forked from csev/py4e
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathelement.py
More file actions
1725 lines (1474 loc) · 64.1 KB
/
element.py
File metadata and controls
1725 lines (1474 loc) · 64.1 KB
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
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
__license__ = "MIT"
from pdb import set_trace
import collections
import re
import sys
import warnings
from bs4.dammit import EntitySubstitution
DEFAULT_OUTPUT_ENCODING = "utf-8"
PY3K = (sys.version_info[0] > 2)
whitespace_re = re.compile("\s+")
def _alias(attr):
"""Alias one attribute name to another for backward compatibility"""
@property
def alias(self):
return getattr(self, attr)
@alias.setter
def alias(self):
return setattr(self, attr)
return alias
class NamespacedAttribute(str):
def __new__(cls, prefix, name, namespace=None):
if name is None:
obj = str.__new__(cls, prefix)
elif prefix is None:
# Not really namespaced.
obj = str.__new__(cls, name)
else:
obj = str.__new__(cls, prefix + ":" + name)
obj.prefix = prefix
obj.name = name
obj.namespace = namespace
return obj
class AttributeValueWithCharsetSubstitution(str):
"""A stand-in object for a character encoding specified in HTML."""
class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution):
"""A generic stand-in for the value of a meta tag's 'charset' attribute.
When Beautiful Soup parses the markup '<meta charset="utf8">', the
value of the 'charset' attribute will be one of these objects.
"""
def __new__(cls, original_value):
obj = str.__new__(cls, original_value)
obj.original_value = original_value
return obj
def encode(self, encoding):
return encoding
class ContentMetaAttributeValue(AttributeValueWithCharsetSubstitution):
"""A generic stand-in for the value of a meta tag's 'content' attribute.
When Beautiful Soup parses the markup:
<meta http-equiv="content-type" content="text/html; charset=utf8">
The value of the 'content' attribute will be one of these objects.
"""
CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M)
def __new__(cls, original_value):
match = cls.CHARSET_RE.search(original_value)
if match is None:
# No substitution necessary.
return str.__new__(str, original_value)
obj = str.__new__(cls, original_value)
obj.original_value = original_value
return obj
def encode(self, encoding):
def rewrite(match):
return match.group(1) + encoding
return self.CHARSET_RE.sub(rewrite, self.original_value)
class HTMLAwareEntitySubstitution(EntitySubstitution):
"""Entity substitution rules that are aware of some HTML quirks.
Specifically, the contents of <script> and <style> tags should not
undergo entity substitution.
Incoming NavigableString objects are checked to see if they're the
direct children of a <script> or <style> tag.
"""
cdata_containing_tags = set(["script", "style"])
preformatted_tags = set(["pre"])
@classmethod
def _substitute_if_appropriate(cls, ns, f):
if (isinstance(ns, NavigableString)
and ns.parent is not None
and ns.parent.name in cls.cdata_containing_tags):
# Do nothing.
return ns
# Substitute.
return f(ns)
@classmethod
def substitute_html(cls, ns):
return cls._substitute_if_appropriate(
ns, EntitySubstitution.substitute_html)
@classmethod
def substitute_xml(cls, ns):
return cls._substitute_if_appropriate(
ns, EntitySubstitution.substitute_xml)
class PageElement(object):
"""Contains the navigational information for some part of the page
(either a tag or a piece of text)"""
# There are five possible values for the "formatter" argument passed in
# to methods like encode() and prettify():
#
# "html" - All Unicode characters with corresponding HTML entities
# are converted to those entities on output.
# "minimal" - Bare ampersands and angle brackets are converted to
# XML entities: & < >
# None - The null formatter. Unicode characters are never
# converted to entities. This is not recommended, but it's
# faster than "minimal".
# A function - This function will be called on every string that
# needs to undergo entity substitution.
#
# In an HTML document, the default "html" and "minimal" functions
# will leave the contents of <script> and <style> tags alone. For
# an XML document, all tags will be given the same treatment.
HTML_FORMATTERS = {
"html" : HTMLAwareEntitySubstitution.substitute_html,
"minimal" : HTMLAwareEntitySubstitution.substitute_xml,
None : None
}
XML_FORMATTERS = {
"html" : EntitySubstitution.substitute_html,
"minimal" : EntitySubstitution.substitute_xml,
None : None
}
def format_string(self, s, formatter='minimal'):
"""Format the given string using the given formatter."""
if not isinstance(formatter, collections.Callable):
formatter = self._formatter_for_name(formatter)
if formatter is None:
output = s
else:
output = formatter(s)
return output
@property
def _is_xml(self):
"""Is this element part of an XML tree or an HTML tree?
This is used when mapping a formatter name ("minimal") to an
appropriate function (one that performs entity-substitution on
the contents of <script> and <style> tags, or not). It's
inefficient, but it should be called very rarely.
"""
if self.parent is None:
# This is the top-level object. It should have .is_xml set
# from tree creation. If not, take a guess--BS is usually
# used on HTML markup.
return getattr(self, 'is_xml', False)
return self.parent._is_xml
def _formatter_for_name(self, name):
"Look up a formatter function based on its name and the tree."
if self._is_xml:
return self.XML_FORMATTERS.get(
name, EntitySubstitution.substitute_xml)
else:
return self.HTML_FORMATTERS.get(
name, HTMLAwareEntitySubstitution.substitute_xml)
def setup(self, parent=None, previous_element=None, next_element=None,
previous_sibling=None, next_sibling=None):
"""Sets up the initial relations between this element and
other elements."""
self.parent = parent
self.previous_element = previous_element
if previous_element is not None:
self.previous_element.next_element = self
self.next_element = next_element
if self.next_element:
self.next_element.previous_element = self
self.next_sibling = next_sibling
if self.next_sibling:
self.next_sibling.previous_sibling = self
if (not previous_sibling
and self.parent is not None and self.parent.contents):
previous_sibling = self.parent.contents[-1]
self.previous_sibling = previous_sibling
if previous_sibling:
self.previous_sibling.next_sibling = self
nextSibling = _alias("next_sibling") # BS3
previousSibling = _alias("previous_sibling") # BS3
def replace_with(self, replace_with):
if not self.parent:
raise ValueError(
"Cannot replace one element with another when the"
"element to be replaced is not part of a tree.")
if replace_with is self:
return
if replace_with is self.parent:
raise ValueError("Cannot replace a Tag with its parent.")
old_parent = self.parent
my_index = self.parent.index(self)
self.extract()
old_parent.insert(my_index, replace_with)
return self
replaceWith = replace_with # BS3
def unwrap(self):
my_parent = self.parent
if not self.parent:
raise ValueError(
"Cannot replace an element with its contents when that"
"element is not part of a tree.")
my_index = self.parent.index(self)
self.extract()
for child in reversed(self.contents[:]):
my_parent.insert(my_index, child)
return self
replace_with_children = unwrap
replaceWithChildren = unwrap # BS3
def wrap(self, wrap_inside):
me = self.replace_with(wrap_inside)
wrap_inside.append(me)
return wrap_inside
def extract(self):
"""Destructively rips this element out of the tree."""
if self.parent is not None:
del self.parent.contents[self.parent.index(self)]
#Find the two elements that would be next to each other if
#this element (and any children) hadn't been parsed. Connect
#the two.
last_child = self._last_descendant()
next_element = last_child.next_element
if (self.previous_element is not None and
self.previous_element is not next_element):
self.previous_element.next_element = next_element
if next_element is not None and next_element is not self.previous_element:
next_element.previous_element = self.previous_element
self.previous_element = None
last_child.next_element = None
self.parent = None
if (self.previous_sibling is not None
and self.previous_sibling is not self.next_sibling):
self.previous_sibling.next_sibling = self.next_sibling
if (self.next_sibling is not None
and self.next_sibling is not self.previous_sibling):
self.next_sibling.previous_sibling = self.previous_sibling
self.previous_sibling = self.next_sibling = None
return self
def _last_descendant(self, is_initialized=True, accept_self=True):
"Finds the last element beneath this object to be parsed."
if is_initialized and self.next_sibling:
last_child = self.next_sibling.previous_element
else:
last_child = self
while isinstance(last_child, Tag) and last_child.contents:
last_child = last_child.contents[-1]
if not accept_self and last_child is self:
last_child = None
return last_child
# BS3: Not part of the API!
_lastRecursiveChild = _last_descendant
def insert(self, position, new_child):
if new_child is None:
raise ValueError("Cannot insert None into a tag.")
if new_child is self:
raise ValueError("Cannot insert a tag into itself.")
if (isinstance(new_child, str)
and not isinstance(new_child, NavigableString)):
new_child = NavigableString(new_child)
position = min(position, len(self.contents))
if hasattr(new_child, 'parent') and new_child.parent is not None:
# We're 'inserting' an element that's already one
# of this object's children.
if new_child.parent is self:
current_index = self.index(new_child)
if current_index < position:
# We're moving this element further down the list
# of this object's children. That means that when
# we extract this element, our target index will
# jump down one.
position -= 1
new_child.extract()
new_child.parent = self
previous_child = None
if position == 0:
new_child.previous_sibling = None
new_child.previous_element = self
else:
previous_child = self.contents[position - 1]
new_child.previous_sibling = previous_child
new_child.previous_sibling.next_sibling = new_child
new_child.previous_element = previous_child._last_descendant(False)
if new_child.previous_element is not None:
new_child.previous_element.next_element = new_child
new_childs_last_element = new_child._last_descendant(False)
if position >= len(self.contents):
new_child.next_sibling = None
parent = self
parents_next_sibling = None
while parents_next_sibling is None and parent is not None:
parents_next_sibling = parent.next_sibling
parent = parent.parent
if parents_next_sibling is not None:
# We found the element that comes next in the document.
break
if parents_next_sibling is not None:
new_childs_last_element.next_element = parents_next_sibling
else:
# The last element of this tag is the last element in
# the document.
new_childs_last_element.next_element = None
else:
next_child = self.contents[position]
new_child.next_sibling = next_child
if new_child.next_sibling is not None:
new_child.next_sibling.previous_sibling = new_child
new_childs_last_element.next_element = next_child
if new_childs_last_element.next_element is not None:
new_childs_last_element.next_element.previous_element = new_childs_last_element
self.contents.insert(position, new_child)
def append(self, tag):
"""Appends the given tag to the contents of this tag."""
self.insert(len(self.contents), tag)
def insert_before(self, predecessor):
"""Makes the given element the immediate predecessor of this one.
The two elements will have the same parent, and the given element
will be immediately before this one.
"""
if self is predecessor:
raise ValueError("Can't insert an element before itself.")
parent = self.parent
if parent is None:
raise ValueError(
"Element has no parent, so 'before' has no meaning.")
# Extract first so that the index won't be screwed up if they
# are siblings.
if isinstance(predecessor, PageElement):
predecessor.extract()
index = parent.index(self)
parent.insert(index, predecessor)
def insert_after(self, successor):
"""Makes the given element the immediate successor of this one.
The two elements will have the same parent, and the given element
will be immediately after this one.
"""
if self is successor:
raise ValueError("Can't insert an element after itself.")
parent = self.parent
if parent is None:
raise ValueError(
"Element has no parent, so 'after' has no meaning.")
# Extract first so that the index won't be screwed up if they
# are siblings.
if isinstance(successor, PageElement):
successor.extract()
index = parent.index(self)
parent.insert(index+1, successor)
def find_next(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the first item that matches the given criteria and
appears after this Tag in the document."""
return self._find_one(self.find_all_next, name, attrs, text, **kwargs)
findNext = find_next # BS3
def find_all_next(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns all items that match the given criteria and appear
after this Tag in the document."""
return self._find_all(name, attrs, text, limit, self.next_elements,
**kwargs)
findAllNext = find_all_next # BS3
def find_next_sibling(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the closest sibling to this Tag that matches the
given criteria and appears after this Tag in the document."""
return self._find_one(self.find_next_siblings, name, attrs, text,
**kwargs)
findNextSibling = find_next_sibling # BS3
def find_next_siblings(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns the siblings of this Tag that match the given
criteria and appear after this Tag in the document."""
return self._find_all(name, attrs, text, limit,
self.next_siblings, **kwargs)
findNextSiblings = find_next_siblings # BS3
fetchNextSiblings = find_next_siblings # BS2
def find_previous(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the first item that matches the given criteria and
appears before this Tag in the document."""
return self._find_one(
self.find_all_previous, name, attrs, text, **kwargs)
findPrevious = find_previous # BS3
def find_all_previous(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns all items that match the given criteria and appear
before this Tag in the document."""
return self._find_all(name, attrs, text, limit, self.previous_elements,
**kwargs)
findAllPrevious = find_all_previous # BS3
fetchPrevious = find_all_previous # BS2
def find_previous_sibling(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the closest sibling to this Tag that matches the
given criteria and appears before this Tag in the document."""
return self._find_one(self.find_previous_siblings, name, attrs, text,
**kwargs)
findPreviousSibling = find_previous_sibling # BS3
def find_previous_siblings(self, name=None, attrs={}, text=None,
limit=None, **kwargs):
"""Returns the siblings of this Tag that match the given
criteria and appear before this Tag in the document."""
return self._find_all(name, attrs, text, limit,
self.previous_siblings, **kwargs)
findPreviousSiblings = find_previous_siblings # BS3
fetchPreviousSiblings = find_previous_siblings # BS2
def find_parent(self, name=None, attrs={}, **kwargs):
"""Returns the closest parent of this Tag that matches the given
criteria."""
# NOTE: We can't use _find_one because findParents takes a different
# set of arguments.
r = None
l = self.find_parents(name, attrs, 1, **kwargs)
if l:
r = l[0]
return r
findParent = find_parent # BS3
def find_parents(self, name=None, attrs={}, limit=None, **kwargs):
"""Returns the parents of this Tag that match the given
criteria."""
return self._find_all(name, attrs, None, limit, self.parents,
**kwargs)
findParents = find_parents # BS3
fetchParents = find_parents # BS2
@property
def next(self):
return self.next_element
@property
def previous(self):
return self.previous_element
#These methods do the real heavy lifting.
def _find_one(self, method, name, attrs, text, **kwargs):
r = None
l = method(name, attrs, text, 1, **kwargs)
if l:
r = l[0]
return r
def _find_all(self, name, attrs, text, limit, generator, **kwargs):
"Iterates over a generator looking for things that match."
if text is None and 'string' in kwargs:
text = kwargs['string']
del kwargs['string']
if isinstance(name, SoupStrainer):
strainer = name
else:
strainer = SoupStrainer(name, attrs, text, **kwargs)
if text is None and not limit and not attrs and not kwargs:
if name is True or name is None:
# Optimization to find all tags.
result = (element for element in generator
if isinstance(element, Tag))
return ResultSet(strainer, result)
elif isinstance(name, str):
# Optimization to find all tags with a given name.
result = (element for element in generator
if isinstance(element, Tag)
and element.name == name)
return ResultSet(strainer, result)
results = ResultSet(strainer)
while True:
try:
i = next(generator)
except StopIteration:
break
if i:
found = strainer.search(i)
if found:
results.append(found)
if limit and len(results) >= limit:
break
return results
#These generators can be used to navigate starting from both
#NavigableStrings and Tags.
@property
def next_elements(self):
i = self.next_element
while i is not None:
yield i
i = i.next_element
@property
def next_siblings(self):
i = self.next_sibling
while i is not None:
yield i
i = i.next_sibling
@property
def previous_elements(self):
i = self.previous_element
while i is not None:
yield i
i = i.previous_element
@property
def previous_siblings(self):
i = self.previous_sibling
while i is not None:
yield i
i = i.previous_sibling
@property
def parents(self):
i = self.parent
while i is not None:
yield i
i = i.parent
# Methods for supporting CSS selectors.
tag_name_re = re.compile('^[a-zA-Z0-9][-.a-zA-Z0-9:_]*$')
# /^([a-zA-Z0-9][-.a-zA-Z0-9:_]*)\[(\w+)([=~\|\^\$\*]?)=?"?([^\]"]*)"?\]$/
# \---------------------------/ \---/\-------------/ \-------/
# | | | |
# | | | The value
# | | ~,|,^,$,* or =
# | Attribute
# Tag
attribselect_re = re.compile(
r'^(?P<tag>[a-zA-Z0-9][-.a-zA-Z0-9:_]*)?\[(?P<attribute>[\w-]+)(?P<operator>[=~\|\^\$\*]?)' +
r'=?"?(?P<value>[^\]"]*)"?\]$'
)
def _attr_value_as_string(self, value, default=None):
"""Force an attribute value into a string representation.
A multi-valued attribute will be converted into a
space-separated stirng.
"""
value = self.get(value, default)
if isinstance(value, list) or isinstance(value, tuple):
value =" ".join(value)
return value
def _tag_name_matches_and(self, function, tag_name):
if not tag_name:
return function
else:
def _match(tag):
return tag.name == tag_name and function(tag)
return _match
def _attribute_checker(self, operator, attribute, value=''):
"""Create a function that performs a CSS selector operation.
Takes an operator, attribute and optional value. Returns a
function that will return True for elements that match that
combination.
"""
if operator == '=':
# string representation of `attribute` is equal to `value`
return lambda el: el._attr_value_as_string(attribute) == value
elif operator == '~':
# space-separated list representation of `attribute`
# contains `value`
def _includes_value(element):
attribute_value = element.get(attribute, [])
if not isinstance(attribute_value, list):
attribute_value = attribute_value.split()
return value in attribute_value
return _includes_value
elif operator == '^':
# string representation of `attribute` starts with `value`
return lambda el: el._attr_value_as_string(
attribute, '').startswith(value)
elif operator == '$':
# string represenation of `attribute` ends with `value`
return lambda el: el._attr_value_as_string(
attribute, '').endswith(value)
elif operator == '*':
# string representation of `attribute` contains `value`
return lambda el: value in el._attr_value_as_string(attribute, '')
elif operator == '|':
# string representation of `attribute` is either exactly
# `value` or starts with `value` and then a dash.
def _is_or_starts_with_dash(element):
attribute_value = element._attr_value_as_string(attribute, '')
return (attribute_value == value or attribute_value.startswith(
value + '-'))
return _is_or_starts_with_dash
else:
return lambda el: el.has_attr(attribute)
# Old non-property versions of the generators, for backwards
# compatibility with BS3.
def nextGenerator(self):
return self.next_elements
def nextSiblingGenerator(self):
return self.next_siblings
def previousGenerator(self):
return self.previous_elements
def previousSiblingGenerator(self):
return self.previous_siblings
def parentGenerator(self):
return self.parents
class NavigableString(str, PageElement):
PREFIX = ''
SUFFIX = ''
def __new__(cls, value):
"""Create a new NavigableString.
When unpickling a NavigableString, this method is called with
the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
passed in to the superclass's __new__ or the superclass won't know
how to handle non-ASCII characters.
"""
if isinstance(value, str):
u = str.__new__(cls, value)
else:
u = str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
u.setup()
return u
def __copy__(self):
"""A copy of a NavigableString has the same contents and class
as the original, but it is not connected to the parse tree.
"""
return type(self)(self)
def __getnewargs__(self):
return (str(self),)
def __getattr__(self, attr):
"""text.string gives you text. This is for backwards
compatibility for Navigable*String, but for CData* it lets you
get the string without the CData wrapper."""
if attr == 'string':
return self
else:
raise AttributeError(
"'%s' object has no attribute '%s'" % (
self.__class__.__name__, attr))
def output_ready(self, formatter="minimal"):
output = self.format_string(self, formatter)
return self.PREFIX + output + self.SUFFIX
@property
def name(self):
return None
@name.setter
def name(self, name):
raise AttributeError("A NavigableString cannot be given a name.")
class PreformattedString(NavigableString):
"""A NavigableString not subject to the normal formatting rules.
The string will be passed into the formatter (to trigger side effects),
but the return value will be ignored.
"""
def output_ready(self, formatter="minimal"):
"""CData strings are passed into the formatter.
But the return value is ignored."""
self.format_string(self, formatter)
return self.PREFIX + self + self.SUFFIX
class CData(PreformattedString):
PREFIX = '<![CDATA['
SUFFIX = ']]>'
class ProcessingInstruction(PreformattedString):
PREFIX = '<?'
SUFFIX = '>'
class Comment(PreformattedString):
PREFIX = '<!--'
SUFFIX = '-->'
class Declaration(PreformattedString):
PREFIX = '<?'
SUFFIX = '?>'
class Doctype(PreformattedString):
@classmethod
def for_name_and_ids(cls, name, pub_id, system_id):
value = name or ''
if pub_id is not None:
value += ' PUBLIC "%s"' % pub_id
if system_id is not None:
value += ' "%s"' % system_id
elif system_id is not None:
value += ' SYSTEM "%s"' % system_id
return Doctype(value)
PREFIX = '<!DOCTYPE '
SUFFIX = '>\n'
class Tag(PageElement):
"""Represents a found HTML tag with its attributes and contents."""
def __init__(self, parser=None, builder=None, name=None, namespace=None,
prefix=None, attrs=None, parent=None, previous=None):
"Basic constructor."
if parser is None:
self.parser_class = None
else:
# We don't actually store the parser object: that lets extracted
# chunks be garbage-collected.
self.parser_class = parser.__class__
if name is None:
raise ValueError("No value provided for new tag's name.")
self.name = name
self.namespace = namespace
self.prefix = prefix
if attrs is None:
attrs = {}
elif attrs:
if builder is not None and builder.cdata_list_attributes:
attrs = builder._replace_cdata_list_attribute_values(
self.name, attrs)
else:
attrs = dict(attrs)
else:
attrs = dict(attrs)
self.attrs = attrs
self.contents = []
self.setup(parent, previous)
self.hidden = False
# Set up any substitutions, such as the charset in a META tag.
if builder is not None:
builder.set_up_substitutions(self)
self.can_be_empty_element = builder.can_be_empty_element(name)
else:
self.can_be_empty_element = False
parserClass = _alias("parser_class") # BS3
def __copy__(self):
"""A copy of a Tag is a new Tag, unconnected to the parse tree.
Its contents are a copy of the old Tag's contents.
"""
clone = type(self)(None, self.builder, self.name, self.namespace,
self.nsprefix, self.attrs)
for attr in ('can_be_empty_element', 'hidden'):
setattr(clone, attr, getattr(self, attr))
for child in self.contents:
clone.append(child.__copy__())
return clone
@property
def is_empty_element(self):
"""Is this tag an empty-element tag? (aka a self-closing tag)
A tag that has contents is never an empty-element tag.
A tag that has no contents may or may not be an empty-element
tag. It depends on the builder used to create the tag. If the
builder has a designated list of empty-element tags, then only
a tag whose name shows up in that list is considered an
empty-element tag.
If the builder has no designated list of empty-element tags,
then any tag with no contents is an empty-element tag.
"""
return len(self.contents) == 0 and self.can_be_empty_element
isSelfClosing = is_empty_element # BS3
@property
def string(self):
"""Convenience property to get the single string within this tag.
:Return: If this tag has a single string child, return value
is that string. If this tag has no children, or more than one
child, return value is None. If this tag has one child tag,
return value is the 'string' attribute of the child tag,
recursively.
"""
if len(self.contents) != 1:
return None
child = self.contents[0]
if isinstance(child, NavigableString):
return child
return child.string
@string.setter
def string(self, string):
self.clear()
self.append(string.__class__(string))
def _all_strings(self, strip=False, types=(NavigableString, CData)):
"""Yield all strings of certain classes, possibly stripping them.
By default, yields only NavigableString and CData objects. So
no comments, processing instructions, etc.
"""
for descendant in self.descendants:
if (
(types is None and not isinstance(descendant, NavigableString))
or
(types is not None and type(descendant) not in types)):
continue
if strip:
descendant = descendant.strip()
if len(descendant) == 0:
continue
yield descendant
strings = property(_all_strings)
@property
def stripped_strings(self):
for string in self._all_strings(True):
yield string
def get_text(self, separator="", strip=False,
types=(NavigableString, CData)):
"""
Get all child strings, concatenated using the given separator.
"""
return separator.join([s for s in self._all_strings(
strip, types=types)])
getText = get_text
text = property(get_text)
def decompose(self):
"""Recursively destroys the contents of this tree."""
self.extract()
i = self
while i is not None:
next = i.next_element
i.__dict__.clear()
i.contents = []
i = next
def clear(self, decompose=False):
"""
Extract all children. If decompose is True, decompose instead.
"""
if decompose:
for element in self.contents[:]:
if isinstance(element, Tag):
element.decompose()
else:
element.extract()
else:
for element in self.contents[:]:
element.extract()
def index(self, element):
"""
Find the index of a child by identity, not value. Avoids issues with
tag.contents.index(element) getting the index of equal elements.
"""
for i, child in enumerate(self.contents):
if child is element:
return i
raise ValueError("Tag.index: element not in tag")
def get(self, key, default=None):
"""Returns the value of the 'key' attribute for the tag, or
the value given for 'default' if it doesn't have that
attribute."""
return self.attrs.get(key, default)
def has_attr(self, key):
return key in self.attrs
def __hash__(self):
return str(self).__hash__()
def __getitem__(self, key):
"""tag[key] returns the value of the 'key' attribute for the tag,
and throws an exception if it's not there."""
return self.attrs[key]
def __iter__(self):
"Iterating over a tag iterates over its contents."
return iter(self.contents)
def __len__(self):
"The length of a tag is the length of its list of contents."
return len(self.contents)
def __contains__(self, x):
return x in self.contents
def __bool__(self):
"A tag is non-None even if it has no contents."
return True
def __setitem__(self, key, value):
"""Setting tag[key] sets the value of the 'key' attribute for the
tag."""
self.attrs[key] = value
def __delitem__(self, key):
"Deleting tag[key] deletes all 'key' attributes for the tag."
self.attrs.pop(key, None)
def __call__(self, *args, **kwargs):
"""Calling a tag like a function is the same as calling its
find_all() method. Eg. tag('a') returns a list of all the A tags
found within this tag."""
return self.find_all(*args, **kwargs)
def __getattr__(self, tag):
#print "Getattr %s.%s" % (self.__class__, tag)
if len(tag) > 3 and tag.endswith('Tag'):
# BS3: soup.aTag -> "soup.find("a")
tag_name = tag[:-3]
warnings.warn(
'.%sTag is deprecated, use .find("%s") instead.' % (
tag_name, tag_name))
return self.find(tag_name)
# We special case contents to avoid recursion.
elif not tag.startswith("__") and not tag=="contents":