BUG: Converting string of type lxml.etree._ElementUnicodeResult to a datetime using pandas.to_datetime (#62604)

Co-authored-by: Matthew Roeschke <[email protected]>

Author: floura-angel

doc/source/whatsnew/v3.0.0.rst

@@ -971,6 +971,8 @@ Datetimelike
 - Bug in constructing arrays with :class:`ArrowDtype` with ``timestamp`` type incorrectly allowing ``Decimal("NaN")`` (:issue:`61773`)
 - Bug in constructing arrays with a timezone-aware :class:`ArrowDtype` from timezone-naive datetime objects incorrectly treating those as UTC times instead of wall times like :class:`DatetimeTZDtype` (:issue:`61775`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
+- Bug in :func:`to_datetime` where passing an ``lxml.etree._ElementUnicodeResult`` together with ``format`` raised  ``TypeError``. Now subclasses of ``str`` are handled. (:issue:`60933`)
+
 
 Timedelta
 ^^^^^^^^^

pandas/_libs/tslibs/strptime.pyx

@@ -405,6 +405,11 @@ def array_strptime(
                 if len(val) == 0 or val in nat_strings:
                     iresult[i] = NPY_NAT
                     continue
+                elif type(val) is not str:
+                    # GH#60933: normalize string subclasses
+                    # (e.g. lxml.etree._ElementUnicodeResult). The downstream Cython
+                    # path expects an exact `str`, so ensure we pass a plain str
+                    val = str(val)
             elif checknull_with_nat_and_na(val):
                 iresult[i] = NPY_NAT
                 continue

pandas/tests/tools/test_to_datetime.py

@@ -3790,3 +3790,14 @@ def test_to_datetime_wrapped_datetime64_ps():
         ["1970-01-01 00:00:01.901901901"], dtype="datetime64[ns]", freq=None
     )
     tm.assert_index_equal(result, expected)
+
+
+def test_to_datetime_lxml_elementunicoderesult_with_format(cache):
+    etree = pytest.importorskip("lxml.etree")
+
+    s = "2025-02-05 16:59:57"
+    node = etree.XML(f"<date>{s}</date>")
+    val = node.xpath("/date/node()")[0]  # _ElementUnicodeResult
+
+    out = to_datetime(Series([val]), format="%Y-%m-%d %H:%M:%S", cache=cache)
+    assert out.iloc[0] == Timestamp(s)