From 83f242c5d1acad6e7af4bb6df459b7535a1853e5 Mon Sep 17 00:00:00 2001
From: Abdulaziz Aloqeely <52792999+DAzVise@users.noreply.github.com>
Date: Sat, 20 Apr 2024 14:11:18 +0300
Subject: [PATCH] Fix wrong dateformat guess if first element had May as month

---
 doc/source/whatsnew/v3.0.0.rst         |  1 +
 pandas/core/tools/datetimes.py         | 11 +++++++++++
 pandas/tests/tools/test_to_datetime.py | 14 ++++++++++++++
 3 files changed, 26 insertions(+)

diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
index f291820bc5266..f505c1e75cfae 100644
--- a/doc/source/whatsnew/v3.0.0.rst
+++ b/doc/source/whatsnew/v3.0.0.rst
@@ -356,6 +356,7 @@ Datetimelike
 - Bug in :class:`Timestamp` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``tzinfo`` or data (:issue:`48688`)
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
 - Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56382`)
+- Bug in :func:`to_datetime` could guess the date format incorrectly if the first element had May as month (:issue:`58328`)
 - Bug in :func:`tseries.api.guess_datetime_format` would fail to infer time format when "%Y" == "%H%M" (:issue:`57452`)
 
 Timedelta
diff --git a/pandas/core/tools/datetimes.py b/pandas/core/tools/datetimes.py
index df7a6cdb1ea52..77791eec0bf96 100644
--- a/pandas/core/tools/datetimes.py
+++ b/pandas/core/tools/datetimes.py
@@ -128,6 +128,17 @@ def _guess_datetime_format_for_array(arr, dayfirst: bool | None = False) -> str
     if (first_non_null := tslib.first_non_null(arr)) != -1:
         if type(first_non_nan_element := arr[first_non_null]) is str:  # noqa: E721
             # GH#32264 np.str_ object
+            if "may" in first_non_nan_element.lower():
+                # GH 58328
+                first_non_nan_element = next(
+                    (
+                        x
+                        for x in arr[first_non_null + 1 :]
+                        if isinstance(x, str) and "may" not in x.lower()
+                    ),
+                    first_non_nan_element,
+                )
+
             guessed_format = guess_datetime_format(
                 first_non_nan_element, dayfirst=dayfirst
             )
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index b59dd194cac27..1a3c94d33e254 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -2649,6 +2649,20 @@ def test_guess_datetime_format_for_array_all_nans(self):
         )
         assert format_for_string_of_nans is None
 
+    @pytest.mark.parametrize(
+        "test_list, expected_format",
+        [
+            (["1 May 2023", "1 Apr 2023", "1 Sep 2023"], "%d %b %Y"),
+            (["1 May 2023", "1 April 2023", "1 September 2023"], "%d %B %Y"),
+            (["1 May 2023", "2 May 2023", "3 May 2023"], "%d %B %Y"),
+        ],
+    )
+    def test_guess_datetime_format_for_array_first_element_month_may(
+        self, test_list, expected_format
+    ):  # GH 58328
+        test_array = np.array(test_list, dtype=object)
+        assert tools._guess_datetime_format_for_array(test_array) == expected_format
+
 
 class TestToDatetimeInferFormat:
     @pytest.mark.parametrize(