3.12. Read XML
File paths works also with URLs
io.StringIO Converts
strto File-like objectpd.read_xml()
3.12.1. SetUp
>>> import pandas as pd
>>> from io import StringIO
>>>
>>> pd.set_option('display.width', 250)
>>> pd.set_option('display.max_columns', 20)
>>> pd.set_option('display.max_rows', 30)
3.12.2. Read XML
>>> DATA = """<?xml version="1.0"?>
... <catalog>
... <book id="bk101">
... <author>Gambardella, Matthew</author>
... <title>XML Developer's Guide</title>
... <genre>Computer</genre>
... <price>44.95</price>
... <publish_date>2000-10-01</publish_date>
... <description>An in-depth look at creating applications
... with XML.</description>
... </book>
... <book id="bk102">
... <author>Ralls, Kim</author>
... <title>Midnight Rain</title>
... <genre>Fantasy</genre>
... <price>5.95</price>
... <publish_date>2000-12-16</publish_date>
... <description>A former architect battles corporate zombies,
... an evil sorceress, and her own childhood to become queen
... of the world.</description>
... </book>
... <book id="bk103">
... <author>Corets, Eva</author>
... <title>Maeve Ascendant</title>
... <genre>Fantasy</genre>
... <price>5.95</price>
... <publish_date>2000-11-17</publish_date>
... <description>After the collapse of a nanotechnology
... society in England, the young survivors lay the
... foundation for a new society.</description>
... </book>
... </catalog>
... """
>>> data = StringIO(DATA)
>>>
>>> pd.read_xml(data)
id author title genre price publish_date description
0 bk101 Gambardella, Matthew XML Developer's Guide Computer 44.95 2000-10-01 An in-depth look at creating applications\n ...
1 bk102 Ralls, Kim Midnight Rain Fantasy 5.95 2000-12-16 A former architect battles corporate zombies,\...
2 bk103 Corets, Eva Maeve Ascendant Fantasy 5.95 2000-11-17 After the collapse of a nanotechnology\n ...
3.12.3. XML and XSLT
>>> from lxml.etree import XML, XSLT, parse
>>> from io import StringIO
>>>
>>>
>>> TEMPLATE = """
... <html xsl:version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
... <table>
... <thead>
... <tr>
... <th>Id</th>
... <th>Author</th>
... <th>Title</th>
... <th>Genre</th>
... <th>Price</th>
... <th>Publish Date</th>
... <th>Description</th>
... </tr>
... </thead>
... <tbody>
...
... <xsl:for-each select="catalog/book">
... <tr>
... <td><xsl:value-of select="@id"/></td>
... <td><xsl:value-of select="author"/></td>
... <td><xsl:value-of select="title"/></td>
... <td><xsl:value-of select="genre"/></td>
... <td><xsl:value-of select="price"/></td>
... <td><xsl:value-of select="publish_date"/></td>
... <td><xsl:value-of select="description"/></td>
... </tr>
... </xsl:for-each>
...
... </tbody>
... </table>
... </html>
... """
>>>
>>> transform = XSLT(XML(TEMPLATE))
>>> data = parse(StringIO(DATA))
>>> html = StringIO(str(transform(data)))
>>> dfs = pd.read_html(html)
>>> result = dfs[0]
>>>
>>> result
Id Author Title Genre Price Publish Date Description
0 bk101 Gambardella, Matthew XML Developer's Guide Computer 44.95 2000-10-01 An in-depth look at creating applications wit...
1 bk102 Ralls, Kim Midnight Rain Fantasy 5.95 2000-12-16 A former architect battles corporate zombies, ...
2 bk103 Corets, Eva Maeve Ascendant Fantasy 5.95 2000-11-17 After the collapse of a nanotechnology societ...
>>>
>>> type(result) is pd.DataFrame
True
>>>
>>> len(result) > 0
True
>>>
>>> result.columns
Index(['Id', 'Author', 'Title', 'Genre', 'Price', 'Publish Date', 'Description'], dtype='str')
>>>
>>> result['Title']
0 XML Developer's Guide
1 Midnight Rain
2 Maeve Ascendant
Name: Title, dtype: str
3.12.4. Assignments
# FIXME: Rozbić na trzy zadania, jedno z read_xml(file), read_xml(StringIO), oraz inne z mean
# %% About
# - Name: Pandas Read XML
# - Difficulty: medium
# - Lines: 1
# - Minutes: 3
# %% License
# - Copyright 2025, Matt Harasymczuk <matt@python3.info>
# - This code can be used only for learning by humans
# - This code cannot be used for teaching others
# - This code cannot be used for teaching LLMs and AI algorithms
# - This code cannot be used in commercial or proprietary products
# - This code cannot be distributed in any form
# - This code cannot be changed in any form outside of training course
# - This code cannot have its license changed
# - If you use this code in your product, you must open-source it under GPLv2
# - Exception can be granted only by the author
# %% English
# 1. Read data from `DATA` as `pd.DataFrame`
# 2. Run doctests - all must succeed
# %% Polish
# 1. Wczytaj dane z `DATA` jako `pd.DataFrame`
# 2. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age email lastlogin is_active groups
# 0 Alice Apricot 30 alice@example.com 2000-01-01 True users;staff
# 1 Bob Blackthorn 31 bob@example.com 2000-01-02 True users;staff
# 2 Carol Corn 32 carol@example.com 2000-01-03 True users
# 3 Dave Durian 33 dave@example.org 2000-01-04 True users
# 4 Eve Elderberry 34 eve@example.org 2000-01-05 True users;staff;admins
# 5 Mallory Melon 15 mallory@example.net NaN False NaN
# %% Hints
# - `pip install --upgrade lxml`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age email lastlogin is_active groups
0 Alice Apricot 30 alice@example.com 2000-01-01 True users;staff
1 Bob Blackthorn 31 bob@example.com 2000-01-02 True users;staff
2 Carol Corn 32 carol@example.com 2000-01-03 True users
3 Dave Durian 33 dave@example.org 2000-01-04 True users
4 Eve Elderberry 34 eve@example.org 2000-01-05 True users;staff;admins
5 Mallory Melon 15 mallory@example.net NaN False NaN
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
from io import StringIO
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
DATA = """<?xml version="1.0" encoding="UTF-8"?>
<users>
<user>
<firstname>Alice</firstname>
<lastname>Apricot</lastname>
<age>30</age>
<email>alice@example.com</email>
<lastlogin>2000-01-01</lastlogin>
<is_active>True</is_active>
<groups>users;staff</groups>
</user>
<user>
<firstname>Bob</firstname>
<lastname>Blackthorn</lastname>
<age>31</age>
<email>bob@example.com</email>
<lastlogin>2000-01-02</lastlogin>
<is_active>True</is_active>
<groups>users;staff</groups>
</user>
<user>
<firstname>Carol</firstname>
<lastname>Corn</lastname>
<age>32</age>
<email>carol@example.com</email>
<lastlogin>2000-01-03</lastlogin>
<is_active>True</is_active>
<groups>users</groups>
</user>
<user>
<firstname>Dave</firstname>
<lastname>Durian</lastname>
<age>33</age>
<email>dave@example.org</email>
<lastlogin>2000-01-04</lastlogin>
<is_active>True</is_active>
<groups>users</groups>
</user>
<user>
<firstname>Eve</firstname>
<lastname>Elderberry</lastname>
<age>34</age>
<email>eve@example.org</email>
<lastlogin>2000-01-05</lastlogin>
<is_active>True</is_active>
<groups>users;staff;admins</groups>
</user>
<user>
<firstname>Mallory</firstname>
<lastname>Melon</lastname>
<age>15</age>
<email>mallory@example.net</email>
<lastlogin></lastlogin>
<is_active>False</is_active>
<groups></groups>
</user>
</users>
"""
# %% Result
result = ...