U
|
¬ý°dK ã @ s$ d Z ddlmZ ddlZddlmZmZmZ ddlm Z ddl
|
m Z m Z m Z mZmZmZmZmZmZmZ ddlmZ ddlmZmZ dd lmZ dd
|
l m Z dd l m Z dd l m!Z! dd l"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( ddl)m*Z* e r
|
ddl+m,Z, ddl-m.Z. ddl/m0Z0 ee!d e!d d dG dd dZ1G dd de1Z2G dd de1Z3d d d d d d!d"d#Z4d$d%d&d'Z5d(d%d)d*Z6e j7fd+d,d-d.d.d/d0d1d2d d3d4d5d d d6d(d7d8d9Z8ee!d e!d d dd:dd;d;ddddd<d=ddd>de j7d?d+d,d-d.d.d/d0d1d2d d3d4d5d d d6d(d7d@dAZ9dS )Bz3
|
:mod:`pandas.io.xml` is a module for reading XML.
|
é )Ú annotationsN)ÚAnyÚCallableÚSequence)Úlib)
|
Ú TYPE_CHECKINGÚCompressionOptionsÚ ConvertersArgÚDtypeArgÚ DtypeBackendÚFilePathÚ ParseDatesArgÚ
|
ReadBufferÚStorageOptionsÚ
|
XMLParsers)Úimport_optional_dependency)ÚAbstractMethodErrorÚ ParserError)Údoc)Úcheck_dtype_backend)Ú is_list_like)Ú _shared_docs)Ú file_existsÚ
|
get_handleÚinfer_compressionÚ is_fsspec_urlÚis_urlÚstringify_path)Ú
|
TextParser)ÚElement)Úetree)Ú DataFrameÚstorage_optionsÚdecompression_optionsÚpath_or_buffer)r" r# c @ s e Zd ZdZddddddddd d
|
d d d dddddZddddZdddddZddd d d Zddd d Zddd!d"Z dd#d$d%d&Z
|
d'S )(Ú_XMLFrameParserab
|
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.
|
ú.FilePath | ReadBuffer[bytes] | ReadBuffer[str]Ústrúdict[str, str] | NoneÚboolúSequence[str] | NoneúDtypeArg | NoneúConvertersArg | NoneúParseDatesArg | Noneú
|
str | Noneú5FilePath | ReadBuffer[bytes] | ReadBuffer[str] | Noneúdict[str, list[str]] | Noner r ÚNone)r$ ÚxpathÚ
|
namespacesÚ
|
elems_onlyÚ
|
attrs_onlyÚnamesÚdtypeÚ
|
convertersÚ parse_datesÚencodingÚ
|
stylesheetÚ iterparseÚ compressionr" Úreturnc C s^ || _ || _|| _|| _|| _|| _|| _|| _| | _|
|
| _ | | _
|
| | _ d | _ | | _ || _d S ©N)r$ r2 r3 r4 r5 r6 r7 r8 r9 r: r; r< Zis_styler= r" )Úselfr$ r2 r3 r4 r5 r6 r7 r8 r9 r: r; r< r= r" © rA úDd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/io/xml.pyÚ__init__ s z_XMLFrameParser.__init__úlist[dict[str, str | None]]©r> c C s t | dS )z
|
Parse xml data.
|
|
This method will call the other internal methods to
|
validate xpath, names, parse and return specific nodes.
|
N©r ©r@ rA rA rB Ú
|
parse_data² s z_XMLFrameParser.parse_dataú list[Any])Úelemsr> c sÖ j rjrtdj rDjr4fdd|D }qdd |D }n>jrZdd |D }n(jrtfdd|D }ndd |D }dd |D }tt d d |D ¡ fd
|
d|D }jrÒfd d|D }|S ) a=
|
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.
|
z4Either element or attributes can be parsed not both.c sL g | ]D}|j r(|j ¡ s(|j|j ¡ ini d d t j| d¡D qS )c S s& i | ] \}}||j r |j ¡ nd qS r? ©ÚtextÚstrip©Ú.0ÚnmÚchrA rA rB Ú
|
<dictcomp>Ý s ÿ ú;_XMLFrameParser._parse_nodes.<locals>.<listcomp>.<dictcomp>Ú*)rL ÚisspaceÚtagrM Úzipr6 Úfindall©rO ÚelrG rA rB Ú
|
<listcomp>Ö s øÿÿþúz0_XMLFrameParser._parse_nodes.<locals>.<listcomp>c S s g | ]}d d | d¡D qS )c S s$ i | ] }|j |jr |j ¡ nd qS r? ©rV rL rM ©rO rQ rA rA rB rR æ s ÿ rS rT ©rX rY rA rA rB r[ å s üþc S s g | ]}d d |j ¡ D qS )c S s" i | ]\}}||r| ¡ nd qS r? )rM ©rO ÚkÚvrA rA rB rR ï s rS ©ÚattribÚitemsrY rA rA rB r[ î s ÿc
|
sP g | ]H}|j |jr,|j ¡ s,|j|j ¡ ini d d t j| d¡D qS )c S s& i | ] \}}||j r |j ¡ nd qS r? rK rN rA rA rB rR ý s ÿ rS rT )rc rL rU rV rM rW r6 rX rY rG rA rB r[ õ s õÿÿþùc S sH g | ]@}|j |jr,|j ¡ s,|j|j ¡ ini d d | d¡D qS )c S s$ i | ] }|j |jr |j ¡ nd qS r? r\ r] rA rA rB rR s ÿ rS rT )rc rL rU rV rM rX rY rA rA rB r[ s õÿÿþùc S s g | ]}d d | ¡ D qS )c S s, i | ]$\}}d |kr"| d ¡d n||qS )Ú}é )Úsplitr_ rA rA rB rR s rS )rd ©rO ÚdrA rA rB r[ s c S s g | ]}| ¡ D ]}|qqS rA ©Úkeys©rO ri r` rA rA rB r[ s
|
c s g | ] fd dD qS )c s& i | ] }|| ¡ kr | nd qS r? rj ©rO r` ©ri rA rB rR s rS rA ©rO rj rn rB r[ s c s g | ]}t t j| ¡ qS rA ©ÚdictrW r6 Úvaluesrh rG rA rB r[ s )r4 r5 Ú
|
ValueErrorr6 Úlistrq Úfromkeys)r@ rJ ÚdictsrA ©rk r@ rB Ú _parse_nodes¼ s:
|
ôûþ
|
ó óÿz _XMLFrameParser._parse_nodesr )r< r> c sì g }d}t jts*ttjj djrBttj ¡ nd}t j| slttj| dt
|
j ds¼t j t r´t j s´tj s´j d¡s´tj ddk r¼tdtj| ttj| k}|j d d
|
D ]¤\}}d |jkr|j d ¡d n|j}|d kr.||kr.i }|dk r.jrÞ|rÞtj| jD ]\} }
|
|| kr |jr||j ¡ nd} | | ¡ kr |
|
|kr | ||
|
< | |jkrX|j| | ¡ krX|
|
|krX|j| ||
|
< qXnPj| D ]D} || kr|jr|j ¡ nd|| < | |jkrè|j| || < qè|dkrê||krX|dk rX| |¡ d}| ¡ t
|
|drê| ¡ dk rê| ¡ dk rê| ¡ d= qjqê|g kr¤tdt t !dd |D ¡ fdd|D }jrèfdd|D }|S )a
|
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.
|
Nz" is not a valid type for iterparseÚ z+ is not a valid type for value in iterparseÚread©z<?xmlú<Úinferziterparse is designed for large XML files that are fully extracted on local disk and not as compressed files or online sources.)ÚstartÚend)Úeventsre rf r~ r Ú getpreviousr z+No result from selected items in iterparse.c S s g | ]}| ¡ D ]}|qqS rA rj rl rA rA rB r[ s
|
z4_XMLFrameParser._iterparse_nodes.<locals>.<listcomp>c s g | ] fd dD qS )c s& i | ] }|| ¡ kr | nd qS r? rj rm rn rA rB rR s z?_XMLFrameParser._iterparse_nodes.<locals>.<listcomp>.<dictcomp>rA ro rj rn rB r[ s c s g | ]}t t j| ¡ qS rA rp rh rG rA rB r[ s )"Ú
|
isinstancer< rq Ú TypeErrorÚtypeÚ__name__ÚnextÚiterrk r Úhasattrr$ r' r r Ú
|
startswithr r ÚlenÚsetrV rg r6 rW rL rM rr rc ÚappendÚclearr Z getparentrt ru ) r@ r< rv ÚrowZrow_nodeZiterparse_repeatsÚeventÚelemZ curr_elemÚcolrP Zelem_valrA rw rB Ú_iterparse_nodes" s ÿ ÿ
|
ÿþý
|
üûÿ ÿ"
|
|
|
|
|
|
|
|
ÿ
|
ÿ
|
z _XMLFrameParser._iterparse_nodesc C s t | dS )a&
|
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.
|
NrF rG rA rA rB Ú_validate_path s z _XMLFrameParser._validate_pathc C s t | dS )zþ
|
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.
|
NrF rG rA rA rB Ú_validate_names s z _XMLFrameParser._validate_nameszElement | etree._Element©Úraw_docr> c C s t | dS )z
|
Build tree from path_or_buffer.
|
|
This method will parse XML object into tree
|
either from string/bytes or file location.
|
NrF )r@ r rA rA rB Ú
|
_parse_doc§ s z_XMLFrameParser._parse_docN) r
Ú
|
__module__Ú __qualname__Ú__doc__rC rH rx r r r r rA rA rA rB r% 9 s S*!
|
ffr% c @ sJ e Zd ZdZddddZddddZd dd
|
d Zd d dddZdS )Ú_EtreeFrameParserz
|
Internal class to parse XML into DataFrames with the Python
|
standard library XML module: `xml.etree.ElementTree`.
|
rD rE c C sh ddl m} | jd k r td| jd kr>| | j¡| _| ¡ }| ¡ | jd krZ| |¡n|
|
|¡}|S )Nr ©r< zBTo use stylesheet, you need lxml installed and selected as parser.) Úxml.etree.ElementTreer< r; rs r r$ Úxml_docr r rx r ©r@ r< rJ Z xml_dictsrA rA rB rH ¹ s
|
ÿ
|
ÿ ýz _EtreeFrameParser.parse_datarI c C sº d}z| j j| j| jd}dd |D }dd |D }|dkrFt||dk r| jrd|g krdt|| jrz|i krzt||g kr|i krt|W n ttfk
|
r´ tdY nX |S ) z
|
Notes
|
-----
|
`etree` supports limited XPath. If user attempts a more complex
|
expression syntax error will raise.
|
úæxpath 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.©r3 c S s g | ]}| d ¡D ]}|qqS ©rT r^ ©rO rZ rQ rA rA rB r[ á s z4_EtreeFrameParser._validate_path.<locals>.<listcomp>c S s& i | ] }|j ¡ D ]\}}||qqS rA rb ©rO rZ r` ra rA rA rB rR â s
|
z4_EtreeFrameParser._validate_path.<locals>.<dictcomp>NzxYou have used an incorrect or unsupported XPath expression for etree library or you used an undeclared namespace prefix.) r rX r2 r3 rs r4 r5 ÚKeyErrorÚ SyntaxError©r@ ÚmsgrJ ÚchildrenÚattrsrA rA rB r Ï s( ÿ ÿ
|
z _EtreeFrameParser._validate_pathr1 c C s | j r| jr"| jtt| j }n&| jj| j| jd}|rD| d¡ng }t | j rnt
|
| j t
|
|k rt dnt t | j j dd S )Nr¡ rT ú7names does not match length of child elements in xpath.ú is not a valid type for names)r6 r< r r r Úfindr2 r3 rX r r rs r r r
)r@ r© ÚparentrA rA rB r ø s
|
ÿÿz!_EtreeFrameParser._validate_namesr& r r c C sZ ddl m}m} t|| j| j| jd}t| }|| jd}|||d}W 5 Q R X | ¡ S )Nr )Ú XMLParserÚparse©Úfilepath_or_bufferr: r= r" ©r: ©Úparser) r r¯ r° Úget_data_from_filepathr: r= r" Úpreprocess_dataÚgetroot)r@ r r¯ r° Ú handle_dataÚxml_dataÚ curr_parserÚdocumentrA rA rB r s ü
|
z _EtreeFrameParser._parse_docN)r
r r r rH r r r rA rA rA rB r ³ s
|
)r c @ sX e Zd ZdZddddZddddZd dd
|
d Zd d dddZddddZdS )Ú_LxmlFrameParserz
|
Internal class to parse XML into DataFrames with third-party
|
full-featured XML library, `lxml`, that supports
|
XPath 1.0 and XSLT 1.0.
|
rD rE c C st ddl m} | jdkrJ| | j¡| _| jrB| | j¡| _| ¡ | _| ¡ }| ¡ | jdkrf|
|
|¡n| |¡}|S )zå
|
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.
|
r r N) Ú
|
lxml.etreer< r r$ r r; Úxsl_docÚ_transform_docr r rx r r rA rA rB rH ) s
|
|
ÿ ýz_LxmlFrameParser.parse_datarI c C s d}| j j| j| jd}dd |D }dd |D }|g krDt||g kr| jrb|g krbt|| jrx|i krxt||g kr|i krt||S )Nr r¡ c S s g | ]}| d ¡D ]}|qqS r¢ )r2 r£ rA rA rB r[ Q s z3_LxmlFrameParser._validate_path.<locals>.<listcomp>c S s& i | ] }|j ¡ D ]\}}||qqS rA rb r¤ rA rA rB rR R s
|
z3_LxmlFrameParser._validate_path.<locals>.<dictcomp>)r r2 r3 rs r4 r5 r§ rA rA rB r F s ÿ z _LxmlFrameParser._validate_pathr1 c C sz | j rv| jr"| jtt| j }n| jj| jd | jd}t| j r`t| j t|k rvt dnt
|
t | j j dd S )Nz[1]/*r¡ r« r¬ ) r6 r< r r r r2 r3 r r rs r r r
)r@ r© rA rA rB r a s ÿ
|
ÿÿz _LxmlFrameParser._validate_namesr& zetree._Elementr c C s ddl m}m}m} t|| j| j| jd}t|V}|| jd}t |t
|
j rx| jd kr^t d|| ¡ | j¡|d}n |||d}W 5 Q R X |S )Nr )r¯ Ú
|
fromstringr° r± r³ z2Can not pass encoding None when input is StringIO.r´ )r¾ r¯ rÁ r° r¶ r: r= r" r· r ÚioÚStringIOr ÚgetvalueÚencode) r@ r r¯ rÁ r° r¹ rº r» r¼ rA rA rB r v s( ü
|
|
ÿ ÿz_LxmlFrameParser._parse_doczetree._XSLTResultTreec C s$ ddl m} || j}|| j}|S )zã
|
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.
|
r )ÚXSLT)r¾ rÆ r¿ r )r@ rÆ Z transformerZnew_docrA rA rB rÀ s
|
|
z _LxmlFrameParser._transform_docN) r
r r r rH r r r rÀ rA rA rA rB r½ " s !r½ z6FilePath | bytes | ReadBuffer[bytes] | ReadBuffer[str]r. r r z1str | bytes | ReadBuffer[bytes] | ReadBuffer[str])r² r: r= r" r> c C s t | tst| } t | tr| d¡st | trHt| sHt| sHt| rt| d|||d"}t |j
|
drr|j
|
¡ n|j
|
} W 5 Q R X | S )aG
|
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.
|
r{ Úr)r: r= r" rz ) r Úbytesr r' r r r r r r Úhandlerz )r² r: r= r" Z
|
handle_objrA rA rB r¶ § s6
|
ÿþüûúù û
|
ÿ ý r¶ zio.StringIO | io.BytesIOrE c C s. t | trt | ¡} nt | tr*t | ¡} | S )z÷
|
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.
|
)r r' r rà rÈ ÚBytesIO)ÚdatarA rA rB r· Ô s
|
|
|
|
r· r! c
|
K sr t t| }dd | D }z6t|fd|i|}| ¡ W 5 Q R £ W S Q R X W n tk
|
rl tdY nX dS )zí
|
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.
|
c S s g | ]}t | ¡ qS rA )rt rr rh rA rA rB r[ ð s z"_data_to_frame.<locals>.<listcomp>r6 zqXML document may be too complex for import. Try to flatten document and use distinct element and attribute names.N)r r r rz r )rË ÚkwargsÚtagsZnodesÚtprA rA rB Ú_data_to_frameæ s ÿrÏ r& r' r( r) r* r+ r, r- r r/ r0 z DtypeBackend | lib.NoDefault)r$ r2 r3 r4 r5 r6 r7 r8 r9 r: rµ r; r< r= r" Ú dtype_backendr> c K s |
|
dkrJt ddd}|dk r@t| ||||||||| | | | |}q~tdn4|
|
dkrvt| ||||||||| | | | |}ntd| ¡ }tf |||||d |S )
|
a
|
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.
|
Úlxmlz
|
lxml.etreeÚignore)ÚerrorsNz7lxml not found, please install or use the etree parser.r z,Values for parser can only be lxml or etree.)rË r7 r8 r9 rÐ )r r½ Ú ImportErrorr rs rH rÏ )r$ r2 r3 r4 r5 r6 r7 r8 r9 r: rµ r; r< r= r" rÐ rÌ rÑ ÚpZ
|
data_dictsrA rA rB Ú_parseý s` $ ò
|
òûúrÖ z./*Fzutf-8rÑ r} )r2 r3 r4 r5 r6 r7 r8 r9 r: rµ r; r< r= r" rÐ c C s0 t | t| ||||||||| |
|
| | | ||dS )a·"
|
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
|
-------
|
df
|
A DataFrame.
|
|
See Also
|
--------
|
read_json : Convert a JSON string to pandas object.
|
read_html : Read HTML tables into a list of DataFrame objects.
|
|
Notes
|
-----
|
This method is best designed to import shallow XML documents in
|
following format which is the ideal fit for the two-dimensions of a
|
``DataFrame`` (row by column). ::
|
|
<root>
|
<row>
|
<column1>data</column1>
|
<column2>data</column2>
|
<column3>data</column3>
|
...
|
</row>
|
<row>
|
...
|
</row>
|
...
|
</root>
|
|
As a file format, XML documents can be designed any way including
|
layout of elements and attributes as long as it conforms to W3C
|
specifications. Therefore, this method is a convenience handler for
|
a specific flatter design and not all possible XML structures.
|
|
However, for more complex XML documents, ``stylesheet`` allows you to
|
temporarily redesign original document with XSLT (a special purpose
|
language) for a flatter version for migration to a DataFrame.
|
|
This function will *always* return a single :class:`DataFrame` or raise
|
exceptions due to issues with XML document, ``xpath``, or other
|
parameters.
|
|
See the :ref:`read_xml documentation in the IO section of the docs
|
<io.read_xml>` for more information in using this method to parse XML
|
files to DataFrames.
|
|
Examples
|
--------
|
>>> xml = '''<?xml version='1.0' encoding='utf-8'?>
|
... <data xmlns="http://example.com">
|
... <row>
|
... <shape>square</shape>
|
... <degrees>360</degrees>
|
... <sides>4.0</sides>
|
... </row>
|
... <row>
|
... <shape>circle</shape>
|
... <degrees>360</degrees>
|
... <sides/>
|
... </row>
|
... <row>
|
... <shape>triangle</shape>
|
... <degrees>180</degrees>
|
... <sides>3.0</sides>
|
... </row>
|
... </data>'''
|
|
>>> df = pd.read_xml(xml)
|
>>> df
|
shape degrees sides
|
0 square 360 4.0
|
1 circle 360 NaN
|
2 triangle 180 3.0
|
|
>>> xml = '''<?xml version='1.0' encoding='utf-8'?>
|
... <data>
|
... <row shape="square" degrees="360" sides="4.0"/>
|
... <row shape="circle" degrees="360"/>
|
... <row shape="triangle" degrees="180" sides="3.0"/>
|
... </data>'''
|
|
>>> df = pd.read_xml(xml, xpath=".//row")
|
>>> df
|
shape degrees sides
|
0 square 360 4.0
|
1 circle 360 NaN
|
2 triangle 180 3.0
|
|
>>> xml = '''<?xml version='1.0' encoding='utf-8'?>
|
... <doc:data xmlns:doc="https://example.com">
|
... <doc:row>
|
... <doc:shape>square</doc:shape>
|
... <doc:degrees>360</doc:degrees>
|
... <doc:sides>4.0</doc:sides>
|
... </doc:row>
|
... <doc:row>
|
... <doc:shape>circle</doc:shape>
|
... <doc:degrees>360</doc:degrees>
|
... <doc:sides/>
|
... </doc:row>
|
... <doc:row>
|
... <doc:shape>triangle</doc:shape>
|
... <doc:degrees>180</doc:degrees>
|
... <doc:sides>3.0</doc:sides>
|
... </doc:row>
|
... </doc:data>'''
|
|
>>> df = pd.read_xml(xml,
|
... xpath="//doc:row",
|
... namespaces={{"doc": "https://example.com"}})
|
>>> df
|
shape degrees sides
|
0 square 360 4.0
|
1 circle 360 NaN
|
2 triangle 180 3.0
|
©r$ r2 r3 r4 r5 r6 r7 r8 r9 r: rµ r; r< r= r" rÐ )r rÖ r× rA rA rB Úread_xmlX s* ðrØ ):r Ú
|
__future__r r Útypingr r r Z pandas._libsr Zpandas._typingr r r r
|
r r r r r r Zpandas.compat._optionalr Z pandas.errorsr r Zpandas.util._decoratorsr Zpandas.util._validatorsr Zpandas.core.dtypes.commonr Zpandas.core.shared_docsr Zpandas.io.commonr r r r r r Zpandas.io.parsersr r r rÑ r Zpandasr! r% r r½ r¶ r· rÏ Z
|
no_defaultrÖ rØ rA rA rA rB Ú<module> sh 0
|
þ xo -'ð0[
|
þî
|
