/usr/lib/python3/dist-packages/pandas/io/tests/test_html.py is in python3-pandas 0.13.1-2ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 | from __future__ import print_function
import os
import re
import warnings
try:
from importlib import import_module
except ImportError:
import_module = __import__
from distutils.version import LooseVersion
import nose
import numpy as np
from numpy.random import rand
from numpy.testing.decorators import slow
from pandas import (DataFrame, MultiIndex, read_csv, Timestamp, Index,
date_range, Series)
from pandas.compat import map, zip, StringIO, string_types
from pandas.io.common import URLError, urlopen, file_path_to_url
from pandas.io.html import read_html
import pandas.util.testing as tm
from pandas.util.testing import makeCustomDataframe as mkdf, network
def _have_module(module_name):
try:
import_module(module_name)
return True
except ImportError:
return False
def _skip_if_no(module_name):
if not _have_module(module_name):
raise nose.SkipTest("{0!r} not found".format(module_name))
def _skip_if_none_of(module_names):
if isinstance(module_names, string_types):
_skip_if_no(module_names)
if module_names == 'bs4':
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
raise nose.SkipTest("Bad version of bs4: 4.2.0")
else:
not_found = [module_name for module_name in module_names if not
_have_module(module_name)]
if set(not_found) & set(module_names):
raise nose.SkipTest("{0!r} not found".format(not_found))
if 'bs4' in module_names:
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
raise nose.SkipTest("Bad version of bs4: 4.2.0")
DATA_PATH = tm.get_data_path()
def assert_framelist_equal(list1, list2, *args, **kwargs):
assert len(list1) == len(list2), ('lists are not of equal size '
'len(list1) == {0}, '
'len(list2) == {1}'.format(len(list1),
len(list2)))
msg = 'not all list elements are DataFrames'
both_frames = all(map(lambda x, y: isinstance(x, DataFrame) and
isinstance(y, DataFrame), list1, list2))
assert both_frames, msg
for frame_i, frame_j in zip(list1, list2):
tm.assert_frame_equal(frame_i, frame_j, *args, **kwargs)
assert not frame_i.empty, 'frames are both empty'
def test_bs4_version_fails():
_skip_if_none_of(('bs4', 'html5lib'))
import bs4
if bs4.__version__ == LooseVersion('4.2.0'):
tm.assert_raises(AssertionError, read_html, os.path.join(DATA_PATH,
"spam.html"),
flavor='bs4')
class TestReadHtml(tm.TestCase):
@classmethod
def setUpClass(cls):
super(TestReadHtml, cls).setUpClass()
_skip_if_none_of(('bs4', 'html5lib'))
def read_html(self, *args, **kwargs):
kwargs['flavor'] = kwargs.get('flavor', self.flavor)
return read_html(*args, **kwargs)
def setup_data(self):
self.spam_data = os.path.join(DATA_PATH, 'spam.html')
self.banklist_data = os.path.join(DATA_PATH, 'banklist.html')
def setup_flavor(self):
self.flavor = 'bs4'
def setUp(self):
self.setup_data()
self.setup_flavor()
def test_to_html_compat(self):
df = mkdf(4, 3, data_gen_f=lambda *args: rand(), c_idx_names=False,
r_idx_names=False).applymap('{0:.3f}'.format).astype(float)
out = df.to_html()
res = self.read_html(out, attrs={'class': 'dataframe'},
index_col=0)[0]
tm.assert_frame_equal(res, df)
@network
def test_banklist_url(self):
url = 'http://www.fdic.gov/bank/individual/failed/banklist.html'
df1 = self.read_html(url, 'First Federal Bank of Florida',
attrs={"id": 'table'})
df2 = self.read_html(url, 'Metcalf Bank', attrs={'id': 'table'})
assert_framelist_equal(df1, df2)
@network
def test_spam_url(self):
url = ('http://ndb.nal.usda.gov/ndb/foods/show/1732?fg=&man=&'
'lfacet=&format=&count=&max=25&offset=&sort=&qlookup=spam')
df1 = self.read_html(url, '.*Water.*')
df2 = self.read_html(url, 'Unit')
assert_framelist_equal(df1, df2)
@slow
def test_banklist(self):
df1 = self.read_html(self.banklist_data, '.*Florida.*',
attrs={'id': 'table'})
df2 = self.read_html(self.banklist_data, 'Metcalf Bank',
attrs={'id': 'table'})
assert_framelist_equal(df1, df2)
def test_spam_no_types(self):
with tm.assert_produces_warning(FutureWarning):
df1 = self.read_html(self.spam_data, '.*Water.*',
infer_types=False)
with tm.assert_produces_warning(FutureWarning):
df2 = self.read_html(self.spam_data, 'Unit', infer_types=False)
assert_framelist_equal(df1, df2)
self.assertEqual(df1[0].ix[0, 0], 'Proximates')
self.assertEqual(df1[0].columns[0], 'Nutrient')
def test_spam_with_types(self):
df1 = self.read_html(self.spam_data, '.*Water.*')
df2 = self.read_html(self.spam_data, 'Unit')
assert_framelist_equal(df1, df2)
self.assertEqual(df1[0].ix[0, 0], 'Proximates')
self.assertEqual(df1[0].columns[0], 'Nutrient')
def test_spam_no_match(self):
dfs = self.read_html(self.spam_data)
for df in dfs:
tm.assert_isinstance(df, DataFrame)
def test_banklist_no_match(self):
dfs = self.read_html(self.banklist_data, attrs={'id': 'table'})
for df in dfs:
tm.assert_isinstance(df, DataFrame)
def test_spam_header(self):
df = self.read_html(self.spam_data, '.*Water.*', header=1)[0]
self.assertEqual(df.columns[0], 'Proximates')
self.assertFalse(df.empty)
def test_skiprows_int(self):
df1 = self.read_html(self.spam_data, '.*Water.*', skiprows=1)
df2 = self.read_html(self.spam_data, 'Unit', skiprows=1)
assert_framelist_equal(df1, df2)
def test_skiprows_xrange(self):
df1 = self.read_html(self.spam_data, '.*Water.*',
skiprows=range(2))[0]
df2 = self.read_html(self.spam_data, 'Unit', skiprows=range(2))[0]
tm.assert_frame_equal(df1, df2)
def test_skiprows_list(self):
df1 = self.read_html(self.spam_data, '.*Water.*', skiprows=[1, 2])
df2 = self.read_html(self.spam_data, 'Unit', skiprows=[2, 1])
assert_framelist_equal(df1, df2)
def test_skiprows_set(self):
df1 = self.read_html(self.spam_data, '.*Water.*',
skiprows=set([1, 2]))
df2 = self.read_html(self.spam_data, 'Unit', skiprows=set([2, 1]))
assert_framelist_equal(df1, df2)
def test_skiprows_slice(self):
df1 = self.read_html(self.spam_data, '.*Water.*', skiprows=1)
df2 = self.read_html(self.spam_data, 'Unit', skiprows=1)
assert_framelist_equal(df1, df2)
def test_skiprows_slice_short(self):
df1 = self.read_html(self.spam_data, '.*Water.*',
skiprows=slice(2))
df2 = self.read_html(self.spam_data, 'Unit', skiprows=slice(2))
assert_framelist_equal(df1, df2)
def test_skiprows_slice_long(self):
df1 = self.read_html(self.spam_data, '.*Water.*',
skiprows=slice(2, 5))
df2 = self.read_html(self.spam_data, 'Unit',
skiprows=slice(4, 1, -1))
assert_framelist_equal(df1, df2)
def test_skiprows_ndarray(self):
df1 = self.read_html(self.spam_data, '.*Water.*',
skiprows=np.arange(2))
df2 = self.read_html(self.spam_data, 'Unit', skiprows=np.arange(2))
assert_framelist_equal(df1, df2)
def test_skiprows_invalid(self):
with tm.assertRaisesRegexp(TypeError,
'is not a valid type for skipping rows'):
self.read_html(self.spam_data, '.*Water.*', skiprows='asdf')
def test_index(self):
df1 = self.read_html(self.spam_data, '.*Water.*', index_col=0)
df2 = self.read_html(self.spam_data, 'Unit', index_col=0)
assert_framelist_equal(df1, df2)
def test_header_and_index_no_types(self):
with tm.assert_produces_warning(FutureWarning):
df1 = self.read_html(self.spam_data, '.*Water.*', header=1,
index_col=0, infer_types=False)
with tm.assert_produces_warning(FutureWarning):
df2 = self.read_html(self.spam_data, 'Unit', header=1,
index_col=0, infer_types=False)
assert_framelist_equal(df1, df2)
def test_header_and_index_with_types(self):
df1 = self.read_html(self.spam_data, '.*Water.*', header=1,
index_col=0)
df2 = self.read_html(self.spam_data, 'Unit', header=1, index_col=0)
assert_framelist_equal(df1, df2)
def test_infer_types(self):
with tm.assert_produces_warning(FutureWarning):
df1 = self.read_html(self.spam_data, '.*Water.*', index_col=0,
infer_types=False)
with tm.assert_produces_warning(FutureWarning):
df2 = self.read_html(self.spam_data, 'Unit', index_col=0,
infer_types=False)
assert_framelist_equal(df1, df2)
with tm.assert_produces_warning(FutureWarning):
df2 = self.read_html(self.spam_data, 'Unit', index_col=0,
infer_types=True)
with tm.assertRaises(AssertionError):
assert_framelist_equal(df1, df2)
def test_string_io(self):
with open(self.spam_data) as f:
data1 = StringIO(f.read())
with open(self.spam_data) as f:
data2 = StringIO(f.read())
df1 = self.read_html(data1, '.*Water.*')
df2 = self.read_html(data2, 'Unit')
assert_framelist_equal(df1, df2)
def test_string(self):
with open(self.spam_data) as f:
data = f.read()
df1 = self.read_html(data, '.*Water.*')
df2 = self.read_html(data, 'Unit')
assert_framelist_equal(df1, df2)
def test_file_like(self):
with open(self.spam_data) as f:
df1 = self.read_html(f, '.*Water.*')
with open(self.spam_data) as f:
df2 = self.read_html(f, 'Unit')
assert_framelist_equal(df1, df2)
@network
def test_bad_url_protocol(self):
with tm.assertRaises(URLError):
self.read_html('git://github.com', match='.*Water.*')
@network
def test_invalid_url(self):
with tm.assertRaises(URLError):
self.read_html('http://www.a23950sdfa908sd.com', match='.*Water.*')
@slow
def test_file_url(self):
url = self.banklist_data
dfs = self.read_html(file_path_to_url(url), 'First', attrs={'id': 'table'})
tm.assert_isinstance(dfs, list)
for df in dfs:
tm.assert_isinstance(df, DataFrame)
@slow
def test_invalid_table_attrs(self):
url = self.banklist_data
with tm.assertRaisesRegexp(ValueError, 'No tables found'):
self.read_html(url, 'First Federal Bank of Florida',
attrs={'id': 'tasdfable'})
def _bank_data(self, *args, **kwargs):
return self.read_html(self.banklist_data, 'Metcalf',
attrs={'id': 'table'}, *args, **kwargs)
@slow
def test_multiindex_header(self):
df = self._bank_data(header=[0, 1])[0]
tm.assert_isinstance(df.columns, MultiIndex)
@slow
def test_multiindex_index(self):
df = self._bank_data(index_col=[0, 1])[0]
tm.assert_isinstance(df.index, MultiIndex)
@slow
def test_multiindex_header_index(self):
df = self._bank_data(header=[0, 1], index_col=[0, 1])[0]
tm.assert_isinstance(df.columns, MultiIndex)
tm.assert_isinstance(df.index, MultiIndex)
@slow
def test_multiindex_header_skiprows_tuples(self):
df = self._bank_data(header=[0, 1], skiprows=1, tupleize_cols=True)[0]
tm.assert_isinstance(df.columns, Index)
@slow
def test_multiindex_header_skiprows(self):
df = self._bank_data(header=[0, 1], skiprows=1)[0]
tm.assert_isinstance(df.columns, MultiIndex)
@slow
def test_multiindex_header_index_skiprows(self):
df = self._bank_data(header=[0, 1], index_col=[0, 1], skiprows=1)[0]
tm.assert_isinstance(df.index, MultiIndex)
tm.assert_isinstance(df.columns, MultiIndex)
@slow
def test_regex_idempotency(self):
url = self.banklist_data
dfs = self.read_html(file_path_to_url(url),
match=re.compile(re.compile('Florida')),
attrs={'id': 'table'})
tm.assert_isinstance(dfs, list)
for df in dfs:
tm.assert_isinstance(df, DataFrame)
def test_negative_skiprows(self):
with tm.assertRaisesRegexp(ValueError,
'\(you passed a negative value\)'):
self.read_html(self.spam_data, 'Water', skiprows=-1)
@network
def test_multiple_matches(self):
url = 'http://code.google.com/p/pythonxy/wiki/StandardPlugins'
dfs = self.read_html(url, match='Python',
attrs={'class': 'wikitable'})
self.assert_(len(dfs) > 1)
@network
def test_pythonxy_plugins_table(self):
url = 'http://code.google.com/p/pythonxy/wiki/StandardPlugins'
dfs = self.read_html(url, match='Python',
attrs={'class': 'wikitable'})
zz = [df.iloc[0, 0] for df in dfs]
self.assertEqual(sorted(zz), sorted(['Python', 'SciTE']))
@slow
def test_thousands_macau_stats(self):
all_non_nan_table_index = -2
macau_data = os.path.join(DATA_PATH, 'macau.html')
dfs = self.read_html(macau_data, index_col=0,
attrs={'class': 'style1'})
df = dfs[all_non_nan_table_index]
self.assertFalse(any(s.isnull().any() for _, s in df.iteritems()))
@slow
def test_thousands_macau_index_col(self):
all_non_nan_table_index = -2
macau_data = os.path.join(DATA_PATH, 'macau.html')
dfs = self.read_html(macau_data, index_col=0, header=0)
df = dfs[all_non_nan_table_index]
self.assertFalse(any(s.isnull().any() for _, s in df.iteritems()))
def test_countries_municipalities(self):
# GH5048
data1 = StringIO('''<table>
<thead>
<tr>
<th>Country</th>
<th>Municipality</th>
<th>Year</th>
</tr>
</thead>
<tbody>
<tr>
<td>Ukraine</td>
<th>Odessa</th>
<td>1944</td>
</tr>
</tbody>
</table>''')
data2 = StringIO('''
<table>
<tbody>
<tr>
<th>Country</th>
<th>Municipality</th>
<th>Year</th>
</tr>
<tr>
<td>Ukraine</td>
<th>Odessa</th>
<td>1944</td>
</tr>
</tbody>
</table>''')
res1 = self.read_html(data1)
res2 = self.read_html(data2, header=0)
assert_framelist_equal(res1, res2)
def test_nyse_wsj_commas_table(self):
data = os.path.join(DATA_PATH, 'nyse_wsj.html')
df = self.read_html(data, index_col=0, header=0,
attrs={'class': 'mdcTable'})[0]
columns = Index(['Issue(Roll over for charts and headlines)',
'Volume', 'Price', 'Chg', '% Chg'])
nrows = 100
self.assertEqual(df.shape[0], nrows)
self.assertTrue(df.columns.equals(columns))
@slow
def test_banklist_header(self):
from pandas.io.html import _remove_whitespace
def try_remove_ws(x):
try:
return _remove_whitespace(x)
except AttributeError:
return x
df = self.read_html(self.banklist_data, 'Metcalf',
attrs={'id': 'table'})[0]
ground_truth = read_csv(os.path.join(DATA_PATH, 'banklist.csv'),
converters={'Updated Date': Timestamp,
'Closing Date': Timestamp})
self.assertEqual(df.shape, ground_truth.shape)
old = ['First Vietnamese American BankIn Vietnamese',
'Westernbank Puerto RicoEn Espanol',
'R-G Premier Bank of Puerto RicoEn Espanol',
'EurobankEn Espanol', 'Sanderson State BankEn Espanol',
'Washington Mutual Bank(Including its subsidiary Washington '
'Mutual Bank FSB)',
'Silver State BankEn Espanol',
'AmTrade International BankEn Espanol',
'Hamilton Bank, NAEn Espanol',
'The Citizens Savings BankPioneer Community Bank, Inc.']
new = ['First Vietnamese American Bank', 'Westernbank Puerto Rico',
'R-G Premier Bank of Puerto Rico', 'Eurobank',
'Sanderson State Bank', 'Washington Mutual Bank',
'Silver State Bank', 'AmTrade International Bank',
'Hamilton Bank, NA', 'The Citizens Savings Bank']
dfnew = df.applymap(try_remove_ws).replace(old, new)
gtnew = ground_truth.applymap(try_remove_ws)
converted = dfnew.convert_objects(convert_numeric=True)
tm.assert_frame_equal(converted.convert_objects(convert_dates='coerce'),
gtnew)
@slow
def test_gold_canyon(self):
gc = 'Gold Canyon'
with open(self.banklist_data, 'r') as f:
raw_text = f.read()
self.assert_(gc in raw_text)
df = self.read_html(self.banklist_data, 'Gold Canyon',
attrs={'id': 'table'})[0]
self.assert_(gc in df.to_string())
def test_different_number_of_rows(self):
expected = """<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>C_l0_g0</th>
<th>C_l0_g1</th>
<th>C_l0_g2</th>
<th>C_l0_g3</th>
<th>C_l0_g4</th>
</tr>
</thead>
<tbody>
<tr>
<th>R_l0_g0</th>
<td> 0.763</td>
<td> 0.233</td>
<td> nan</td>
<td> nan</td>
<td> nan</td>
</tr>
<tr>
<th>R_l0_g1</th>
<td> 0.244</td>
<td> 0.285</td>
<td> 0.392</td>
<td> 0.137</td>
<td> 0.222</td>
</tr>
</tbody>
</table>"""
out = """<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>C_l0_g0</th>
<th>C_l0_g1</th>
<th>C_l0_g2</th>
<th>C_l0_g3</th>
<th>C_l0_g4</th>
</tr>
</thead>
<tbody>
<tr>
<th>R_l0_g0</th>
<td> 0.763</td>
<td> 0.233</td>
</tr>
<tr>
<th>R_l0_g1</th>
<td> 0.244</td>
<td> 0.285</td>
<td> 0.392</td>
<td> 0.137</td>
<td> 0.222</td>
</tr>
</tbody>
</table>"""
expected = self.read_html(expected, index_col=0)[0]
res = self.read_html(out, index_col=0)[0]
tm.assert_frame_equal(expected, res)
def test_parse_dates_list(self):
df = DataFrame({'date': date_range('1/1/2001', periods=10)})
expected = df.to_html()
res = self.read_html(expected, parse_dates=[0], index_col=0)
tm.assert_frame_equal(df, res[0])
def test_parse_dates_combine(self):
raw_dates = Series(date_range('1/1/2001', periods=10))
df = DataFrame({'date': raw_dates.map(lambda x: str(x.date())),
'time': raw_dates.map(lambda x: str(x.time()))})
res = self.read_html(df.to_html(), parse_dates={'datetime': [1, 2]},
index_col=1)
newdf = DataFrame({'datetime': raw_dates})
tm.assert_frame_equal(newdf, res[0])
class TestReadHtmlLxml(tm.TestCase):
@classmethod
def setUpClass(cls):
super(TestReadHtmlLxml, cls).setUpClass()
_skip_if_no('lxml')
def read_html(self, *args, **kwargs):
self.flavor = ['lxml']
kwargs['flavor'] = kwargs.get('flavor', self.flavor)
return read_html(*args, **kwargs)
def test_data_fail(self):
from lxml.etree import XMLSyntaxError
spam_data = os.path.join(DATA_PATH, 'spam.html')
banklist_data = os.path.join(DATA_PATH, 'banklist.html')
with tm.assertRaises(XMLSyntaxError):
self.read_html(spam_data, flavor=['lxml'])
with tm.assertRaises(XMLSyntaxError):
self.read_html(banklist_data, flavor=['lxml'])
def test_works_on_valid_markup(self):
filename = os.path.join(DATA_PATH, 'valid_markup.html')
dfs = self.read_html(filename, index_col=0, flavor=['lxml'])
tm.assert_isinstance(dfs, list)
tm.assert_isinstance(dfs[0], DataFrame)
@slow
def test_fallback_success(self):
_skip_if_none_of(('bs4', 'html5lib'))
banklist_data = os.path.join(DATA_PATH, 'banklist.html')
self.read_html(banklist_data, '.*Water.*', flavor=['lxml', 'html5lib'])
def test_parse_dates_list(self):
df = DataFrame({'date': date_range('1/1/2001', periods=10)})
expected = df.to_html()
res = self.read_html(expected, parse_dates=[0], index_col=0)
tm.assert_frame_equal(df, res[0])
def test_parse_dates_combine(self):
raw_dates = Series(date_range('1/1/2001', periods=10))
df = DataFrame({'date': raw_dates.map(lambda x: str(x.date())),
'time': raw_dates.map(lambda x: str(x.time()))})
res = self.read_html(df.to_html(), parse_dates={'datetime': [1, 2]},
index_col=1)
newdf = DataFrame({'datetime': raw_dates})
tm.assert_frame_equal(newdf, res[0])
def test_invalid_flavor():
url = 'google.com'
nose.tools.assert_raises(ValueError, read_html, url, 'google',
flavor='not a* valid**++ flaver')
def get_elements_from_file(url, element='table'):
_skip_if_none_of(('bs4', 'html5lib'))
url = file_path_to_url(url)
from bs4 import BeautifulSoup
with urlopen(url) as f:
soup = BeautifulSoup(f, features='html5lib')
return soup.find_all(element)
@slow
def test_bs4_finds_tables():
filepath = os.path.join(DATA_PATH, "spam.html")
with warnings.catch_warnings():
warnings.filterwarnings('ignore')
assert get_elements_from_file(filepath, 'table')
def get_lxml_elements(url, element):
_skip_if_no('lxml')
from lxml.html import parse
doc = parse(url)
return doc.xpath('.//{0}'.format(element))
@slow
def test_lxml_finds_tables():
filepath = os.path.join(DATA_PATH, "spam.html")
assert get_lxml_elements(filepath, 'table')
@slow
def test_lxml_finds_tbody():
filepath = os.path.join(DATA_PATH, "spam.html")
assert get_lxml_elements(filepath, 'tbody')
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)
|