Created
September 3, 2021 07:10
-
-
Save larryhou/f559f94558bacec81069fb988f3ddc51 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
from __future__ import print_function | |
import json | |
import lxml.etree as etree | |
def parse(item): # type: (etree.Element)->any | |
keys = list(item.keys()) | |
if len(item) == 0: | |
if len(keys) == 0: return item.text | |
return dict([(k, item.get(k)) for k in keys]) | |
else: | |
data = dict([(k, item.get(k)) for k in keys]) | |
for c in item: | |
t = c.tag # type: str | |
if t in data: | |
if isinstance(data[t], list): data[t].append(parse(c)) | |
else: data[t] = [data[t], parse(c)] | |
else: data[t] = parse(c) | |
return data | |
def main(): | |
import sys | |
for name in sys.argv[1:]: | |
data = etree.parse(open(name, 'r')).getroot() | |
print(json.dumps(parse(data), indent=4, ensure_ascii=False)) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment