
+
+with open(CSVFILE, newline='') as csvfile:
+    reader = csv.DictReader(csvfile)
+    for row in reader:
+        row = dict(row)
+        row['mag_id'] = row.pop('Microsoft Academic Paper ID')
+        row['who_covidence_id'] = row.pop('WHO #Covidence').replace('#', '')
+        print(json.dumps(row, sort_keys=True))