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
|
# -*- coding: utf-8 -*-
"""
HTML parser test cases for etree
"""
import unittest
import tempfile, os, os.path, sys
this_dir = os.path.dirname(__file__)
if this_dir not in sys.path:
sys.path.insert(0, this_dir) # needed for Py3
from common_imports import etree, StringIO, BytesIO, fileInTestDir, _bytes, _str
from common_imports import SillyFileLike, HelperTestCase, write_to_file, next
try:
unicode
except NameError:
unicode = str
class HtmlParserTestCase(HelperTestCase):
"""HTML parser test cases
"""
etree = etree
html_str = _bytes("<html><head><title>test</title></head><body><h1>page title</h1></body></html>")
html_str_pretty = _bytes("""\
<html>
<head><title>test</title></head>
<body><h1>page title</h1></body>
</html>
""")
broken_html_str = _bytes("<html><head><title>test"
"<body><h1>page title</h3></p></html>")
uhtml_str = _bytes(
"<html><head><title>test á</title></head>"
"<body><h1>page á title</h1></body></html>").decode('utf8')
def tearDown(self):
super(HtmlParserTestCase, self).tearDown()
self.etree.set_default_parser()
def test_module_HTML(self):
element = self.etree.HTML(self.html_str)
self.assertEqual(self.etree.tostring(element, method="html"),
self.html_str)
def test_module_HTML_unicode(self):
element = self.etree.HTML(self.uhtml_str)
self.assertEqual(
self.etree.tostring(element, method="html", encoding='unicode'),
self.uhtml_str)
self.assertEqual(element.findtext('.//h1'),
_bytes("page á title").decode('utf8'))
def test_wide_unicode_xml(self):
if sys.maxunicode < 1114111:
return # skip test
element = self.etree.HTML(_bytes(
'<html><body><p>\\U00026007</p></body></html>'
).decode('unicode_escape'))
p_text = element.findtext('.//p')
self.assertEqual(1, len(p_text))
self.assertEqual(_bytes('\\U00026007').decode('unicode_escape'),
p_text)
def test_module_HTML_pretty_print(self):
element = self.etree.HTML(self.html_str)
self.assertEqual(self.etree.tostring(element, method="html", pretty_print=True),
self.html_str_pretty)
def test_module_parse_html_error(self):
parser = self.etree.HTMLParser(recover=False)
parse = self.etree.parse
f = BytesIO("<html></body>")
self.assertRaises(self.etree.XMLSyntaxError,
parse, f, parser)
def test_html_element_name_empty(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
el = Element('name')
self.assertRaises(ValueError, Element, '{}')
self.assertRaises(ValueError, setattr, el, 'tag', '{}')
self.assertRaises(ValueError, Element, '{test}')
self.assertRaises(ValueError, setattr, el, 'tag', '{test}')
def test_html_element_name_colon(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
pname = Element('p:name')
self.assertEqual(pname.tag, 'p:name')
pname = Element('{test}p:name')
self.assertEqual(pname.tag, '{test}p:name')
pname = Element('name')
pname.tag = 'p:name'
self.assertEqual(pname.tag, 'p:name')
def test_html_element_name_quote(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
self.assertRaises(ValueError, Element, 'p"name')
self.assertRaises(ValueError, Element, "na'me")
self.assertRaises(ValueError, Element, '{test}"name')
self.assertRaises(ValueError, Element, "{test}name'")
el = Element('name')
self.assertRaises(ValueError, setattr, el, 'tag', "pname'")
self.assertRaises(ValueError, setattr, el, 'tag', '"pname')
self.assertEqual(el.tag, "name")
def test_html_element_name_space(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
self.assertRaises(ValueError, Element, ' name ')
self.assertRaises(ValueError, Element, 'na me')
self.assertRaises(ValueError, Element, '{test} name')
el = Element('name')
self.assertRaises(ValueError, setattr, el, 'tag', ' name ')
self.assertEqual(el.tag, "name")
def test_html_subelement_name_empty(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
SubElement = self.etree.SubElement
el = Element('name')
self.assertRaises(ValueError, SubElement, el, '{}')
self.assertRaises(ValueError, SubElement, el, '{test}')
def test_html_subelement_name_colon(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
SubElement = self.etree.SubElement
el = Element('name')
pname = SubElement(el, 'p:name')
self.assertEqual(pname.tag, 'p:name')
pname = SubElement(el, '{test}p:name')
self.assertEqual(pname.tag, '{test}p:name')
def test_html_subelement_name_quote(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
SubElement = self.etree.SubElement
el = Element('name')
self.assertRaises(ValueError, SubElement, el, "name'")
self.assertRaises(ValueError, SubElement, el, 'na"me')
self.assertRaises(ValueError, SubElement, el, "{test}na'me")
self.assertRaises(ValueError, SubElement, el, '{test}"name')
def test_html_subelement_name_space(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
SubElement = self.etree.SubElement
el = Element('name')
self.assertRaises(ValueError, SubElement, el, ' name ')
self.assertRaises(ValueError, SubElement, el, 'na me')
self.assertRaises(ValueError, SubElement, el, '{test} name')
def test_module_parse_html_norecover(self):
parser = self.etree.HTMLParser(recover=False)
parse = self.etree.parse
f = BytesIO(self.broken_html_str)
self.assertRaises(self.etree.XMLSyntaxError,
parse, f, parser)
def test_parse_encoding_8bit_explicit(self):
text = _str('Søk på nettet')
html_latin1 = (_str('<p>%s</p>') % text).encode('iso-8859-1')
tree = self.etree.parse(
BytesIO(html_latin1),
self.etree.HTMLParser(encoding="iso-8859-1"))
p = tree.find("//p")
self.assertEqual(p.text, text)
def test_parse_encoding_8bit_override(self):
text = _str('Søk på nettet')
wrong_head = _str('''
<head>
<meta http-equiv="Content-Type"
content="text/html; charset=UTF-8" />
</head>''')
html_latin1 = (_str('<html>%s<body><p>%s</p></body></html>') % (wrong_head,
text)
).encode('iso-8859-1')
self.assertRaises(self.etree.ParseError,
self.etree.parse,
BytesIO(html_latin1))
tree = self.etree.parse(
BytesIO(html_latin1),
self.etree.HTMLParser(encoding="iso-8859-1"))
p = tree.find("//p")
self.assertEqual(p.text, text)
def test_module_HTML_broken(self):
element = self.etree.HTML(self.broken_html_str)
self.assertEqual(self.etree.tostring(element, method="html"),
self.html_str)
def test_module_HTML_cdata(self):
# by default, libxml2 generates CDATA nodes for <script> content
html = _bytes('<html><head><style>foo</style></head></html>')
element = self.etree.HTML(html)
self.assertEqual(element[0][0].text, "foo")
def test_module_HTML_access(self):
element = self.etree.HTML(self.html_str)
self.assertEqual(element[0][0].tag, 'title')
def test_module_parse_html(self):
parser = self.etree.HTMLParser()
filename = tempfile.mktemp(suffix=".html")
write_to_file(filename, self.html_str, 'wb')
try:
f = open(filename, 'rb')
tree = self.etree.parse(f, parser)
f.close()
self.assertEqual(self.etree.tostring(tree.getroot(), method="html"),
self.html_str)
finally:
os.remove(filename)
def test_module_parse_html_filelike(self):
parser = self.etree.HTMLParser()
f = SillyFileLike(self.html_str)
tree = self.etree.parse(f, parser)
html = self.etree.tostring(tree.getroot(),
method="html", encoding='UTF-8')
self.assertEqual(html, self.html_str)
## def test_module_parse_html_filelike_unicode(self):
## parser = self.etree.HTMLParser()
## f = SillyFileLike(self.uhtml_str)
## tree = self.etree.parse(f, parser)
## html = self.etree.tostring(tree.getroot(), encoding='UTF-8')
## self.assertEqual(unicode(html, 'UTF-8'), self.uhtml_str)
def test_html_file_error(self):
parser = self.etree.HTMLParser()
parse = self.etree.parse
self.assertRaises(IOError,
parse, "__some_hopefully_nonexisting_file__.html",
parser)
def test_default_parser_HTML_broken(self):
self.assertRaises(self.etree.XMLSyntaxError,
self.etree.parse, BytesIO(self.broken_html_str))
self.etree.set_default_parser( self.etree.HTMLParser() )
tree = self.etree.parse(BytesIO(self.broken_html_str))
self.assertEqual(self.etree.tostring(tree.getroot(), method="html"),
self.html_str)
self.etree.set_default_parser()
self.assertRaises(self.etree.XMLSyntaxError,
self.etree.parse, BytesIO(self.broken_html_str))
def test_html_iterparse(self):
iterparse = self.etree.iterparse
f = BytesIO(
'<html><head><title>TITLE</title><body><p>P</p></body></html>')
iterator = iterparse(f, html=True)
self.assertEqual(None, iterator.root)
events = list(iterator)
root = iterator.root
self.assertTrue(root is not None)
self.assertEqual(
[('end', root[0][0]), ('end', root[0]), ('end', root[1][0]),
('end', root[1]), ('end', root)],
events)
def test_html_iterparse_stop_short(self):
iterparse = self.etree.iterparse
f = BytesIO(
'<html><head><title>TITLE</title><body><p>P</p></body></html>')
iterator = iterparse(f, html=True)
self.assertEqual(None, iterator.root)
event, element = next(iterator)
self.assertEqual('end', event)
self.assertEqual('title', element.tag)
self.assertEqual(None, iterator.root)
del element
event, element = next(iterator)
self.assertEqual('end', event)
self.assertEqual('head', element.tag)
self.assertEqual(None, iterator.root)
del element
del iterator
def test_html_iterparse_broken(self):
iterparse = self.etree.iterparse
f = BytesIO('<head><title>TEST></head><p>P<br></div>')
iterator = iterparse(f, html=True)
self.assertEqual(None, iterator.root)
events = list(iterator)
root = iterator.root
self.assertTrue(root is not None)
self.assertEqual('html', root.tag)
self.assertEqual('head', root[0].tag)
self.assertEqual('body', root[1].tag)
self.assertEqual('p', root[1][0].tag)
self.assertEqual('br', root[1][0][0].tag)
self.assertEqual(
[('end', root[0][0]), ('end', root[0]), ('end', root[1][0][0]),
('end', root[1][0]), ('end', root[1]), ('end', root)],
events)
def test_html_iterparse_broken_no_recover(self):
iterparse = self.etree.iterparse
f = BytesIO('<p>P<br></div>')
iterator = iterparse(f, html=True, recover=False)
self.assertRaises(self.etree.XMLSyntaxError, list, iterator)
def test_html_iterparse_file(self):
iterparse = self.etree.iterparse
iterator = iterparse(fileInTestDir("shakespeare.html"),
html=True)
self.assertEqual(None, iterator.root)
events = list(iterator)
root = iterator.root
self.assertTrue(root is not None)
self.assertEqual(249, len(events))
self.assertFalse(
[event for (event, element) in events if event != 'end'])
def test_html_iterparse_start(self):
iterparse = self.etree.iterparse
f = BytesIO(
'<html><head><title>TITLE</title><body><p>P</p></body></html>')
iterator = iterparse(f, html=True, events=('start',))
self.assertEqual(None, iterator.root)
events = list(iterator)
root = iterator.root
self.assertNotEqual(None, root)
self.assertEqual(
[('start', root), ('start', root[0]), ('start', root[0][0]),
('start', root[1]), ('start', root[1][0])],
events)
def test_html_feed_parser(self):
parser = self.etree.HTMLParser()
parser.feed("<html><body></")
parser.feed("body></html>")
root = parser.close()
self.assertEqual('html', root.tag)
# test that we find all names in the parser dict
self.assertEqual([root], list(root.iter('html')))
self.assertEqual([root[0]], list(root.iter('body')))
def test_html_feed_parser_chunky(self):
parser = self.etree.HTMLParser()
parser.feed("<htm")
parser.feed("l><body")
parser.feed("><")
parser.feed("p><")
parser.feed("strong")
parser.feed(">some ")
parser.feed("text</strong></p><")
parser.feed("/body></html>")
root = parser.close()
self.assertEqual('html', root.tag)
# test that we find all names in the parser dict
self.assertEqual([root], list(root.iter('html')))
self.assertEqual([root[0]], list(root.iter('body')))
self.assertEqual([root[0][0]], list(root.iter('p')))
self.assertEqual([root[0][0][0]], list(root.iter('strong')))
def test_html_feed_parser_more_tags(self):
parser = self.etree.HTMLParser()
parser.feed('<html><head>')
parser.feed('<title>TITLE</title><body><p>P</p></body><')
parser.feed("/html>")
root = parser.close()
self.assertEqual('html', root.tag)
# test that we find all names in the parser dict
self.assertEqual([root], list(root.iter('html')))
self.assertEqual([root[0]], list(root.iter('head')))
self.assertEqual([root[0][0]], list(root.iter('title')))
self.assertEqual([root[1]], list(root.iter('body')))
self.assertEqual([root[1][0]], list(root.iter('p')))
def test_html_parser_target_tag(self):
assertFalse = self.assertFalse
events = []
class Target(object):
def start(self, tag, attrib):
events.append(("start", tag))
assertFalse(attrib)
def end(self, tag):
events.append(("end", tag))
def close(self):
return "DONE"
parser = self.etree.HTMLParser(target=Target())
parser.feed("<html><body></body></html>")
done = parser.close()
self.assertEqual("DONE", done)
self.assertEqual([
("start", "html"), ("start", "body"),
("end", "body"), ("end", "html")], events)
def test_html_parser_target_doctype_empty(self):
assertFalse = self.assertFalse
events = []
class Target(object):
def start(self, tag, attrib):
events.append(("start", tag))
assertFalse(attrib)
def end(self, tag):
events.append(("end", tag))
def doctype(self, *args):
events.append(("doctype", args))
def close(self):
return "DONE"
parser = self.etree.HTMLParser(target=Target())
parser.feed("<!DOCTYPE><html><body></body></html>")
done = parser.close()
self.assertEqual("DONE", done)
self.assertEqual([
("doctype", (None, None, None)),
("start", "html"), ("start", "body"),
("end", "body"), ("end", "html")], events)
def test_html_parser_target_doctype_html(self):
assertFalse = self.assertFalse
events = []
class Target(object):
def start(self, tag, attrib):
events.append(("start", tag))
assertFalse(attrib)
def end(self, tag):
events.append(("end", tag))
def doctype(self, *args):
events.append(("doctype", args))
def close(self):
return "DONE"
parser = self.etree.HTMLParser(target=Target())
parser.feed("<!DOCTYPE html><html><body></body></html>")
done = parser.close()
self.assertEqual("DONE", done)
self.assertEqual([
("doctype", ("html", None, None)),
("start", "html"), ("start", "body"),
("end", "body"), ("end", "html")], events)
def test_html_parser_target_doctype_html_full(self):
assertFalse = self.assertFalse
events = []
class Target(object):
def start(self, tag, attrib):
events.append(("start", tag))
assertFalse(attrib)
def end(self, tag):
events.append(("end", tag))
def doctype(self, *args):
events.append(("doctype", args))
def close(self):
return "DONE"
parser = self.etree.HTMLParser(target=Target())
parser.feed('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "sys.dtd">'
'<html><body></body></html>')
done = parser.close()
self.assertEqual("DONE", done)
self.assertEqual([
("doctype", ("html", "-//W3C//DTD HTML 4.01//EN", "sys.dtd")),
("start", "html"), ("start", "body"),
("end", "body"), ("end", "html")], events)
def test_suite():
suite = unittest.TestSuite()
suite.addTests([unittest.makeSuite(HtmlParserTestCase)])
return suite
if __name__ == '__main__':
print('to test use test.py %s' % __file__)
|
