Django URL 추출하기

from django.shortcuts import render, get_object_or_404, redirect
from django.http import HttpResponseRedirect, HttpResponse
from .models import Project, Category, Expense, Circle, Rectangle, Triangle, Tyre
from django.views.generic import CreateView
from django.utils.text import slugify
from .forms import ExpenseForm
import json
from django.shortcuts import render
import re
from urllib.parse import urlparse
from django.db.models import Avg, Min, Max




def extract_domains(request):
    # HTML 파일을 불러오기 (테스트를 위해 내부에 정의된 HTML 문자열 사용)
    with open('budget/templates/test.html', 'r', encoding='utf-8') as file:
        html_content = file.read()

    # 정규식을 사용하여 href 속성에 있는 URL 추출
    url_pattern = r'href="(https?://[^"]+)"'
    urls = re.findall(url_pattern, html_content)

    # URL에서 도메인만 추출
    domains = {urlparse(url).netloc for url in urls}

    # 알파벳 순서로 정렬
    sorted_domains = sorted(domains)

    # 정렬된 도메인을 템플릿으로 전달
    return render(request, 'domains_output.html', {'domains': sorted_domains})