ENH: Support for list of formats in pd.to_datetime() (pandas-dev#55226)

pandas/core/tools/datetimes.py

@@ -9,6 +9,7 @@
     Callable,
     TypedDict,
     Union,
+    List,
     cast,
     overload,
 )
@@ -399,6 +400,8 @@ def _convert_listlike_datetimes(
     -------
     Index-like of parsed dates
     """
+
+
     if isinstance(arg, (list, tuple)):
         arg = np.array(arg, dtype="O")
     elif isinstance(arg, NumpyExtensionArray):
@@ -715,13 +718,14 @@ def to_datetime(
     ...
 
 
+#MUDANDO AQUI
 def to_datetime(
     arg: DatetimeScalarOrArrayConvertible | DictConvertible,
     errors: DateTimeErrorChoices = "raise",
     dayfirst: bool = False,
     yearfirst: bool = False,
     utc: bool = False,
-    format: str | None = None,
+    format: str | List[str] | None = None,
     exact: bool | lib.NoDefault = lib.no_default,
     unit: str | None = None,
     infer_datetime_format: lib.NoDefault | bool = lib.no_default,
@@ -795,7 +799,7 @@ def to_datetime(
         <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html
         #time-zone-handling>`_.
 
-    format : str, default None
+    format : str, List[str] , default None
         The strftime to parse time, e.g. :const:`"%d/%m/%Y"`. See
         `strftime documentation
         <https://docs.python.org/3/library/datetime.html
@@ -1065,7 +1069,9 @@ def to_datetime(
     DatetimeIndex(['2018-10-26 12:00:00+00:00', '2020-01-01 18:00:00+00:00'],
                   dtype='datetime64[ns, UTC]', freq=None)
     """
-    if exact is not lib.no_default and format in {"mixed", "ISO8601"}:
+
+
+    if exact is not lib.no_default and format in {"mixed","ISO8601"}:
         raise ValueError("Cannot use 'exact' when 'format' is 'mixed' or 'ISO8601'")
     if infer_datetime_format is not lib.no_default:
         warnings.warn(
@@ -1094,6 +1100,8 @@ def to_datetime(
     # pylint: disable-next=used-before-assignment
     result: Timestamp | NaTType | Series | Index
 
+
+
     if isinstance(arg, Timestamp):
         result = arg
         if utc:
@@ -1125,7 +1133,7 @@ def to_datetime(
             argc = cast(
                 Union[list, tuple, ExtensionArray, np.ndarray, "Series", Index], arg
             )
-            cache_array = _maybe_cache(argc, format, cache, convert_listlike)
+            cache_array = _maybe_cache(argc, format, cache, convert_listlike) # VER TAMBÉM AQUI
         except OutOfBoundsDatetime:
             # caching attempts to create a DatetimeIndex, which may raise
             # an OOB. If that's the desired behavior, then just reraise...
@@ -1138,7 +1146,15 @@ def to_datetime(
         if not cache_array.empty:
             result = _convert_and_box_cache(argc, cache_array)
         else:
-            result = convert_listlike(argc, format)
+            #CHANGED HERE
+            if isinstance(format, (list, tuple)):
+                format = np.array(format, dtype="O")
+                # return list
+                return_list = [Timestamp(convert_listlike([argc[i]],fmt)[0]) for i,fmt in enumerate(format)]
+                # transformed object in DatetimeIndex
+                result = DatetimeIndex(return_list)
+            else:
+                result = convert_listlike(argc, format)
     else:
         result = convert_listlike(np.array([arg]), format)[0]
         if isinstance(arg, bool) and isinstance(result, np.bool_):

pandas/tests/tools/test_to_datetime.py

@@ -1091,6 +1091,19 @@ def test_to_datetime_now_with_format(self, format, expected_ds, string, attribut
         )
         assert (expected - result).max().total_seconds() < 1
 
+
+    def test_to_datetime_where_formart_is_list(self):
+        # https://github.com/pandas-dev/pandas/issues/55226
+        data = ['2023-10-12','2023-10-13 14:30:00']
+        all_formats = ['%Y-%m-%d','%Y-%m-%d %H:%M:%S']
+        result = to_datetime(data,format=all_formats)
+        expected = DatetimeIndex(
+            ['2023-10-12 00:00:00','2023-10-13 14:30:00'], dtype="datetime64[ns]",
+            freq=None
+        )
+        tm.assert_index_equal(result,expected)
+
+
     @pytest.mark.parametrize(
         "dt", [np.datetime64("2000-01-01"), np.datetime64("2000-01-02")]
     )