Mercurial > repos > guerler > springsuite
annotate planemo/lib/python3.7/site-packages/bs4/builder/__init__.py @ 0:d30785e31577 draft
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
author | guerler |
---|---|
date | Fri, 31 Jul 2020 00:18:57 -0400 |
parents | |
children |
rev | line source |
---|---|
0
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
1 # Use of this source code is governed by the MIT license. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
2 __license__ = "MIT" |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
3 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
4 from collections import defaultdict |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
5 import itertools |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
6 import sys |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
7 from bs4.element import ( |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
8 CharsetMetaAttributeValue, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
9 ContentMetaAttributeValue, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
10 Stylesheet, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
11 Script, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
12 TemplateString, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
13 nonwhitespace_re |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
14 ) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
15 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
16 __all__ = [ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
17 'HTMLTreeBuilder', |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
18 'SAXTreeBuilder', |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
19 'TreeBuilder', |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
20 'TreeBuilderRegistry', |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
21 ] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
22 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
23 # Some useful features for a TreeBuilder to have. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
24 FAST = 'fast' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
25 PERMISSIVE = 'permissive' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
26 STRICT = 'strict' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
27 XML = 'xml' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
28 HTML = 'html' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
29 HTML_5 = 'html5' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
30 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
31 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
32 class TreeBuilderRegistry(object): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
33 """A way of looking up TreeBuilder subclasses by their name or by desired |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
34 features. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
35 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
36 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
37 def __init__(self): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
38 self.builders_for_feature = defaultdict(list) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
39 self.builders = [] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
40 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
41 def register(self, treebuilder_class): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
42 """Register a treebuilder based on its advertised features. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
43 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
44 :param treebuilder_class: A subclass of Treebuilder. its .features |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
45 attribute should list its features. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
46 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
47 for feature in treebuilder_class.features: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
48 self.builders_for_feature[feature].insert(0, treebuilder_class) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
49 self.builders.insert(0, treebuilder_class) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
50 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
51 def lookup(self, *features): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
52 """Look up a TreeBuilder subclass with the desired features. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
53 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
54 :param features: A list of features to look for. If none are |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
55 provided, the most recently registered TreeBuilder subclass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
56 will be used. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
57 :return: A TreeBuilder subclass, or None if there's no |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
58 registered subclass with all the requested features. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
59 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
60 if len(self.builders) == 0: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
61 # There are no builders at all. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
62 return None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
63 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
64 if len(features) == 0: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
65 # They didn't ask for any features. Give them the most |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
66 # recently registered builder. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
67 return self.builders[0] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
68 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
69 # Go down the list of features in order, and eliminate any builders |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
70 # that don't match every feature. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
71 features = list(features) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
72 features.reverse() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
73 candidates = None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
74 candidate_set = None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
75 while len(features) > 0: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
76 feature = features.pop() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
77 we_have_the_feature = self.builders_for_feature.get(feature, []) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
78 if len(we_have_the_feature) > 0: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
79 if candidates is None: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
80 candidates = we_have_the_feature |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
81 candidate_set = set(candidates) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
82 else: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
83 # Eliminate any candidates that don't have this feature. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
84 candidate_set = candidate_set.intersection( |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
85 set(we_have_the_feature)) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
86 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
87 # The only valid candidates are the ones in candidate_set. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
88 # Go through the original list of candidates and pick the first one |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
89 # that's in candidate_set. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
90 if candidate_set is None: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
91 return None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
92 for candidate in candidates: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
93 if candidate in candidate_set: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
94 return candidate |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
95 return None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
96 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
97 # The BeautifulSoup class will take feature lists from developers and use them |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
98 # to look up builders in this registry. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
99 builder_registry = TreeBuilderRegistry() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
100 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
101 class TreeBuilder(object): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
102 """Turn a textual document into a Beautiful Soup object tree.""" |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
103 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
104 NAME = "[Unknown tree builder]" |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
105 ALTERNATE_NAMES = [] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
106 features = [] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
107 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
108 is_xml = False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
109 picklable = False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
110 empty_element_tags = None # A tag will be considered an empty-element |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
111 # tag when and only when it has no contents. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
112 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
113 # A value for these tag/attribute combinations is a space- or |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
114 # comma-separated list of CDATA, rather than a single CDATA. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
115 DEFAULT_CDATA_LIST_ATTRIBUTES = {} |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
116 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
117 # Whitespace should be preserved inside these tags. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
118 DEFAULT_PRESERVE_WHITESPACE_TAGS = set() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
119 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
120 # The textual contents of tags with these names should be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
121 # instantiated with some class other than NavigableString. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
122 DEFAULT_STRING_CONTAINERS = {} |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
123 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
124 USE_DEFAULT = object() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
125 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
126 # Most parsers don't keep track of line numbers. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
127 TRACKS_LINE_NUMBERS = False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
128 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
129 def __init__(self, multi_valued_attributes=USE_DEFAULT, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
130 preserve_whitespace_tags=USE_DEFAULT, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
131 store_line_numbers=USE_DEFAULT, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
132 string_containers=USE_DEFAULT, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
133 ): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
134 """Constructor. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
135 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
136 :param multi_valued_attributes: If this is set to None, the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
137 TreeBuilder will not turn any values for attributes like |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
138 'class' into lists. Setting this to a dictionary will |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
139 customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
140 for an example. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
141 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
142 Internally, these are called "CDATA list attributes", but that |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
143 probably doesn't make sense to an end-user, so the argument name |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
144 is `multi_valued_attributes`. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
145 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
146 :param preserve_whitespace_tags: A list of tags to treat |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
147 the way <pre> tags are treated in HTML. Tags in this list |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
148 are immune from pretty-printing; their contents will always be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
149 output as-is. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
150 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
151 :param string_containers: A dictionary mapping tag names to |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
152 the classes that should be instantiated to contain the textual |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
153 contents of those tags. The default is to use NavigableString |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
154 for every tag, no matter what the name. You can override the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
155 default by changing DEFAULT_STRING_CONTAINERS. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
156 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
157 :param store_line_numbers: If the parser keeps track of the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
158 line numbers and positions of the original markup, that |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
159 information will, by default, be stored in each corresponding |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
160 `Tag` object. You can turn this off by passing |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
161 store_line_numbers=False. If the parser you're using doesn't |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
162 keep track of this information, then setting store_line_numbers=True |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
163 will do nothing. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
164 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
165 self.soup = None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
166 if multi_valued_attributes is self.USE_DEFAULT: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
167 multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
168 self.cdata_list_attributes = multi_valued_attributes |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
169 if preserve_whitespace_tags is self.USE_DEFAULT: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
170 preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
171 self.preserve_whitespace_tags = preserve_whitespace_tags |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
172 if store_line_numbers == self.USE_DEFAULT: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
173 store_line_numbers = self.TRACKS_LINE_NUMBERS |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
174 self.store_line_numbers = store_line_numbers |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
175 if string_containers == self.USE_DEFAULT: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
176 string_containers = self.DEFAULT_STRING_CONTAINERS |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
177 self.string_containers = string_containers |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
178 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
179 def initialize_soup(self, soup): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
180 """The BeautifulSoup object has been initialized and is now |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
181 being associated with the TreeBuilder. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
182 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
183 :param soup: A BeautifulSoup object. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
184 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
185 self.soup = soup |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
186 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
187 def reset(self): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
188 """Do any work necessary to reset the underlying parser |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
189 for a new document. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
190 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
191 By default, this does nothing. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
192 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
193 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
194 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
195 def can_be_empty_element(self, tag_name): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
196 """Might a tag with this name be an empty-element tag? |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
197 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
198 The final markup may or may not actually present this tag as |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
199 self-closing. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
200 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
201 For instance: an HTMLBuilder does not consider a <p> tag to be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
202 an empty-element tag (it's not in |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
203 HTMLBuilder.empty_element_tags). This means an empty <p> tag |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
204 will be presented as "<p></p>", not "<p/>" or "<p>". |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
205 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
206 The default implementation has no opinion about which tags are |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
207 empty-element tags, so a tag will be presented as an |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
208 empty-element tag if and only if it has no children. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
209 "<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
210 be left alone. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
211 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
212 :param tag_name: The name of a markup tag. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
213 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
214 if self.empty_element_tags is None: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
215 return True |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
216 return tag_name in self.empty_element_tags |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
217 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
218 def feed(self, markup): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
219 """Run some incoming markup through some parsing process, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
220 populating the `BeautifulSoup` object in self.soup. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
221 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
222 This method is not implemented in TreeBuilder; it must be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
223 implemented in subclasses. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
224 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
225 :return: None. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
226 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
227 raise NotImplementedError() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
228 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
229 def prepare_markup(self, markup, user_specified_encoding=None, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
230 document_declared_encoding=None, exclude_encodings=None): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
231 """Run any preliminary steps necessary to make incoming markup |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
232 acceptable to the parser. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
233 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
234 :param markup: Some markup -- probably a bytestring. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
235 :param user_specified_encoding: The user asked to try this encoding. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
236 :param document_declared_encoding: The markup itself claims to be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
237 in this encoding. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
238 :param exclude_encodings: The user asked _not_ to try any of |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
239 these encodings. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
240 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
241 :yield: A series of 4-tuples: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
242 (markup, encoding, declared encoding, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
243 has undergone character replacement) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
244 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
245 Each 4-tuple represents a strategy for converting the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
246 document to Unicode and parsing it. Each strategy will be tried |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
247 in turn. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
248 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
249 By default, the only strategy is to parse the markup |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
250 as-is. See `LXMLTreeBuilderForXML` and |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
251 `HTMLParserTreeBuilder` for implementations that take into |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
252 account the quirks of particular parsers. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
253 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
254 yield markup, None, None, False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
255 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
256 def test_fragment_to_document(self, fragment): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
257 """Wrap an HTML fragment to make it look like a document. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
258 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
259 Different parsers do this differently. For instance, lxml |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
260 introduces an empty <head> tag, and html5lib |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
261 doesn't. Abstracting this away lets us write simple tests |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
262 which run HTML fragments through the parser and compare the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
263 results against other HTML fragments. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
264 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
265 This method should not be used outside of tests. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
266 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
267 :param fragment: A string -- fragment of HTML. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
268 :return: A string -- a full HTML document. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
269 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
270 return fragment |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
271 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
272 def set_up_substitutions(self, tag): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
273 """Set up any substitutions that will need to be performed on |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
274 a `Tag` when it's output as a string. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
275 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
276 By default, this does nothing. See `HTMLTreeBuilder` for a |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
277 case where this is used. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
278 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
279 :param tag: A `Tag` |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
280 :return: Whether or not a substitution was performed. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
281 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
282 return False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
283 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
284 def _replace_cdata_list_attribute_values(self, tag_name, attrs): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
285 """When an attribute value is associated with a tag that can |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
286 have multiple values for that attribute, convert the string |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
287 value to a list of strings. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
288 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
289 Basically, replaces class="foo bar" with class=["foo", "bar"] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
290 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
291 NOTE: This method modifies its input in place. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
292 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
293 :param tag_name: The name of a tag. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
294 :param attrs: A dictionary containing the tag's attributes. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
295 Any appropriate attribute values will be modified in place. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
296 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
297 if not attrs: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
298 return attrs |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
299 if self.cdata_list_attributes: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
300 universal = self.cdata_list_attributes.get('*', []) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
301 tag_specific = self.cdata_list_attributes.get( |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
302 tag_name.lower(), None) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
303 for attr in list(attrs.keys()): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
304 if attr in universal or (tag_specific and attr in tag_specific): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
305 # We have a "class"-type attribute whose string |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
306 # value is a whitespace-separated list of |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
307 # values. Split it into a list. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
308 value = attrs[attr] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
309 if isinstance(value, str): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
310 values = nonwhitespace_re.findall(value) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
311 else: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
312 # html5lib sometimes calls setAttributes twice |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
313 # for the same tag when rearranging the parse |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
314 # tree. On the second call the attribute value |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
315 # here is already a list. If this happens, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
316 # leave the value alone rather than trying to |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
317 # split it again. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
318 values = value |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
319 attrs[attr] = values |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
320 return attrs |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
321 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
322 class SAXTreeBuilder(TreeBuilder): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
323 """A Beautiful Soup treebuilder that listens for SAX events. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
324 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
325 This is not currently used for anything, but it demonstrates |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
326 how a simple TreeBuilder would work. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
327 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
328 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
329 def feed(self, markup): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
330 raise NotImplementedError() |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
331 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
332 def close(self): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
333 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
334 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
335 def startElement(self, name, attrs): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
336 attrs = dict((key[1], value) for key, value in list(attrs.items())) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
337 #print("Start %s, %r" % (name, attrs)) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
338 self.soup.handle_starttag(name, attrs) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
339 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
340 def endElement(self, name): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
341 #print("End %s" % name) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
342 self.soup.handle_endtag(name) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
343 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
344 def startElementNS(self, nsTuple, nodeName, attrs): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
345 # Throw away (ns, nodeName) for now. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
346 self.startElement(nodeName, attrs) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
347 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
348 def endElementNS(self, nsTuple, nodeName): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
349 # Throw away (ns, nodeName) for now. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
350 self.endElement(nodeName) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
351 #handler.endElementNS((ns, node.nodeName), node.nodeName) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
352 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
353 def startPrefixMapping(self, prefix, nodeValue): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
354 # Ignore the prefix for now. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
355 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
356 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
357 def endPrefixMapping(self, prefix): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
358 # Ignore the prefix for now. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
359 # handler.endPrefixMapping(prefix) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
360 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
361 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
362 def characters(self, content): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
363 self.soup.handle_data(content) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
364 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
365 def startDocument(self): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
366 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
367 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
368 def endDocument(self): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
369 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
370 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
371 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
372 class HTMLTreeBuilder(TreeBuilder): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
373 """This TreeBuilder knows facts about HTML. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
374 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
375 Such as which tags are empty-element tags. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
376 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
377 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
378 empty_element_tags = set([ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
379 # These are from HTML5. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
380 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr', |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
381 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
382 # These are from earlier versions of HTML and are removed in HTML5. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
383 'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer' |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
384 ]) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
385 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
386 # The HTML standard defines these as block-level elements. Beautiful |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
387 # Soup does not treat these elements differently from other elements, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
388 # but it may do so eventually, and this information is available if |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
389 # you need to use it. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
390 block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"]) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
391 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
392 # The HTML standard defines an unusual content model for these tags. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
393 # We represent this by using a string class other than NavigableString |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
394 # inside these tags. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
395 # |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
396 # I made this list by going through the HTML spec |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
397 # (https://html.spec.whatwg.org/#metadata-content) and looking for |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
398 # "metadata content" elements that can contain strings. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
399 # |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
400 # TODO: Arguably <noscript> could go here but it seems |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
401 # qualitatively different from the other tags. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
402 DEFAULT_STRING_CONTAINERS = { |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
403 'style': Stylesheet, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
404 'script': Script, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
405 'template': TemplateString, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
406 } |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
407 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
408 # The HTML standard defines these attributes as containing a |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
409 # space-separated list of values, not a single value. That is, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
410 # class="foo bar" means that the 'class' attribute has two values, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
411 # 'foo' and 'bar', not the single value 'foo bar'. When we |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
412 # encounter one of these attributes, we will parse its value into |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
413 # a list of values if possible. Upon output, the list will be |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
414 # converted back into a string. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
415 DEFAULT_CDATA_LIST_ATTRIBUTES = { |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
416 "*" : ['class', 'accesskey', 'dropzone'], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
417 "a" : ['rel', 'rev'], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
418 "link" : ['rel', 'rev'], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
419 "td" : ["headers"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
420 "th" : ["headers"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
421 "td" : ["headers"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
422 "form" : ["accept-charset"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
423 "object" : ["archive"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
424 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
425 # These are HTML5 specific, as are *.accesskey and *.dropzone above. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
426 "area" : ["rel"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
427 "icon" : ["sizes"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
428 "iframe" : ["sandbox"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
429 "output" : ["for"], |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
430 } |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
431 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
432 DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea']) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
433 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
434 def set_up_substitutions(self, tag): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
435 """Replace the declared encoding in a <meta> tag with a placeholder, |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
436 to be substituted when the tag is output to a string. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
437 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
438 An HTML document may come in to Beautiful Soup as one |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
439 encoding, but exit in a different encoding, and the <meta> tag |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
440 needs to be changed to reflect this. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
441 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
442 :param tag: A `Tag` |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
443 :return: Whether or not a substitution was performed. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
444 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
445 # We are only interested in <meta> tags |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
446 if tag.name != 'meta': |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
447 return False |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
448 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
449 http_equiv = tag.get('http-equiv') |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
450 content = tag.get('content') |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
451 charset = tag.get('charset') |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
452 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
453 # We are interested in <meta> tags that say what encoding the |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
454 # document was originally in. This means HTML 5-style <meta> |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
455 # tags that provide the "charset" attribute. It also means |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
456 # HTML 4-style <meta> tags that provide the "content" |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
457 # attribute and have "http-equiv" set to "content-type". |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
458 # |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
459 # In both cases we will replace the value of the appropriate |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
460 # attribute with a standin object that can take on any |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
461 # encoding. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
462 meta_encoding = None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
463 if charset is not None: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
464 # HTML 5 style: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
465 # <meta charset="utf8"> |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
466 meta_encoding = charset |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
467 tag['charset'] = CharsetMetaAttributeValue(charset) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
468 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
469 elif (content is not None and http_equiv is not None |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
470 and http_equiv.lower() == 'content-type'): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
471 # HTML 4 style: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
472 # <meta http-equiv="content-type" content="text/html; charset=utf8"> |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
473 tag['content'] = ContentMetaAttributeValue(content) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
474 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
475 return (meta_encoding is not None) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
476 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
477 def register_treebuilders_from(module): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
478 """Copy TreeBuilders from the given module into this module.""" |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
479 # I'm fairly sure this is not the best way to do this. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
480 this_module = sys.modules['bs4.builder'] |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
481 for name in module.__all__: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
482 obj = getattr(module, name) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
483 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
484 if issubclass(obj, TreeBuilder): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
485 setattr(this_module, name, obj) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
486 this_module.__all__.append(name) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
487 # Register the builder while we're at it. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
488 this_module.builder_registry.register(obj) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
489 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
490 class ParserRejectedMarkup(Exception): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
491 """An Exception to be raised when the underlying parser simply |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
492 refuses to parse the given markup. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
493 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
494 def __init__(self, message_or_exception): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
495 """Explain why the parser rejected the given markup, either |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
496 with a textual explanation or another exception. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
497 """ |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
498 if isinstance(message_or_exception, Exception): |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
499 e = message_or_exception |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
500 message_or_exception = "%s: %s" % (e.__class__.__name__, str(e)) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
501 super(ParserRejectedMarkup, self).__init__(message_or_exception) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
502 |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
503 # Builders are registered in reverse order of priority, so that custom |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
504 # builder registrations will take precedence. In general, we want lxml |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
505 # to take precedence over html5lib, because it's faster. And we only |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
506 # want to use HTMLParser as a last resort. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
507 from . import _htmlparser |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
508 register_treebuilders_from(_htmlparser) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
509 try: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
510 from . import _html5lib |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
511 register_treebuilders_from(_html5lib) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
512 except ImportError: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
513 # They don't have html5lib installed. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
514 pass |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
515 try: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
516 from . import _lxml |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
517 register_treebuilders_from(_lxml) |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
518 except ImportError: |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
519 # They don't have lxml installed. |
d30785e31577
"planemo upload commit 6eee67778febed82ddd413c3ca40b3183a3898f1"
guerler
parents:
diff
changeset
|
520 pass |