blob: 581c6ea31acdb298bd617c59e6875390fd60012f (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
import requests
import hashlib
import xml.etree.ElementTree as ET
def xml_to_dict(xml_data: str) -> dict:
# Parse the XML data
root = ET.fromstring(xml_data)
# Function to remove namespace from the tag name
def remove_namespace(tag):
return tag.split('}')[-1] # Splits on '}' and returns the last part, the actual tag name without namespace
# Function to recursively convert XML elements to a dictionary
def elem_to_dict(elem):
tag = remove_namespace(elem.tag)
elem_dict = {tag: {}}
# If the element has attributes, add them to the dictionary
elem_dict[tag].update({'@' + remove_namespace(k): v for k, v in elem.attrib.items()})
# Handle the element's text content, if present and not just whitespace
text = elem.text.strip() if elem.text and elem.text.strip() else None
if text:
elem_dict[tag]['#text'] = text
# Process child elements
for child in elem:
child_dict = elem_to_dict(child)
child_tag = remove_namespace(child.tag)
if child_tag not in elem_dict[tag]:
elem_dict[tag][child_tag] = []
elem_dict[tag][child_tag].append(child_dict[child_tag])
# Simplify structure if there's only text or no children and no attributes
if len(elem_dict[tag]) == 1 and '#text' in elem_dict[tag]:
return {tag: elem_dict[tag]['#text']}
elif not elem_dict[tag]:
return {tag: ''}
return elem_dict
# Convert the root element to dictionary
return elem_to_dict(root)
def sha256_hex(input_string: str) -> str:
return hashlib.sha256(input_string.encode()).hexdigest()
|
