add date validation

crawler-user-agents.json

@@ -220,7 +220,7 @@
   ,
   {
     "pattern": "httpx",
-    "addition_date":" 2019/12/23",
+    "addition_date": "2019/12/23",
     "instances": [
       "python-httpx/0.16.1",
       "python-httpx/0.13.0.dev1"
@@ -265,7 +265,7 @@
   ,
   {
     "pattern": "phpcrawl",
-    "addition_date": "2012-09/17",
+    "addition_date": "2012/09/17",
     "url": "http://phpcrawl.cuab.de/",
     "instances": [
       "phpcrawl"

validate.py

@@ -6,6 +6,7 @@
 import json
 import re
 from collections import Counter
+import datetime
 
 from jsonschema import validate
 
@@ -59,6 +60,13 @@ def main():
     for entry in json_data:
         pattern = entry['pattern']
 
+        # assert that field "addition_date" has format "2019/12/23",
+        if 'addition_date' in entry:
+            if not re.match(r'\d{4}/\d{2}/\d{2}', entry['addition_date']):
+                raise ValueError('addition_date {!r} has invalid format'.format(entry['addition_date']))
+            # parse the date with datetime
+            datetime.datetime.strptime(entry['addition_date'], '%Y/%m/%d')
+
         # canonicalize entry
         if 'depends_on' not in entry: entry['depends_on'] = []