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
|
"""Integration code for CSS selectors using `Soup Sieve <https://facelessuser.github.io/soupsieve/>`_ (pypi: ``soupsieve``).
Acquire a `CSS` object through the `element.Tag.css` attribute of
the starting point of your CSS selector, or (if you want to run a
selector against the entire document) of the `BeautifulSoup` object
itself.
The main advantage of doing this instead of using ``soupsieve``
functions is that you don't need to keep passing the `element.Tag` to be
selected against, since the `CSS` object is permanently scoped to that
`element.Tag`.
"""
from __future__ import annotations
from types import ModuleType
from typing import (
Any,
cast,
Iterable,
Iterator,
Optional,
TYPE_CHECKING,
)
import warnings
from bs4._typing import _NamespaceMapping
if TYPE_CHECKING:
from soupsieve import SoupSieve
from bs4 import element
from bs4.element import ResultSet, Tag
soupsieve: Optional[ModuleType]
try:
import soupsieve
except ImportError:
soupsieve = None
warnings.warn(
"The soupsieve package is not installed. CSS selectors cannot be used."
)
class CSS(object):
"""A proxy object against the ``soupsieve`` library, to simplify its
CSS selector API.
You don't need to instantiate this class yourself; instead, use
`element.Tag.css`.
:param tag: All CSS selectors run by this object will use this as
their starting point.
:param api: An optional drop-in replacement for the ``soupsieve`` module,
intended for use in unit tests.
"""
def __init__(self, tag: element.Tag, api: Optional[ModuleType] = None):
if api is None:
api = soupsieve
if api is None:
raise NotImplementedError(
"Cannot execute CSS selectors because the soupsieve package is not installed."
)
self.api = api
self.tag = tag
def escape(self, ident: str) -> str:
"""Escape a CSS identifier.
This is a simple wrapper around `soupsieve.escape() <https://facelessuser.github.io/soupsieve/api/#soupsieveescape>`_. See the
documentation for that function for more information.
"""
if soupsieve is None:
raise NotImplementedError(
"Cannot escape CSS identifiers because the soupsieve package is not installed."
)
return cast(str, self.api.escape(ident))
def _ns(
self, ns: Optional[_NamespaceMapping], select: str
) -> Optional[_NamespaceMapping]:
"""Normalize a dictionary of namespaces."""
if not isinstance(select, self.api.SoupSieve) and ns is None:
# If the selector is a precompiled pattern, it already has
# a namespace context compiled in, which cannot be
# replaced.
ns = self.tag._namespaces
return ns
def _rs(self, results: Iterable[Tag]) -> ResultSet[Tag]:
"""Normalize a list of results to a py:class:`ResultSet`.
A py:class:`ResultSet` is more consistent with the rest of
Beautiful Soup's API, and :py:meth:`ResultSet.__getattr__` has
a helpful error message if you try to treat a list of results
as a single result (a common mistake).
"""
# Import here to avoid circular import
from bs4 import ResultSet
return ResultSet(None, results)
def compile(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
flags: int = 0,
**kwargs: Any,
) -> SoupSieve:
"""Pre-compile a selector and return the compiled object.
:param selector: A CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will use the prefixes it encountered while
parsing the document.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.compile() <https://facelessuser.github.io/soupsieve/api/#soupsievecompile>`_ method.
:param kwargs: Keyword arguments to be passed into Soup Sieve's
`soupsieve.compile() <https://facelessuser.github.io/soupsieve/api/#soupsievecompile>`_ method.
:return: A precompiled selector object.
:rtype: soupsieve.SoupSieve
"""
return self.api.compile(select, self._ns(namespaces, select), flags, **kwargs)
def select_one(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
flags: int = 0,
**kwargs: Any,
) -> element.Tag | None:
"""Perform a CSS selection operation on the current Tag and return the
first result, if any.
This uses the Soup Sieve library. For more information, see
that library's documentation for the `soupsieve.select_one() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect_one>`_ method.
:param selector: A CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will use the prefixes it encountered while
parsing the document.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.select_one() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect_one>`_ method.
:param kwargs: Keyword arguments to be passed into Soup Sieve's
`soupsieve.select_one() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect_one>`_ method.
"""
return self.api.select_one(
select, self.tag, self._ns(namespaces, select), flags, **kwargs
)
def select(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
limit: int = 0,
flags: int = 0,
**kwargs: Any,
) -> ResultSet[element.Tag]:
"""Perform a CSS selection operation on the current `element.Tag`.
This uses the Soup Sieve library. For more information, see
that library's documentation for the `soupsieve.select() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect>`_ method.
:param selector: A CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will pass in the prefixes it encountered while
parsing the document.
:param limit: After finding this number of results, stop looking.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.select() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect>`_ method.
:param kwargs: Keyword arguments to be passed into Soup Sieve's
`soupsieve.select() <https://facelessuser.github.io/soupsieve/api/#soupsieveselect>`_ method.
"""
if limit is None:
limit = 0
return self._rs(
self.api.select(
select, self.tag, self._ns(namespaces, select), limit, flags, **kwargs
)
)
def iselect(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
limit: int = 0,
flags: int = 0,
**kwargs: Any,
) -> Iterator[element.Tag]:
"""Perform a CSS selection operation on the current `element.Tag`.
This uses the Soup Sieve library. For more information, see
that library's documentation for the `soupsieve.iselect()
<https://facelessuser.github.io/soupsieve/api/#soupsieveiselect>`_
method. It is the same as select(), but it returns a generator
instead of a list.
:param selector: A string containing a CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will pass in the prefixes it encountered while
parsing the document.
:param limit: After finding this number of results, stop looking.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.iselect() <https://facelessuser.github.io/soupsieve/api/#soupsieveiselect>`_ method.
:param kwargs: Keyword arguments to be passed into Soup Sieve's
`soupsieve.iselect() <https://facelessuser.github.io/soupsieve/api/#soupsieveiselect>`_ method.
"""
return self.api.iselect(
select, self.tag, self._ns(namespaces, select), limit, flags, **kwargs
)
def closest(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
flags: int = 0,
**kwargs: Any,
) -> Optional[element.Tag]:
"""Find the `element.Tag` closest to this one that matches the given selector.
This uses the Soup Sieve library. For more information, see
that library's documentation for the `soupsieve.closest()
<https://facelessuser.github.io/soupsieve/api/#soupsieveclosest>`_
method.
:param selector: A string containing a CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will pass in the prefixes it encountered while
parsing the document.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.closest() <https://facelessuser.github.io/soupsieve/api/#soupsieveclosest>`_ method.
:param kwargs: Keyword arguments to be passed into Soup Sieve's
`soupsieve.closest() <https://facelessuser.github.io/soupsieve/api/#soupsieveclosest>`_ method.
"""
return self.api.closest(
select, self.tag, self._ns(namespaces, select), flags, **kwargs
)
def match(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
flags: int = 0,
**kwargs: Any,
) -> bool:
"""Check whether or not this `element.Tag` matches the given CSS selector.
This uses the Soup Sieve library. For more information, see
that library's documentation for the `soupsieve.match()
<https://facelessuser.github.io/soupsieve/api/#soupsievematch>`_
method.
:param: a CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will pass in the prefixes it encountered while
parsing the document.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.match()
<https://facelessuser.github.io/soupsieve/api/#soupsievematch>`_
method.
:param kwargs: Keyword arguments to be passed into SoupSieve's
`soupsieve.match()
<https://facelessuser.github.io/soupsieve/api/#soupsievematch>`_
method.
"""
return cast(
bool,
self.api.match(
select, self.tag, self._ns(namespaces, select), flags, **kwargs
),
)
def filter(
self,
select: str,
namespaces: Optional[_NamespaceMapping] = None,
flags: int = 0,
**kwargs: Any,
) -> ResultSet[element.Tag]:
"""Filter this `element.Tag`'s direct children based on the given CSS selector.
This uses the Soup Sieve library. It works the same way as
passing a `element.Tag` into that library's `soupsieve.filter()
<https://facelessuser.github.io/soupsieve/api/#soupsievefilter>`_
method. For more information, see the documentation for
`soupsieve.filter()
<https://facelessuser.github.io/soupsieve/api/#soupsievefilter>`_.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will pass in the prefixes it encountered while
parsing the document.
:param flags: Flags to be passed into Soup Sieve's
`soupsieve.filter()
<https://facelessuser.github.io/soupsieve/api/#soupsievefilter>`_
method.
:param kwargs: Keyword arguments to be passed into SoupSieve's
`soupsieve.filter()
<https://facelessuser.github.io/soupsieve/api/#soupsievefilter>`_
method.
"""
return self._rs(
self.api.filter(
select, self.tag, self._ns(namespaces, select), flags, **kwargs
)
)
|