Générer un fil RSS sur base d'une page web

#!/usr/bin/env python

import argparse
from datetime import datetime
from urllib.parse import urljoin
from zoneinfo import ZoneInfo

import bs4
import requests
from feedgen.feed import FeedGenerator


class Lirtuel:
    base_url = "http://www.lirtuel.be/"
    categories = {
        "fiction": "F",
        "general": "FB",
        "particularites": "FY",
        "fantasy": "FM",
        "policier": "FF",
        "sf": "FL",
        "thriller": "FH",
        "historique": "FV",
        "horreur": "FK",
        "sciencessociales": "J",
        "nature": "WN",
        "sciences": "P",
    }

    def __init__(self, query):
        self.query = query

    def feed(self, filename):
        if self.query in self.categories:
            search_results = requests.get(
                urljoin(self.base_url, "/resources"),
                params={
                    "utf8": "%E2%9C%93",
                    "category": self.categories.get(self.query),
                    "sort_by": "created_at_desc",
                },
            )
        else:
            search_results = requests.get(
                urljoin(self.base_url, "/resources"),
                params={"utf8": "✓", "q": self.query},
            )
        self._request_url = search_results.url
        soup = bs4.BeautifulSoup(search_results.content, "html.parser")
        feed = self._gen_feed(soup.find_all(class_="list-details__item"))
        feed.atom_file(filename, pretty=True)

    def _gen_feed(self, entries):
        feed = FeedGenerator()
        feed.id(self._request_url)
        feed.title(f"Lirtuel Feed for {self.query}")
        feed.description(f"Lirtuel Feed for {self.query}")
        feed.link(href=self._request_url, rel="self")

        for entry in entries:
            date = datetime.now(tz=ZoneInfo("Europe/Brussels"))
            url = urljoin(self.base_url, entry.h3.a["href"])
            title = " ".join(entry.h3.a.text.split())
            author = entry.find(attrs={"class": "contributors"}).a.text

            e = feed.add_entry()
            e.id(url)
            e.link(href=url)
            e.title(f"{title} / {author}")
            e.pubDate(date)

        return feed


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Generating a RSS feed for a query on Lirtuel"
    )

    parser.add_argument(
        "-q",
        "--query",
        help="Specify the query to submit to Lirtuel",
        required=True,
    )
    parser.add_argument(
        "-o",
        "--output",
        help="Specifiy the filename where to output the RSS file.",
        required=False,
    )
    args = parser.parse_args()

    Lirtuel(query=args.query).feed(args.output)