BUG: read_excel forward-filling MI names

doc/source/whatsnew/v1.3.0.rst

@@ -267,6 +267,7 @@ I/O
 - Bug in :func:`to_hdf` raising ``KeyError`` when trying to apply
   for subclasses of ``DataFrame`` or ``Series`` (:issue:`33748`).
 - Bug in :func:`json_normalize` resulting in the first element of a generator object not being included in the returned ``DataFrame`` (:issue:`35923`)
+- Bug in :func:`read_excel` forward filling :class:`MultiIndex` names with multiple header and index columns specified (:issue:`34673`)
 
 
 Period

pandas/io/excel/_base.py

@@ -504,6 +504,8 @@ def parse(
                         header_name, _ = pop_header_name(data[row], index_col)
                         header_names.append(header_name)
 
+            has_index_names = is_list_like(header) and len(header) > 1
+
             if is_list_like(index_col):
                 # Forward fill values for MultiIndex index.
                 if header is None:
@@ -513,6 +515,12 @@ def parse(
                 else:
                     offset = 1 + max(header)
 
+                # GH34673: if MultiIndex names present and not defined in the header,
+                # offset needs to be incremented so that forward filling starts
+                # from the first MI value instead of the name
+                if has_index_names:
+                    offset += 1
+
                 # Check if we have an empty dataset
                 # before trying to collect data.
                 if offset < len(data):
@@ -525,8 +533,6 @@ def parse(
                             else:
                                 last = data[row][col]
 
-            has_index_names = is_list_like(header) and len(header) > 1
-
             # GH 12292 : error when read one empty column from excel file
             try:
                 parser = TextParser(

pandas/tests/io/excel/test_readers.py

@@ -841,6 +841,43 @@ def test_read_excel_multiindex(self, read_ext):
         )
         tm.assert_frame_equal(actual, expected)
 
+    @pytest.mark.parametrize(
+        "sheet_name,idx_lvl2",
+        [
+            ("both_name_blank_after_mi_name", [np.nan, "b", "a", "b"]),
+            ("both_name_multiple_blanks", [np.nan] * 4),
+        ],
+    )
+    def test_read_excel_multiindex_blank_after_name(
+        self, read_ext, sheet_name, idx_lvl2
+    ):
+        # GH34673
+        if pd.read_excel.keywords["engine"] == "pyxlsb":
+            pytest.xfail("Sheets containing datetimes not supported by pyxlsb (GH4679")
+
+        mi_file = "testmultiindex" + read_ext
+        mi = MultiIndex.from_product([["foo", "bar"], ["a", "b"]], names=["c1", "c2"])
+        expected = DataFrame(
+            [
+                [1, 2.5, pd.Timestamp("2015-01-01"), True],
+                [2, 3.5, pd.Timestamp("2015-01-02"), False],
+                [3, 4.5, pd.Timestamp("2015-01-03"), False],
+                [4, 5.5, pd.Timestamp("2015-01-04"), True],
+            ],
+            columns=mi,
+            index=MultiIndex.from_arrays(
+                (["foo", "foo", "bar", "bar"], idx_lvl2),
+                names=["ilvl1", "ilvl2"],
+            ),
+        )
+        result = pd.read_excel(
+            mi_file,
+            sheet_name=sheet_name,
+            index_col=[0, 1],
+            header=[0, 1],
+        )
+        tm.assert_frame_equal(result, expected)
+
     def test_read_excel_multiindex_header_only(self, read_ext):
         # see gh-11733.
         #