Files
2026-06-09 23:10:17 +02:00

150 lines
4.2 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import random
import re
from html import unescape
from html.parser import HTMLParser
from urllib.parse import urljoin
from urllib.request import Request, urlopen
CHEFKOCH_TODAY_URL = "https://www.chefkoch.de/rezepte/was-koche-ich-heute/"
FALLBACK_RECIPES = [
{
"title": "Cremige Pasta mit Tomaten",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "ca. 25 Minuten",
},
{
"title": "Kartoffel-Brokkoli-Auflauf",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "vegetarisch",
},
{
"title": "Schnelle Reispfanne",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "einfach",
},
{
"title": "Wraps mit Hähnchen",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "schnell",
},
{
"title": "Gemüse-Curry",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "würzig",
},
{
"title": "Ofenkartoffeln mit Dip",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "günstig",
},
{
"title": "Gnocchi-Pfanne",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "15 Minuten",
},
{
"title": "Pizza-Toast",
"url": "https://www.chefkoch.de/",
"image_url": "",
"meta": "MVP-Klassiker",
},
]
class ChefkochTodayParser(HTMLParser):
def __init__(self):
super().__init__()
self.recipes = []
self._current_link = None
self._current_text = []
self._current_image_url = ""
def handle_starttag(self, tag, attrs):
attrs = dict(attrs)
if tag == "a":
href = attrs.get("href", "")
if re.search(r"/rezepte/\d+/.+\.html", href):
self._current_link = urljoin(CHEFKOCH_TODAY_URL, href)
self._current_text = []
self._current_image_url = ""
elif tag == "img" and self._current_link:
self._current_image_url = attrs.get("src") or attrs.get("data-src") or ""
def handle_data(self, data):
if self._current_link:
self._current_text.append(data)
def handle_endtag(self, tag):
if tag != "a" or not self._current_link:
return
title, meta = parse_recipe_text(" ".join(self._current_text))
if title and not any(recipe["url"] == self._current_link for recipe in self.recipes):
self.recipes.append(
{
"title": title,
"url": self._current_link,
"image_url": self._current_image_url,
"meta": meta,
}
)
self._current_link = None
self._current_text = []
self._current_image_url = ""
def parse_recipe_text(text):
text = unescape(re.sub(r"\s+", " ", text)).strip()
text = text.replace("rating_star", "").strip()
rating_match = re.match(r"(?P<rating>\d+[,.]\d)\s*/?\s*5?\s*\((?P<count>\d+)\)\s*(?P<title>.+)", text)
if rating_match:
rating = rating_match.group("rating")
count = rating_match.group("count")
title = clean_recipe_title(rating_match.group("title"))
return title, f"{rating}/5 ({count})"
return clean_recipe_title(text), ""
def clean_recipe_title(title):
title = re.sub(r"\s+von\s+essen\s*&\s*trinken.*$", "", title, flags=re.IGNORECASE)
title = re.sub(r"[^\w\sÄÖÜäöüß.,&'’:/()\-]", "", title)
return re.sub(r"\s+", " ", title).strip()
def fetch_chefkoch_today_recipes():
cache_buster = random.randint(100000, 999999)
request = Request(
f"{CHEFKOCH_TODAY_URL}?rf={cache_buster}",
headers={
"User-Agent": "Mozilla/5.0 (compatible; RezeptFinder/1.0)",
"Cache-Control": "no-cache",
},
)
with urlopen(request, timeout=8) as response:
html = response.read().decode("utf-8", errors="replace")
parser = ChefkochTodayParser()
parser.feed(html)
return parser.recipes[:8]
def get_recipes():
try:
recipes = fetch_chefkoch_today_recipes()
except Exception:
return FALLBACK_RECIPES
return recipes or FALLBACK_RECIPES