def test_multiple_header_rows(self):
# Issue #13434
expected_df = DataFrame(data=[("Hillary", 68,
"D"), ("Bernie", 74,
"D"), ("Donald", 69, "R")])
expected_df.columns = [["Unnamed: 0_level_0", "Age", "Party"],
[
"Name", "Unnamed: 1_level_1",
"Unnamed: 2_level_1"
]]
html = expected_df.to_html(index=False)
html_df = read_html(html, )[0]
tm.assert_frame_equal(expected_df, html_df)
def test_keep_default_na(self):
html_data = """<table>
<thead>
<th>a</th>
</tr>
</thead>
<tbody>
<tr>
<td> N/A</td>
</tr>
<tr>
<td> NA</td>
</tr>
</tbody>
</table>"""
expected_df = DataFrame({'a': ['N/A', 'NA']})
html_df = read_html(html_data, keep_default_na=False)[0]
tm.assert_frame_equal(expected_df, html_df)
expected_df = DataFrame({'a': [np.nan, np.nan]})
html_df = read_html(html_data, keep_default_na=True)[0]
tm.assert_frame_equal(expected_df, html_df)
def test_na_values(self):
# GH 13461
html_data = """<table>
<thead>
<th>a</th>
</tr>
</thead>
<tbody>
<tr>
<td> 0.763</td>
</tr>
<tr>
<td> 0.244</td>
</tr>
</tbody>
</table>"""
expected_df = DataFrame({'a': [0.763, np.nan]})
html_df = read_html(html_data, na_values=[0.244])[0]
tm.assert_frame_equal(expected_df, html_df)
def test_converters(self):
# GH 13461
html_data = """<table>
<thead>
<th>a</th>
</tr>
</thead>
<tbody>
<tr>
<td> 0.763</td>
</tr>
<tr>
<td> 0.244</td>
</tr>
</tbody>
</table>"""
expected_df = DataFrame({'a': ['0.763', '0.244']})
html_df = read_html(html_data, converters={'a': str})[0]
tm.assert_frame_equal(expected_df, html_df)
def read_html(self, *args, **kwargs):
kwargs['flavor'] = self.flavor
return read_html(*args, **kwargs)
def read_html(self, *args, **kwargs):
kwargs.setdefault('flavor', self.flavor)
return read_html(*args, **kwargs)
def test_bool_header_arg(self):
# GH 6114
for arg in [True, False]:
with pytest.raises(TypeError):
read_html(self.spam_data, header=arg)
def test_same_ordering():
_skip_if_none_of(['bs4', 'lxml', 'html5lib'])
filename = os.path.join(DATA_PATH, 'valid_markup.html')
dfs_lxml = read_html(filename, index_col=0, flavor=['lxml'])
dfs_bs4 = read_html(filename, index_col=0, flavor=['bs4'])
assert_framelist_equal(dfs_lxml, dfs_bs4)
def test_invalid_flavor():
url = 'google.com'
with pytest.raises(ValueError):
read_html(url, 'google', flavor='not a* valid**++ flavor')