-
-
Save fbender/100a9bc3da9733fcb8c6274b51005c6e to your computer and use it in GitHub Desktop.
Convert Internet Explorer 'capture network traffic' XML to a HAR file (by @craigds, force-unicode-version).
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
#!/usr/bin/env python | |
""" | |
Converts Internet Explorer 'capture network traffic' XML to a HAR file. | |
Turns out that XML is just a HAR file anyways, but in XML form. So this | |
just converts it to JSON, and Bob's your uncle. | |
Requires Python 2.7+ and LXML. | |
""" | |
from __future__ import unicode_literals | |
import argparse | |
import json | |
from lxml import objectify | |
import sys | |
if sys.version_info > (3,): | |
str_type = str | |
else: | |
str_type = unicode | |
list_things = { | |
'pages', | |
'entries', | |
'cookies', | |
'queryString', | |
'headers', | |
} | |
def xml_to_dict(element): | |
if element.tag in list_things: | |
return [xml_to_dict(e) for e in element.getchildren()] | |
else: | |
if element.getchildren(): | |
return {e.tag: xml_to_dict(e) for e in element.getchildren()} | |
else: | |
return str_type(element.pyval) | |
def main(): | |
parser = argparse.ArgumentParser(description="Convert IE's crazy XML-HAR into a real HAR file") | |
parser.add_argument('infile', type=argparse.FileType('r', encoding='UTF-8'), default=sys.stdin) | |
parser.add_argument('outfile', type=argparse.FileType('w', encoding='UTF-8'), default=sys.stdout) | |
args = parser.parse_args() | |
tree = objectify.parse(args.infile) | |
root = tree.getroot() | |
d = {root.tag: xml_to_dict(root)} | |
json.dump(d, args.outfile, indent=2, sort_keys=True) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hmmm...
$ python --version
Python 2.7.10
$ pip show lxml
DEPRECATION: Python 2.7 will reach the end of its life on January 1st, 2020. Please upgrade your Python as Python 2.7 won't be maintained after that date. A future version of pip will drop support for Python 2.7.
Name: lxml
Version: 4.4.0