Created
November 20, 2014 09:43
-
-
Save willcalderbank/2067b669687b56e515c8 to your computer and use it in GitHub Desktop.
Convert xml to dict
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
from collections import defaultdict | |
import functools | |
from lxml import etree | |
def etree_to_dict(t, ns=None): | |
""" | |
http://stackoverflow.com/questions/2148119/how-to-convert-an-xml-string-to-a-dictionary-in-python | |
""" | |
def strip_ns(tag): | |
if ns: | |
return tag.replace('{%s}' % ns, '') | |
return tag | |
d = {strip_ns(t.tag): {} if t.attrib else None} | |
children = list(t) | |
if children: | |
dd = defaultdict(list) | |
for dc in map(functools.partial(etree_to_dict, ns=ns), children): | |
for k, v in dc.iteritems(): | |
dd[k].append(v) | |
d = {strip_ns(t.tag): {k:v[0] if len(v) == 1 else v for k, v in dd.iteritems()}} | |
if t.attrib: | |
d[strip_ns(t.tag)].update(('@' + k, v) for k, v in t.attrib.iteritems()) | |
if t.text: | |
text = t.text.strip() | |
if children or t.attrib: | |
if text: | |
d[strip_ns(t.tag)]['#text'] = text | |
else: | |
d[strip_ns(t.tag)] = text | |
return d |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment