Fix ci

Author: ritwizsinha

doc/source/whatsnew/v3.0.0.rst

@@ -557,6 +557,7 @@ I/O
 - Bug in :meth:`HDFStore.get` was failing to save data of dtype datetime64[s] correctly (:issue:`59004`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
+- Bug in :meth:`read_html` would return an incorrect result when parsing a table with a space character in a ``<td>`` tag. (:issue:`12345`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
 
 Period

pandas/io/html.py

@@ -1149,7 +1149,8 @@ def read_html(
     {storage_options}
 
         .. versionadded:: 2.1.0
-    
+
+
     skip_blank_lines: bool, default True
         Whether lines containing only spaces should be skipped or not.
 
@@ -1228,5 +1229,5 @@ def read_html(
         extract_links=extract_links,
         dtype_backend=dtype_backend,
         storage_options=storage_options,
-        skip_blank_lines=skip_blank_lines
+        skip_blank_lines=skip_blank_lines,
     )

pandas/tests/io/test_html.py

@@ -1242,6 +1242,32 @@ def test_preserve_empty_rows(self, flavor_read_html):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_preserve_rows_with_spaces(self, flavor_read_html):
+        result = flavor_read_html(
+            StringIO(
+                """
+            <table>
+                <tr>
+                    <th>A</th>
+                    <th>B</th>
+                </tr>
+                <tr>
+                    <td>a</td>
+                    <td>b</td>
+                </tr>
+                <tr>
+                    <td>  </td>
+                    <td> </td>
+                </tr>
+            </table>
+        """
+            ),
+            skip_blank_lines=False,
+        )[0]
+        expected = DataFrame(data=[["a", "b"], ["  ", " "]], columns=["A", "B"])
+
+        tm.assert_frame_equal(result, expected)
+
     def test_ignore_empty_rows_when_inferring_header(self, flavor_read_html):
         result = flavor_read_html(
             StringIO(