-
-
Notifications
You must be signed in to change notification settings - Fork 17.4k
/
xml.py
1135 lines (934 loc) · 36.2 KB
/
xml.py
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
"""
:mod:`pandas.io.xml` is a module for reading XML.
"""
from __future__ import annotations
import io
from typing import (
Any,
Callable,
Sequence,
)
from pandas._libs import lib
from pandas._typing import (
TYPE_CHECKING,
CompressionOptions,
ConvertersArg,
DtypeArg,
DtypeBackend,
FilePath,
ParseDatesArg,
ReadBuffer,
StorageOptions,
XMLParsers,
)
from pandas.compat._optional import import_optional_dependency
from pandas.errors import (
AbstractMethodError,
ParserError,
)
from pandas.util._decorators import doc
from pandas.util._validators import check_dtype_backend
from pandas.core.dtypes.common import is_list_like
from pandas.core.shared_docs import _shared_docs
from pandas.io.common import (
file_exists,
get_handle,
infer_compression,
is_fsspec_url,
is_url,
stringify_path,
)
from pandas.io.parsers import TextParser
if TYPE_CHECKING:
from xml.etree.ElementTree import Element
from lxml import etree
from pandas import DataFrame
@doc(
storage_options=_shared_docs["storage_options"],
decompression_options=_shared_docs["decompression_options"] % "path_or_buffer",
)
class _XMLFrameParser:
"""
Internal subclass to parse XML into DataFrames.
Parameters
----------
path_or_buffer : a valid JSON str, path object or file-like object
Any valid string path is acceptable. The string could be a URL. Valid
URL schemes include http, ftp, s3, and file.
xpath : str or regex
The XPath expression to parse required set of nodes for
migration to `Data Frame`. `etree` supports limited XPath.
namespaces : dict
The namespaces defined in XML document (`xmlns:namespace='URI')
as dicts with key being namespace and value the URI.
elems_only : bool
Parse only the child elements at the specified `xpath`.
attrs_only : bool
Parse only the attributes at the specified `xpath`.
names : list
Column names for Data Frame of parsed XML data.
dtype : dict
Data type for data or columns. E.g. {{'a': np.float64,
'b': np.int32, 'c': 'Int64'}}
.. versionadded:: 1.5.0
converters : dict, optional
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels.
.. versionadded:: 1.5.0
parse_dates : bool or list of int or names or list of lists or dict
Converts either index or select columns to datetimes
.. versionadded:: 1.5.0
encoding : str
Encoding of xml object or document.
stylesheet : str or file-like
URL, file, file-like object, or a raw string containing XSLT,
`etree` does not support XSLT but retained for consistency.
iterparse : dict, optional
Dict with row element as key and list of descendant elements
and/or attributes as value to be retrieved in iterparsing of
XML document.
.. versionadded:: 1.5.0
{decompression_options}
.. versionchanged:: 1.4.0 Zstandard support.
{storage_options}
See also
--------
pandas.io.xml._EtreeFrameParser
pandas.io.xml._LxmlFrameParser
Notes
-----
To subclass this class effectively you must override the following methods:`
* :func:`parse_data`
* :func:`_parse_nodes`
* :func:`_iterparse_nodes`
* :func:`_parse_doc`
* :func:`_validate_names`
* :func:`_validate_path`
See each method's respective documentation for details on their
functionality.
"""
def __init__(
self,
path_or_buffer: FilePath | ReadBuffer[bytes] | ReadBuffer[str],
xpath: str,
namespaces: dict[str, str] | None,
elems_only: bool,
attrs_only: bool,
names: Sequence[str] | None,
dtype: DtypeArg | None,
converters: ConvertersArg | None,
parse_dates: ParseDatesArg | None,
encoding: str | None,
stylesheet: FilePath | ReadBuffer[bytes] | ReadBuffer[str] | None,
iterparse: dict[str, list[str]] | None,
compression: CompressionOptions,
storage_options: StorageOptions,
) -> None:
self.path_or_buffer = path_or_buffer
self.xpath = xpath
self.namespaces = namespaces
self.elems_only = elems_only
self.attrs_only = attrs_only
self.names = names
self.dtype = dtype
self.converters = converters
self.parse_dates = parse_dates
self.encoding = encoding
self.stylesheet = stylesheet
self.iterparse = iterparse
self.is_style = None
self.compression = compression
self.storage_options = storage_options
def parse_data(self) -> list[dict[str, str | None]]:
"""
Parse xml data.
This method will call the other internal methods to
validate xpath, names, parse and return specific nodes.
"""
raise AbstractMethodError(self)
def _parse_nodes(self, elems: list[Any]) -> list[dict[str, str | None]]:
"""
Parse xml nodes.
This method will parse the children and attributes of elements
in xpath, conditionally for only elements, only attributes
or both while optionally renaming node names.
Raises
------
ValueError
* If only elements and only attributes are specified.
Notes
-----
Namespace URIs will be removed from return node values. Also,
elements with missing children or attributes compared to siblings
will have optional keys filled with None values.
"""
dicts: list[dict[str, str | None]]
if self.elems_only and self.attrs_only:
raise ValueError("Either element or attributes can be parsed not both.")
if self.elems_only:
if self.names:
dicts = [
{
**(
{el.tag: el.text.strip()}
if el.text and not el.text.isspace()
else {}
),
**{
nm: ch.text.strip() if ch.text else None
for nm, ch in zip(self.names, el.findall("*"))
},
}
for el in elems
]
else:
dicts = [
{
ch.tag: ch.text.strip() if ch.text else None
for ch in el.findall("*")
}
for el in elems
]
elif self.attrs_only:
dicts = [
{k: v.strip() if v else None for k, v in el.attrib.items()}
for el in elems
]
else:
if self.names:
dicts = [
{
**el.attrib,
**(
{el.tag: el.text.strip()}
if el.text and not el.text.isspace()
else {}
),
**{
nm: ch.text.strip() if ch.text else None
for nm, ch in zip(self.names, el.findall("*"))
},
}
for el in elems
]
else:
dicts = [
{
**el.attrib,
**(
{el.tag: el.text.strip()}
if el.text and not el.text.isspace()
else {}
),
**{
ch.tag: ch.text.strip() if ch.text else None
for ch in el.findall("*")
},
}
for el in elems
]
dicts = [
{k.split("}")[1] if "}" in k else k: v for k, v in d.items()} for d in dicts
]
keys = list(dict.fromkeys([k for d in dicts for k in d.keys()]))
dicts = [{k: d[k] if k in d.keys() else None for k in keys} for d in dicts]
if self.names:
dicts = [dict(zip(self.names, d.values())) for d in dicts]
return dicts
def _iterparse_nodes(self, iterparse: Callable) -> list[dict[str, str | None]]:
"""
Iterparse xml nodes.
This method will read in local disk, decompressed XML files for elements
and underlying descendants using iterparse, a method to iterate through
an XML tree without holding entire XML tree in memory.
Raises
------
TypeError
* If `iterparse` is not a dict or its dict value is not list-like.
ParserError
* If `path_or_buffer` is not a physical file on disk or file-like object.
* If no data is returned from selected items in `iterparse`.
Notes
-----
Namespace URIs will be removed from return node values. Also,
elements with missing children or attributes in submitted list
will have optional keys filled with None values.
"""
dicts: list[dict[str, str | None]] = []
row: dict[str, str | None] | None = None
if not isinstance(self.iterparse, dict):
raise TypeError(
f"{type(self.iterparse).__name__} is not a valid type for iterparse"
)
row_node = next(iter(self.iterparse.keys())) if self.iterparse else ""
if not is_list_like(self.iterparse[row_node]):
raise TypeError(
f"{type(self.iterparse[row_node])} is not a valid type "
"for value in iterparse"
)
if (not hasattr(self.path_or_buffer, "read")) and (
not isinstance(self.path_or_buffer, str)
or is_url(self.path_or_buffer)
or is_fsspec_url(self.path_or_buffer)
or self.path_or_buffer.startswith(("<?xml", "<"))
or infer_compression(self.path_or_buffer, "infer") is not None
):
raise ParserError(
"iterparse is designed for large XML files that are fully extracted on "
"local disk and not as compressed files or online sources."
)
iterparse_repeats = len(self.iterparse[row_node]) != len(
set(self.iterparse[row_node])
)
for event, elem in iterparse(self.path_or_buffer, events=("start", "end")):
curr_elem = elem.tag.split("}")[1] if "}" in elem.tag else elem.tag
if event == "start":
if curr_elem == row_node:
row = {}
if row is not None:
if self.names and iterparse_repeats:
for col, nm in zip(self.iterparse[row_node], self.names):
if curr_elem == col:
elem_val = elem.text.strip() if elem.text else None
if elem_val not in row.values() and nm not in row:
row[nm] = elem_val
if col in elem.attrib:
if elem.attrib[col] not in row.values() and nm not in row:
row[nm] = elem.attrib[col]
else:
for col in self.iterparse[row_node]:
if curr_elem == col:
row[col] = elem.text.strip() if elem.text else None
if col in elem.attrib:
row[col] = elem.attrib[col]
if event == "end":
if curr_elem == row_node and row is not None:
dicts.append(row)
row = None
elem.clear()
if hasattr(elem, "getprevious"):
while (
elem.getprevious() is not None and elem.getparent() is not None
):
del elem.getparent()[0]
if dicts == []:
raise ParserError("No result from selected items in iterparse.")
keys = list(dict.fromkeys([k for d in dicts for k in d.keys()]))
dicts = [{k: d[k] if k in d.keys() else None for k in keys} for d in dicts]
if self.names:
dicts = [dict(zip(self.names, d.values())) for d in dicts]
return dicts
def _validate_path(self) -> list[Any]:
"""
Validate xpath.
This method checks for syntax, evaluation, or empty nodes return.
Raises
------
SyntaxError
* If xpah is not supported or issues with namespaces.
ValueError
* If xpah does not return any nodes.
"""
raise AbstractMethodError(self)
def _validate_names(self) -> None:
"""
Validate names.
This method will check if names is a list-like and aligns
with length of parse nodes.
Raises
------
ValueError
* If value is not a list and less then length of nodes.
"""
raise AbstractMethodError(self)
def _parse_doc(
self, raw_doc: FilePath | ReadBuffer[bytes] | ReadBuffer[str]
) -> Element | etree._Element:
"""
Build tree from path_or_buffer.
This method will parse XML object into tree
either from string/bytes or file location.
"""
raise AbstractMethodError(self)
class _EtreeFrameParser(_XMLFrameParser):
"""
Internal class to parse XML into DataFrames with the Python
standard library XML module: `xml.etree.ElementTree`.
"""
def parse_data(self) -> list[dict[str, str | None]]:
from xml.etree.ElementTree import iterparse
if self.stylesheet is not None:
raise ValueError(
"To use stylesheet, you need lxml installed and selected as parser."
)
if self.iterparse is None:
self.xml_doc = self._parse_doc(self.path_or_buffer)
elems = self._validate_path()
self._validate_names()
xml_dicts: list[dict[str, str | None]] = (
self._parse_nodes(elems)
if self.iterparse is None
else self._iterparse_nodes(iterparse)
)
return xml_dicts
def _validate_path(self) -> list[Any]:
"""
Notes
-----
`etree` supports limited XPath. If user attempts a more complex
expression syntax error will raise.
"""
msg = (
"xpath does not return any nodes or attributes. "
"Be sure to specify in `xpath` the parent nodes of "
"children and attributes to parse. "
"If document uses namespaces denoted with "
"xmlns, be sure to define namespaces and "
"use them in xpath."
)
try:
elems = self.xml_doc.findall(self.xpath, namespaces=self.namespaces)
children = [ch for el in elems for ch in el.findall("*")]
attrs = {k: v for el in elems for k, v in el.attrib.items()}
if elems is None:
raise ValueError(msg)
if elems is not None:
if self.elems_only and children == []:
raise ValueError(msg)
if self.attrs_only and attrs == {}:
raise ValueError(msg)
if children == [] and attrs == {}:
raise ValueError(msg)
except (KeyError, SyntaxError):
raise SyntaxError(
"You have used an incorrect or unsupported XPath "
"expression for etree library or you used an "
"undeclared namespace prefix."
)
return elems
def _validate_names(self) -> None:
children: list[Any]
if self.names:
if self.iterparse:
children = self.iterparse[next(iter(self.iterparse))]
else:
parent = self.xml_doc.find(self.xpath, namespaces=self.namespaces)
children = parent.findall("*") if parent else []
if is_list_like(self.names):
if len(self.names) < len(children):
raise ValueError(
"names does not match length of child elements in xpath."
)
else:
raise TypeError(
f"{type(self.names).__name__} is not a valid type for names"
)
def _parse_doc(
self, raw_doc: FilePath | ReadBuffer[bytes] | ReadBuffer[str]
) -> Element:
from xml.etree.ElementTree import (
XMLParser,
parse,
)
handle_data = get_data_from_filepath(
filepath_or_buffer=raw_doc,
encoding=self.encoding,
compression=self.compression,
storage_options=self.storage_options,
)
with preprocess_data(handle_data) as xml_data:
curr_parser = XMLParser(encoding=self.encoding)
document = parse(xml_data, parser=curr_parser)
return document.getroot()
class _LxmlFrameParser(_XMLFrameParser):
"""
Internal class to parse XML into DataFrames with third-party
full-featured XML library, `lxml`, that supports
XPath 1.0 and XSLT 1.0.
"""
def parse_data(self) -> list[dict[str, str | None]]:
"""
Parse xml data.
This method will call the other internal methods to
validate xpath, names, optionally parse and run XSLT,
and parse original or transformed XML and return specific nodes.
"""
from lxml.etree import iterparse
if self.iterparse is None:
self.xml_doc = self._parse_doc(self.path_or_buffer)
if self.stylesheet:
self.xsl_doc = self._parse_doc(self.stylesheet)
self.xml_doc = self._transform_doc()
elems = self._validate_path()
self._validate_names()
xml_dicts: list[dict[str, str | None]] = (
self._parse_nodes(elems)
if self.iterparse is None
else self._iterparse_nodes(iterparse)
)
return xml_dicts
def _validate_path(self) -> list[Any]:
msg = (
"xpath does not return any nodes or attributes. "
"Be sure to specify in `xpath` the parent nodes of "
"children and attributes to parse. "
"If document uses namespaces denoted with "
"xmlns, be sure to define namespaces and "
"use them in xpath."
)
elems = self.xml_doc.xpath(self.xpath, namespaces=self.namespaces)
children = [ch for el in elems for ch in el.xpath("*")]
attrs = {k: v for el in elems for k, v in el.attrib.items()}
if elems == []:
raise ValueError(msg)
if elems != []:
if self.elems_only and children == []:
raise ValueError(msg)
if self.attrs_only and attrs == {}:
raise ValueError(msg)
if children == [] and attrs == {}:
raise ValueError(msg)
return elems
def _validate_names(self) -> None:
children: list[Any]
if self.names:
if self.iterparse:
children = self.iterparse[next(iter(self.iterparse))]
else:
children = self.xml_doc.xpath(
self.xpath + "[1]/*", namespaces=self.namespaces
)
if is_list_like(self.names):
if len(self.names) < len(children):
raise ValueError(
"names does not match length of child elements in xpath."
)
else:
raise TypeError(
f"{type(self.names).__name__} is not a valid type for names"
)
def _parse_doc(
self, raw_doc: FilePath | ReadBuffer[bytes] | ReadBuffer[str]
) -> etree._Element:
from lxml.etree import (
XMLParser,
fromstring,
parse,
)
handle_data = get_data_from_filepath(
filepath_or_buffer=raw_doc,
encoding=self.encoding,
compression=self.compression,
storage_options=self.storage_options,
)
with preprocess_data(handle_data) as xml_data:
curr_parser = XMLParser(encoding=self.encoding)
if isinstance(xml_data, io.StringIO):
if self.encoding is None:
raise TypeError(
"Can not pass encoding None when input is StringIO."
)
document = fromstring(
xml_data.getvalue().encode(self.encoding), parser=curr_parser
)
else:
document = parse(xml_data, parser=curr_parser)
return document
def _transform_doc(self) -> etree._XSLTResultTree:
"""
Transform original tree using stylesheet.
This method will transform original xml using XSLT script into
am ideally flatter xml document for easier parsing and migration
to Data Frame.
"""
from lxml.etree import XSLT
transformer = XSLT(self.xsl_doc)
new_doc = transformer(self.xml_doc)
return new_doc
def get_data_from_filepath(
filepath_or_buffer: FilePath | bytes | ReadBuffer[bytes] | ReadBuffer[str],
encoding: str | None,
compression: CompressionOptions,
storage_options: StorageOptions,
) -> str | bytes | ReadBuffer[bytes] | ReadBuffer[str]:
"""
Extract raw XML data.
The method accepts three input types:
1. filepath (string-like)
2. file-like object (e.g. open file object, StringIO)
3. XML string or bytes
This method turns (1) into (2) to simplify the rest of the processing.
It returns input types (2) and (3) unchanged.
"""
if not isinstance(filepath_or_buffer, bytes):
filepath_or_buffer = stringify_path(filepath_or_buffer)
if (
isinstance(filepath_or_buffer, str)
and not filepath_or_buffer.startswith(("<?xml", "<"))
) and (
not isinstance(filepath_or_buffer, str)
or is_url(filepath_or_buffer)
or is_fsspec_url(filepath_or_buffer)
or file_exists(filepath_or_buffer)
):
with get_handle(
filepath_or_buffer,
"r",
encoding=encoding,
compression=compression,
storage_options=storage_options,
) as handle_obj:
filepath_or_buffer = (
handle_obj.handle.read()
if hasattr(handle_obj.handle, "read")
else handle_obj.handle
)
return filepath_or_buffer
def preprocess_data(data) -> io.StringIO | io.BytesIO:
"""
Convert extracted raw data.
This method will return underlying data of extracted XML content.
The data either has a `read` attribute (e.g. a file object or a
StringIO/BytesIO) or is a string or bytes that is an XML document.
"""
if isinstance(data, str):
data = io.StringIO(data)
elif isinstance(data, bytes):
data = io.BytesIO(data)
return data
def _data_to_frame(data, **kwargs) -> DataFrame:
"""
Convert parsed data to Data Frame.
This method will bind xml dictionary data of keys and values
into named columns of Data Frame using the built-in TextParser
class that build Data Frame and infers specific dtypes.
"""
tags = next(iter(data))
nodes = [list(d.values()) for d in data]
try:
with TextParser(nodes, names=tags, **kwargs) as tp:
return tp.read()
except ParserError:
raise ParserError(
"XML document may be too complex for import. "
"Try to flatten document and use distinct "
"element and attribute names."
)
def _parse(
path_or_buffer: FilePath | ReadBuffer[bytes] | ReadBuffer[str],
xpath: str,
namespaces: dict[str, str] | None,
elems_only: bool,
attrs_only: bool,
names: Sequence[str] | None,
dtype: DtypeArg | None,
converters: ConvertersArg | None,
parse_dates: ParseDatesArg | None,
encoding: str | None,
parser: XMLParsers,
stylesheet: FilePath | ReadBuffer[bytes] | ReadBuffer[str] | None,
iterparse: dict[str, list[str]] | None,
compression: CompressionOptions,
storage_options: StorageOptions,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
**kwargs,
) -> DataFrame:
"""
Call internal parsers.
This method will conditionally call internal parsers:
LxmlFrameParser and/or EtreeParser.
Raises
------
ImportError
* If lxml is not installed if selected as parser.
ValueError
* If parser is not lxml or etree.
"""
p: _EtreeFrameParser | _LxmlFrameParser
if parser == "lxml":
lxml = import_optional_dependency("lxml.etree", errors="ignore")
if lxml is not None:
p = _LxmlFrameParser(
path_or_buffer,
xpath,
namespaces,
elems_only,
attrs_only,
names,
dtype,
converters,
parse_dates,
encoding,
stylesheet,
iterparse,
compression,
storage_options,
)
else:
raise ImportError("lxml not found, please install or use the etree parser.")
elif parser == "etree":
p = _EtreeFrameParser(
path_or_buffer,
xpath,
namespaces,
elems_only,
attrs_only,
names,
dtype,
converters,
parse_dates,
encoding,
stylesheet,
iterparse,
compression,
storage_options,
)
else:
raise ValueError("Values for parser can only be lxml or etree.")
data_dicts = p.parse_data()
return _data_to_frame(
data=data_dicts,
dtype=dtype,
converters=converters,
parse_dates=parse_dates,
dtype_backend=dtype_backend,
**kwargs,
)
@doc(
storage_options=_shared_docs["storage_options"],
decompression_options=_shared_docs["decompression_options"] % "path_or_buffer",
)
def read_xml(
path_or_buffer: FilePath | ReadBuffer[bytes] | ReadBuffer[str],
*,
xpath: str = "./*",
namespaces: dict[str, str] | None = None,
elems_only: bool = False,
attrs_only: bool = False,
names: Sequence[str] | None = None,
dtype: DtypeArg | None = None,
converters: ConvertersArg | None = None,
parse_dates: ParseDatesArg | None = None,
# encoding can not be None for lxml and StringIO input
encoding: str | None = "utf-8",
parser: XMLParsers = "lxml",
stylesheet: FilePath | ReadBuffer[bytes] | ReadBuffer[str] | None = None,
iterparse: dict[str, list[str]] | None = None,
compression: CompressionOptions = "infer",
storage_options: StorageOptions = None,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
) -> DataFrame:
r"""
Read XML document into a ``DataFrame`` object.
.. versionadded:: 1.3.0
Parameters
----------
path_or_buffer : str, path object, or file-like object
String, path object (implementing ``os.PathLike[str]``), or file-like
object implementing a ``read()`` function. The string can be any valid XML
string or a path. The string can further be a URL. Valid URL schemes
include http, ftp, s3, and file.
xpath : str, optional, default './\*'
The XPath to parse required set of nodes for migration to DataFrame.
XPath should return a collection of elements and not a single
element. Note: The ``etree`` parser supports limited XPath
expressions. For more complex XPath, use ``lxml`` which requires
installation.
namespaces : dict, optional
The namespaces defined in XML document as dicts with key being
namespace prefix and value the URI. There is no need to include all
namespaces in XML, only the ones used in ``xpath`` expression.
Note: if XML document uses default namespace denoted as
`xmlns='<URI>'` without a prefix, you must assign any temporary
namespace prefix such as 'doc' to the URI in order to parse
underlying nodes and/or attributes. For example, ::
namespaces = {{"doc": "https://example.com"}}
elems_only : bool, optional, default False
Parse only the child elements at the specified ``xpath``. By default,
all child elements and non-empty text nodes are returned.
attrs_only : bool, optional, default False
Parse only the attributes at the specified ``xpath``.
By default, all attributes are returned.
names : list-like, optional
Column names for DataFrame of parsed XML data. Use this parameter to
rename original element names and distinguish same named elements and
attributes.
dtype : Type name or dict of column -> type, optional
Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32,
'c': 'Int64'}}
Use `str` or `object` together with suitable `na_values` settings
to preserve and not interpret dtype.
If converters are specified, they will be applied INSTEAD
of dtype conversion.
.. versionadded:: 1.5.0
converters : dict, optional
Dict of functions for converting values in certain columns. Keys can either
be integers or column labels.
.. versionadded:: 1.5.0
parse_dates : bool or list of int or names or list of lists or dict, default False
Identifiers to parse index or columns to datetime. The behavior is as follows:
* boolean. If True -> try parsing the index.
* list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3
each as a separate date column.
* list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as
a single date column.
* dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call
result 'foo'
.. versionadded:: 1.5.0
encoding : str, optional, default 'utf-8'
Encoding of XML document.
parser : {{'lxml','etree'}}, default 'lxml'
Parser module to use for retrieval of data. Only 'lxml' and
'etree' are supported. With 'lxml' more complex XPath searches
and ability to use XSLT stylesheet are supported.
stylesheet : str, path object or file-like object
A URL, file-like object, or a raw string containing an XSLT script.
This stylesheet should flatten complex, deeply nested XML documents
for easier parsing. To use this feature you must have ``lxml`` module
installed and specify 'lxml' as ``parser``. The ``xpath`` must
reference nodes of transformed XML document generated after XSLT
transformation and not the original XML document. Only XSLT 1.0
scripts and not later versions is currently supported.
iterparse : dict, optional
The nodes or attributes to retrieve in iterparsing of XML document
as a dict with key being the name of repeating element and value being
list of elements or attribute names that are descendants of the repeated
element. Note: If this option is used, it will replace ``xpath`` parsing
and unlike xpath, descendants do not need to relate to each other but can
exist any where in document under the repeating element. This memory-
efficient method should be used for very large XML files (500MB, 1GB, or 5GB+).
For example, ::
iterparse = {{"row_element": ["child_elem", "attr", "grandchild_elem"]}}
.. versionadded:: 1.5.0
{decompression_options}
.. versionchanged:: 1.4.0 Zstandard support.
{storage_options}
dtype_backend : {{"numpy_nullable", "pyarrow"}}, defaults to NumPy backed DataFrames
Which dtype_backend to use, e.g. whether a DataFrame should have NumPy
arrays, nullable dtypes are used for all dtypes that have a nullable
implementation when "numpy_nullable" is set, pyarrow is used for all
dtypes if "pyarrow" is set.
The dtype_backends are still experimential.
.. versionadded:: 2.0
Returns