Made read_html ignore empty tables, added test

Author: mdmueller

pandas/io/html.py

@@ -711,9 +711,14 @@ def _parse(flavor, io, match, header, index_col, skiprows, infer_types,
     else:
         raise_with_traceback(retained)
 
-    return [_data_to_frame(table, header, index_col, skiprows, infer_types,
-                           parse_dates, tupleize_cols, thousands)
-            for table in tables]
+    ret = []
+    for table in tables:
+        try:
+            ret.append(_data_to_frame(table, header, index_col, skiprows,
+                        infer_types, parse_dates, tupleize_cols, thousands))
+        except StopIteration: # empty table
+            continue
+    return ret
 
 
 def read_html(io, match='.+', flavor=None, header=None, index_col=None,

pandas/io/tests/test_html.py

@@ -401,6 +401,36 @@ def test_thousands_macau_index_col(self):
 
         self.assertFalse(any(s.isnull().any() for _, s in df.iteritems()))
 
+    def test_empty_tables(self):
+        """
+        Make sure that read_html ignores empty tables.
+        """
+        data1 = '''<table>
+            <thead>
+                <tr>
+                    <th>A</th>
+                    <th>B</th>
+                </tr>
+            </thead>
+            <tbody>
+                <tr>
+                    <td>1</td>
+                    <td>2</td>
+                </tr>
+            </tbody>
+        </table>'''
+        data2 = data1 + '''<table>
+            <tbody>
+                <tr>
+                    <td></td>
+                    <td></td>
+                </tr>
+            </tbody>
+        </table>'''
+        res1 = self.read_html(StringIO(data1))
+        res2 = self.read_html(StringIO(data2))
+        assert_framelist_equal(res1, res2)
+
     def test_countries_municipalities(self):
         # GH5048
         data1 = StringIO('''<table>