app.py

import os 
import wget
import sys
import bs4
import json
import pandas as pd
from huggingface_hub import InferenceClient
import urllib.request
import gradio as gr

def get_menu():
    fp = urllib.request.urlopen("https://www.sw-ka.de/en/hochschulgastronomie/speiseplan/mensa_adenauerring/")
    mybytes = fp.read()

    html_content = mybytes.decode("utf8")

    #html_content = "".join(open('index.html',mode='r',encoding='utf-8').readlines())
    # Parse the HTML content

    # Parse the HTML using BeautifulSoup
    soup = bs4.BeautifulSoup(html_content, 'html.parser')

    canteen_div = soup.find('div', id='canteen_day_1')
    # Find all tables within the canteen_div
    tables = canteen_div.find_all('table')

    foods = []
    prices = []
    nutri = []
    line_names = []



    cnt = 0
    canteen_div = soup.find('div', id='canteen_day_1')
    # Find all tables within the canteen_div
    tables = canteen_div.find_all('table')
    # Iterate over each table
    for table in tables:
        # Extract food name
    # Find all table rows with a class starting with "mt-"
        menu_items = table.find_all('tr', class_=lambda class_name: class_name and class_name.startswith('mt-'))

        # Iterate through each menu item
        for item in menu_items:
            food_name = item.find('span', class_='bg').text.strip()
            
            # Extract price
            price = item.find('span', class_='bgp price_1').text.strip()
            
            # Extract nutritional information
            nutritional_info = {}
            nutritional_data = item.find('div', class_='nutrition_facts')
            if nutritional_data:
                for element in nutritional_data.find_all('div', class_=['energie', 'proteine', 'kohlenhydrate', 'zucker', 'fett', 'gesaettigt', 'salz']):
                    key = element.find('div').text.strip()
                    value = element.find_all('div')[1].text.strip()
                    nutritional_info[key] = value
            
            # Print extracted information

            #print(f"\nFood Name: {food_name}")
            foods.append(food_name)
            prices.append(price)
            nutri.append(json.dumps(nutritional_info, indent=4))
            #print(f"Price: {price}")
            if nutritional_info:
                #print("Nutritional Information:")
                for key, value in nutritional_info.items():
                    pass
                    #print(f"- {key}: {value}")
            else:
                pass
                #print("No nutritional information available.")
            cnt+=1
        break
        # Iterate over each row
        # Find all rows (tr) with class 'mensatype_rows'
        #rows = table.find_all('tr', class_='mensatype_rows')
    # Find all menu items within the table

    # Find all rows with class 'mensatype_rows'
    canteen_div = soup.find('div', id='canteen_day_1')
    # Find all tables within the canteen_div
    tables = canteen_div.find_all('table')


    # Iterate over each table
    for table in tables:
        # Iterate over each row
        # Find all rows (tr) with class 'mensatype_rows'
        rows = table.find_all('tr', class_='mensatype_rows')
        
        # Iterate over each row
        for row in rows:
            # Extract the row name
            row_name = row.find('div').get_text(strip=True)
            menu_titles = row.find_all('td', class_='menu-title')
            
            # Iterate over each food item
            for menu_title in menu_titles:
                line_names.append(row_name)

    menu = ""
    df = pd.DataFrame(zip(line_names,foods,prices,nutri),columns=['line','food','price','nutri'])
    #df = df[~df['line'].str.contains("Abendessen")]
    #df = df[~df['line'].str.contains("pizza")]
    #df = df[~df['line'].str.contains("werk")]
    df_line = df.groupby('line', sort=False)
    for line, df_group in df_line:
        menu+= "Line Name: " + line + "\n"
        for idx,row in df_group.iterrows():
            menu+=row['food'] + "\n"
            menu+=row['price'] + "\n"
            #menu+=row['nutri'] + "\n"
    return menu

def reply_bot(message, history):
    client = InferenceClient(model="https://9347-141-3-25-29.ngrok-free.app")

    prompt = "<s>[INST] <<SYS>>\nYou are multilingual chat bot that helps deciding what to eat ina german canteen. In the canteen there are different lines with names. Based on the menu and question, you suggest the user which line they should go to. You respond really briefly and do not generate long responses\n<</SYS>>\n\nMenu:\n" + menu + "\n " + histroy + "\n" + message + " [/INST]"

    try:
        for token in client.text_generation(prompt=prompt, max_new_tokens=128, stream=True):
            yield token
    except:
        return "Clear History or ask FR to increase Context Window. Current capacity only 4k tokens"

gr.ChatInterface(reply_bot).launch()