Fix TypeError when pulling field that is None

If normalizing a jsonstruct a field can be set to None
due to a schema change.

Co-Authored-By: William Ayd <[email protected]>

Author: bolkedebruin

doc/source/whatsnew/v1.0.0.rst

@@ -792,7 +792,7 @@ I/O
 - Bug in :func:`read_json` where default encoding was not set to ``utf-8`` (:issue:`29565`)
 - Bug in :class:`PythonParser` where str and bytes were being mixed when dealing with the decimal field (:issue:`29650`)
 - :meth:`read_gbq` now accepts ``progress_bar_type`` to display progress bar while the data downloads. (:issue:`29857`)
--
+- Bug in :func:`pandas.io.json.json_normalize` where a missing value in the location specified by `record_path` would raise a ``TypeError`` (:issue:`30148`)
 
 Plotting
 ^^^^^^^^

pandas/io/json/_normalize.py

@@ -3,7 +3,7 @@
 
 from collections import defaultdict
 import copy
-from typing import DefaultDict, Dict, List, Optional, Union
+from typing import Any, DefaultDict, Dict, Iterable, List, Optional, Union, cast
 
 import numpy as np
 
@@ -228,13 +228,17 @@ def json_normalize(
     Returns normalized data with columns prefixed with the given string.
     """
 
-    def _pull_field(js, spec):
-        result = js
+    def _pull_field(js: Dict[str, Any], spec: Union[List, str]) -> List:
         if isinstance(spec, list):
+            _res = js
             for field in spec:
-                result = result[field]
+                _res = _res[field]
+            result = cast(List, _res)
         else:
-            result = result[spec]
+            result = js[spec]
+
+        if not isinstance(result, Iterable):
+            result = []
 
         return result
 

pandas/tests/io/json/test_normalize.py

@@ -463,6 +463,19 @@ def test_nested_flattening_consistent(self):
         # They should be the same.
         tm.assert_frame_equal(df1, df2)
 
+    def test_nonetype_record_path(self, nulls_fixture):
+        # see gh-30148
+        # should not raise TypeError
+        df1 = json_normalize(
+            [
+                {"state": "Texas", "info": nulls_fixture},
+                {"state": "Florida", "info": [{"i": 2}]},
+            ],
+            record_path=["info"],
+        )
+        df2 = DataFrame({"i": 2}, index=[0])
+        tm.assert_equal(df1, df2)
+
 
 class TestNestedToRecord:
     def test_flat_stays_flat(self):