Spaces:
Sleeping
Sleeping
| def EatEasy_excel_extract(url_input): | |
| import requests | |
| import json | |
| import pandas as pd | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urlparse | |
| import math | |
| from io import BytesIO | |
| payload1 = {'restId': '17902'} | |
| files = [] | |
| headers2 = { | |
| 'Content-Type': 'application/x-www-form-urlencoded', | |
| 'Cookie': 'eateasy-ae-website=lai3mvcb9hd99nnivbt0pn68ibfjsd6g' | |
| } | |
| headers = { | |
| 'Content-Type': 'application/x-www-form-urlencoded', | |
| } | |
| # url_input = input("Enter the restaurant URL: ") | |
| parsed_url = urlparse(url_input) | |
| restaurant_code = parsed_url.path.strip('/').split('/')[-1] | |
| url = "https://www.eateasy.ae/dubai/food/getFilteredMenus" | |
| data = { | |
| "restCode": restaurant_code | |
| } | |
| response = requests.post(url, data=data) | |
| menu_items_list = [] | |
| category_name_list = [] | |
| j = 0 | |
| if response.status_code == 200: | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| menu_item_boxes = soup.find_all('div', class_='menu-item-box') # Find all divs with class 'menu-item-box' | |
| for i, item_box in enumerate(menu_item_boxes): # Iterate over each menu item box | |
| img = item_box.find('img') # Find the img tag within the div | |
| if img: # Check if img tag exists | |
| image_url = img.get('data-image') # Get the value of 'data-image' attribute | |
| else: | |
| image_url = None # If image URL is not found | |
| menu_item_details = item_box.find('div', class_='menu-item-details') # Find menu-item-details div | |
| if menu_item_details: | |
| type_ = menu_item_details.find('p', class_='type').text.strip() | |
| name = menu_item_details.find('h5', class_='menu-food-title').text.strip() | |
| description = menu_item_details.find('p', itemprop='description').text.strip() | |
| price = menu_item_details.find('div', class_='menu-item-price').text.strip() | |
| else: | |
| # If menu-item-details not found, set defaults | |
| type_ = "" | |
| name = "" | |
| description = "" | |
| price = "" | |
| menu_list_options = item_box.find('a', class_='menu-list-options') # Find the menu-list-options anchor tag | |
| if menu_list_options: | |
| value = menu_list_options.get('value') # Get the value attribute | |
| else: | |
| value = None | |
| if type_ not in category_name_list: | |
| category_name_list.append(type_) | |
| j = j+1 | |
| Category_position = j | |
| else: | |
| Category_position = j | |
| menu_item = { | |
| "Category": type_, | |
| "Category_position": Category_position, | |
| "Item_name": name, | |
| "Item_position": i, | |
| "Image": image_url, | |
| "description": description, | |
| "price": price, | |
| "id": value, | |
| } | |
| menu_items_list.append(menu_item) # Append menu item before the request | |
| if value is not None: | |
| option_url = f"https://www.eateasy.ae/dubai/order/add_to_cart_v1/{value}/1/" | |
| option_response = requests.post(option_url, headers=headers2, data=payload1) | |
| if option_response.status_code == 200: | |
| try: | |
| json_data = json.loads(option_response.text) | |
| extracted_data = [] | |
| if 'arrResult' in json_data and 'arrFoodChoice' in json_data['arrResult']: | |
| for choice in json_data['arrResult']['arrFoodChoice']: | |
| extracted_data.append({ | |
| 'Option_group_name': choice['choice_name'], | |
| 'Option_name': choice['name'], | |
| 'Extra_price': choice['price'], | |
| 'Min': choice.get('mandatory', 0), | |
| 'Max': choice.get('max_choice', 1) | |
| }) | |
| grouped_data = {} | |
| for choice in extracted_data: | |
| group_name = choice['Option_group_name'] | |
| if group_name not in grouped_data: | |
| grouped_data[group_name] = { | |
| 'Option_group_name': group_name, | |
| 'Min': choice['Min'], | |
| 'Max': max(choice['Max'], '1'), | |
| } | |
| num_options = sum(key.startswith('Option ') for key in grouped_data[group_name]) | |
| option_index = num_options + 1 # Index for the new option | |
| grouped_data[group_name][f"Option {option_index} Name"] = choice['Option_name'] | |
| grouped_data[group_name][f"Option {option_index} Price"] = choice['Extra_price'] | |
| for group_data in grouped_data.values(): | |
| menu_items_list.append(group_data) | |
| except json.JSONDecodeError: | |
| print("JSON decoding error. Response content may not be in valid JSON format.") | |
| else: | |
| print(f"Failed to get data for item with value {value}. Status code: {option_response.status_code}") | |
| df = pd.DataFrame(menu_items_list) | |
| # Ensure 'Max' column exists before renaming or shifting | |
| if 'Max' in df.columns: | |
| max_column_index = df.columns.get_loc('Max') | |
| for i in range(max_column_index + 1, len(df.columns)): | |
| df.rename(columns={df.columns[i]: ''}, inplace=True) | |
| option_group_name_index = df.columns.get_loc('Option_group_name') | |
| for i in range(option_group_name_index, len(df.columns)): | |
| df.iloc[:, i] = df.iloc[:, i].shift(-1) | |
| df_cleaned = df.dropna(how='all') | |
| output = BytesIO() | |
| with pd.ExcelWriter(output, engine='openpyxl') as writer: | |
| df_cleaned.to_excel(writer, index=False, sheet_name='Menu') | |
| output.seek(0) | |
| return output, f"{restaurant_code}_menu.xlsx" | |
| # excel_file = f"{restaurant_code}_menu.xlsx" | |
| # df.to_excel(excel_file, index=False) | |
| # print(f"Menu items saved to {excel_file}") | |
| else: | |
| print(f"Failed to get menu items. Status code: {response.status_code}") | |
| return True | |