DEP: Remove xlrd as being the default reader for xlsx (#39796)

Author: rhshadrach

doc/source/user_guide/io.rst

@@ -2853,14 +2853,12 @@ See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
    The `xlrd <https://xlrd.readthedocs.io/en/latest/>`__ package is now only for reading
    old-style ``.xls`` files.
 
-   Before pandas 1.2.0, the default argument ``engine=None`` to :func:`~pandas.read_excel`
+   Before pandas 1.3.0, the default argument ``engine=None`` to :func:`~pandas.read_excel`
    would result in using the ``xlrd`` engine in many cases, including new
-   Excel 2007+ (``.xlsx``) files.
-   If `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__  is installed,
-   many of these cases will now default to using the ``openpyxl`` engine.
-   See the :func:`read_excel` documentation for more details.
+   Excel 2007+ (``.xlsx``) files. pandas will now default to using the
+   `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__ engine.
 
-   Thus, it is strongly encouraged to install ``openpyxl`` to read Excel 2007+
+   It is strongly encouraged to install ``openpyxl`` to read Excel 2007+
    (``.xlsx``) files.
    **Please do not report issues when using ``xlrd`` to read ``.xlsx`` files.**
    This is no longer supported, switch to using ``openpyxl`` instead.

doc/source/whatsnew/v1.3.0.rst

@@ -8,6 +8,16 @@ including other versions of pandas.
 
 {{ header }}
 
+.. warning::
+
+   When reading new Excel 2007+ (``.xlsx``) files, the default argument
+   ``engine=None`` to :func:`~pandas.read_excel` will now result in using the
+   `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`_ engine in all cases
+   when the option :attr:`io.excel.xlsx.reader` is set to ``"auto"``.
+   Previously, some cases would use the
+   `xlrd <https://xlrd.readthedocs.io/en/latest/>`_ engine instead. See
+   :ref:`What's new 1.2.0 <whatsnew_120>` for background on this change.
+
 .. ---------------------------------------------------------------------------
 
 Enhancements

pandas/io/excel/_base.py

@@ -158,11 +158,9 @@
          ``pyxlsb`` will be used.
 
          .. versionadded:: 1.3.0
-       - Otherwise if `openpyxl <https://pypi.org/project/openpyxl/>`_ is installed,
-         then ``openpyxl`` will be used.
-       - Otherwise if ``xlrd >= 2.0`` is installed, a ``ValueError`` will be raised.
-       - Otherwise ``xlrd`` will be used and a ``FutureWarning`` will be raised. This
-         case will raise a ``ValueError`` in a future version of pandas.
+       - Otherwise ``openpyxl`` will be used.
+
+         .. versionchanged:: 1.3.0
 
 converters : dict, default None
     Dict of functions for converting values in certain columns. Keys can
@@ -1026,7 +1024,7 @@ class ExcelFile:
     Parameters
     ----------
     path_or_buffer : str, path object (pathlib.Path or py._path.local.LocalPath),
-        a file-like object, xlrd workbook or openpypl workbook.
+        a file-like object, xlrd workbook or openpyxl workbook.
         If a string or path object, expected to be a path to a
         .xls, .xlsx, .xlsb, .xlsm, .odf, .ods, or .odt file.
     engine : str, default None
@@ -1140,9 +1138,7 @@ def __init__(
                     stacklevel = 2
                 warnings.warn(
                     f"Your version of xlrd is {xlrd_version}. In xlrd >= 2.0, "
-                    f"only the xls format is supported. As a result, the "
-                    f"openpyxl engine will be used if it is installed and the "
-                    f"engine argument is not specified. Install "
+                    f"only the xls format is supported. Install "
                     f"openpyxl instead.",
                     FutureWarning,
                     stacklevel=stacklevel,

pandas/io/excel/_util.py

@@ -68,13 +68,6 @@ def get_default_engine(ext, mode="reader"):
             _default_writers["xlsx"] = "xlsxwriter"
         return _default_writers[ext]
     else:
-        if (
-            import_optional_dependency("openpyxl", errors="ignore") is None
-            and import_optional_dependency("xlrd", errors="ignore") is not None
-        ):
-            # if no openpyxl but xlrd installed, return xlrd
-            # the version is handled elsewhere
-            _default_readers["xlsx"] = "xlrd"
         return _default_readers[ext]
 
 

pandas/tests/io/excel/test_readers.py

@@ -125,6 +125,30 @@ def cd_and_set_engine(self, engine, datapath, monkeypatch):
         monkeypatch.chdir(datapath("io", "data", "excel"))
         monkeypatch.setattr(pd, "read_excel", func)
 
+    def test_engine_used(self, read_ext, engine, monkeypatch):
+        # GH 38884
+        def parser(self, *args, **kwargs):
+            return self.engine
+
+        monkeypatch.setattr(pd.ExcelFile, "parse", parser)
+
+        expected_defaults = {
+            "xlsx": "openpyxl",
+            "xlsm": "openpyxl",
+            "xlsb": "pyxlsb",
+            "xls": "xlrd",
+            "ods": "odf",
+        }
+
+        with open("test1" + read_ext, "rb") as f:
+            result = pd.read_excel(f)
+
+        if engine is not None:
+            expected = engine
+        else:
+            expected = expected_defaults[read_ext[1:]]
+        assert result == expected
+
     def test_usecols_int(self, read_ext, df_ref):
         df_ref = df_ref.reindex(columns=["A", "B", "C"])
 
@@ -1172,6 +1196,24 @@ def cd_and_set_engine(self, engine, datapath, monkeypatch):
         monkeypatch.chdir(datapath("io", "data", "excel"))
         monkeypatch.setattr(pd, "ExcelFile", func)
 
+    def test_engine_used(self, read_ext, engine, monkeypatch):
+        expected_defaults = {
+            "xlsx": "openpyxl",
+            "xlsm": "openpyxl",
+            "xlsb": "pyxlsb",
+            "xls": "xlrd",
+            "ods": "odf",
+        }
+
+        with pd.ExcelFile("test1" + read_ext) as excel:
+            result = excel.engine
+
+        if engine is not None:
+            expected = engine
+        else:
+            expected = expected_defaults[read_ext[1:]]
+        assert result == expected
+
     def test_excel_passes_na(self, read_ext):
         with pd.ExcelFile("test4" + read_ext) as excel:
             parsed = pd.read_excel(