Lista dagens luncher i Ebbepark

lunch.py

#!/usr/bin/env python3

import requests
from bs4 import BeautifulSoup
import re
from datetime import date


def strip_trailing_empty_lines(s: str) -> str:
    lines = s.splitlines()
    while lines and lines[-1].strip() == "":
        lines.pop()
    return "\n".join(lines)


def laluna():
    print("\n=============")
    print("La Luna")
    print("=============")

    base_url = "http://www.lalunat1.se"

    try:
        response = requests.get(base_url)
        response.raise_for_status()
    except requests.RequestException as e:
        print(f"Error fetching main page: {e}")
        return

    soup = BeautifulSoup(response.content, "html.parser")
    nav = soup.find(id="nav")

    if not nav:
        print("Could not find navigation section.")
        return

    lunch_links = nav.find_all("a", string="Lunch")
    lunch_text = ""

    for link in lunch_links:
        lunch_url = base_url + link["href"]

        try:
            lunch_response = requests.get(lunch_url)
            lunch_response.raise_for_status()
        except requests.RequestException as e:
            print(f"Error fetching lunch page: {e}")
            continue

        lunch_soup = BeautifulSoup(lunch_response.content, "html.parser")
        text_blocks = lunch_soup.find_all("div", class_="text_content")

        for block in text_blocks:
            for p in block.find_all("p"):
                for strong in p.find_all("strong"):
                    lunch_text += strong.get_text()
                    lunch_text += "\n"

    # Clean up string
    replacements = {
        u"\u00A0": " ",  # non-breaking space
        u"\u200B": " ",  # zero width space
    }

    for pattern, repl in replacements.items():
        lunch_text = lunch_text.replace(pattern, repl)

    # Collapse lines with misplaced line breaks
    lunch_text = re.sub(r"(\S)[ \t]*\n[ \t]*(\S)", r"\1 \2", lunch_text)
    lunch_text = re.sub(r"[ \t]{2,}", " ", lunch_text)
    lunch_text = re.sub(r"^[ ]+", "", lunch_text, flags=re.MULTILINE)

    # Normalize headers with a single newline after each day header
    day_headers = [
        "Måndag", "Tisdag", "Onsdag", "Torsdag", "Fredag",
        "Veckans sallad", "Veckans special", "Veckans vegetariska"
    ]

    for header in day_headers:
        lunch_text = re.sub(fr"{header}[\s:]*", f"{header}\n", lunch_text, flags=re.IGNORECASE)

    # Add new line after week number
    lunch_text = re.sub(r"(Vecka \d+)", r"\1\n", lunch_text, flags=re.IGNORECASE)


    # Insert a tab character before each non-day header line
    lunch_text = "".join([s for s in lunch_text.splitlines(True) if s.strip("\r\n")])
    lunch_text = re.sub(r"^(?!Måndag|Tisdag|Onsdag|Torsdag|Fredag|Veckans sallad|Veckans special|Veckans vegetariska|Vecka \d+)(.*)", r"\t\1", lunch_text, flags=re.MULTILINE)

    lunch_text = strip_trailing_empty_lines(lunch_text)
    print(lunch_text)


def get_lazlos_week_menu(week_tag):
    lunch_menu = week_tag.find_next(id=re.compile(r'^fdm-menu-\d+$'))
    
    if not lunch_menu:
        print("Could not find lunch menu on the page.")
        return

    days = lunch_menu.find_all("ul")

    for day in days:
        day_name_tag = day.find("h3")
        if day_name_tag:
            print(f"\n{day_name_tag.get_text(strip=True)}")
        
        food_items = day.find_all("li", class_="fdm-item")
        for item in food_items:
            food_title_tag = item.find("p", class_="fdm-item-title")
            if food_title_tag:
                print(f"\t{food_title_tag.get_text(strip=True)}")
            
            food_content_div = item.find("div", class_="fdm-item-content")
            if food_content_div:
                subtitles = food_content_div.find_all("p")
                for subtitle in subtitles:
                    subtitle_text = subtitle.get_text(strip=True)
                    if subtitle_text:
                        print(f"\t  {subtitle_text}")

def laszlos_krog():
    print("\n=============")
    print("Laszlos Krog")
    print("=============")

    url = "https://www.laszloskrog.se/ebbepark/"
    
    try:
        response = requests.get(url)
        response.raise_for_status()
    except requests.RequestException as e:
        print(f"Error fetching page: {e}")
        return

    soup = BeautifulSoup(response.content, "html.parser")
    week_tags = soup.find_all("p", class_="vecka")

    current_week_num = date.today().isocalendar().week

    for week_tag in week_tags:
        strong_tag = week_tag.find("strong")
        if not strong_tag:
            continue

        week_text = strong_tag.get_text(strip=True)
        match = re.match(r"VECKA\s+(\d+)", week_text, flags=re.IGNORECASE)

        if match:
            week_num = int(match.group(1))
            if week_num == current_week_num:
                get_lazlos_week_menu(week_tag)
                return  # Stop after finding the correct week

    print("Current week's menu not found.")


if __name__ == "__main__":
    laszlos_krog()
    laluna()