Created
September 15, 2012 20:53
-
-
Save bancek/3729713 to your computer and use it in GitHub Desktop.
XML to JSON
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
from collections import OrderedDict | |
from lxml import objectify | |
def xml_to_py(el): | |
if len(set([x.tag for x in el.getchildren()])) == 1: | |
return [xml_to_py(x) for x in el.getchildren()] | |
if hasattr(el, 'pyval'): | |
return el.pyval | |
data = OrderedDict() | |
for key, value in el.attrib.items(): | |
data[key] = value | |
for child in el.getchildren(): | |
data[child.tag] = xml_to_py(child) | |
return data | |
xml = '''<?xml version="1.0" encoding="UTF-8" standalone="yes"?> | |
<movies> | |
<movie id="1"> | |
<title>Movie 1</title> | |
<shows> | |
<show id="11"> | |
<time>15:00:00</time> | |
</show> | |
<show id="12"> | |
<time>17:15:00</time> | |
</show> | |
</shows> | |
</movie> | |
<movie id="2"> | |
<title>Movie 2</title> | |
<shows> | |
<show id="21"> | |
<time>16:00:00</time> | |
</show> | |
<show id="22"> | |
<time>19:10:00</time> | |
</show> | |
</shows> | |
</movie> | |
</movies> | |
''' | |
py = xml_to_py(objectify.fromstring(xml)) | |
json = json.dumps(py) | |
assert json == """[{"id": "1", "title": "Movie 1", "shows": [["15:00:00"], ["17:15:00"]]}, \ | |
{"id": "2", "title": "Movie 2", "shows": [["16:00:00"], ["19:10:00"]]}]""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment