Add basic budget plan downloader

import requests

import re

from bs4 import BeautifulSoup

from pathlib import Path

from ..schwalbe.studienfachschaften import get_studienfachschaften

def parse_common_budget_plan_element(element):

    studienfachschaft_name = element.text.split("\n")[0].strip()

    plan_links = {a.text: a.attrs["href"] for a in element.find_all("a")}

    return studienfachschaft_name, plan_links

def is_common_budget_plan_element(element):

    return len(re.findall(r"\n", element.text)) == 1

def get_budget_plan_links():

    page = requests.get("https://www.stura.uni-heidelberg.de/finanzen/haushalt/")

    soup = BeautifulSoup(page.text, "html.parser")

    def is_budget_plans_box(element):

        return element.text.strip().startswith("Budgetpläne der Fachschaften")

    budget_plan_elements = soup.find(is_budget_plans_box).find("ul").find_all("li")

    return dict(

        parse_common_budget_plan_element(element)

        for element in budget_plan_elements

        if is_common_budget_plan_element(element)

    )

def get_budget_plan_links_by_studienfachschaft_uuid():

    studienfachschaften = get_studienfachschaften()

    budget_plan_links_by_studienfachschaft_name = get_budget_plan_links()

    result = {}

    for (

        studienfachschaft_name,

        budget_plan_links,

    ) in budget_plan_links_by_studienfachschaft_name.items():

        for studienfachschaft in studienfachschaften:

            if studienfachschaft.name == studienfachschaft_name:

                result[studienfachschaft.uuid] = budget_plan_links

                break

        else:

            print(studienfachschaft_name)  # TODO Handle error

    return result

def download_all_budget_plans():

    links = get_budget_plan_links_by_studienfachschaft_uuid()

    base_dir = Path("instance/budget_plans")

    for studienfachschaft_uuid, budget_plan_links in links.items():

        studienfachschaft_dir = base_dir / str(studienfachschaft_uuid)

        studienfachschaft_dir.mkdir(exist_ok=True, parents=True)

        for year, link in budget_plan_links.items():

            r = requests.get(link, stream=True)

            with open(studienfachschaft_dir / f"{year}.pdf", "wb") as f:

                for chunk in r.iter_content():

                    f.write(chunk)