47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
import requests
|
|
import xml.etree.ElementTree as ET
|
|
from base64 import b64encode
|
|
from server.backend.schemas.pydantic import settings
|
|
import pandas as pd
|
|
from server.backend.api.session import get_session
|
|
|
|
session = get_session({
|
|
"Accept": "application/xml",
|
|
})
|
|
|
|
|
|
def fetch_companies():
|
|
response = session.get(settings.URL_CONTRACTORS, timeout=10)
|
|
response.raise_for_status()
|
|
return response.text
|
|
|
|
def parse_companies(xml: str):
|
|
try:
|
|
NS = {
|
|
"atom": "http://www.w3.org/2005/Atom",
|
|
"m": "http://schemas.microsoft.com/ado/2007/08/dataservices/metadata",
|
|
"d": "http://schemas.microsoft.com/ado/2007/08/dataservices",
|
|
}
|
|
rows = []
|
|
# Парсинг XML-ответа
|
|
root = ET.fromstring(xml)
|
|
# Извлечение конкретных данных
|
|
for entry in root.findall('atom:entry', NS):
|
|
properties = entry.find('atom:content',NS).find(
|
|
'm:properties', NS)
|
|
rows.append({
|
|
'Ref_Key': properties.findtext('d:Ref_Key', default=None, namespaces=NS),
|
|
'Description': properties.findtext('d:Description', default=None, namespaces=NS),
|
|
'FullName': properties.findtext('d:НаименованиеПолное', default=None, namespaces=NS),
|
|
'INN': properties.findtext('d:ИНН', default=None, namespaces=NS),
|
|
'KPP': properties.findtext('d:КПП', default=None, namespaces=NS),
|
|
'DoC': properties.findtext('d:ДатаСоздания', default=None, namespaces=NS),
|
|
})
|
|
df = pd.DataFrame(rows)
|
|
return df
|
|
except ET.ParseError:
|
|
raise
|
|
def contractor():
|
|
xml_data = fetch_companies()
|
|
root = parse_companies(xml_data)
|
|
root.to_excel("./excel_files/contractors.xlsx") |