Spaces:
Sleeping
Sleeping
| def Talabat_excel_extract(url): | |
| import requests | |
| import json | |
| import pandas as pd | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urlparse | |
| from io import BytesIO | |
| def extract_choices(item_id, restaurant_id): | |
| choice_url = f"https://www.talabat.com/nextMenuApi/v2/branches/{restaurant_id}/menu/{item_id}/choices" | |
| response = requests.get(choice_url, headers=headers) | |
| if response.status_code == 200: | |
| choice_data = response.json() | |
| return choice_data | |
| else: | |
| print("Failed to retrieve choices for item ID:", item_id) | |
| return None | |
| # url = input("Enter restaurant URL: ") | |
| parsed_url = urlparse(url) | |
| path_segments = parsed_url.path.split('/') | |
| restaurant_id = path_segments[-2] | |
| restaurant_name = path_segments[-1] | |
| headers = { | |
| 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3' | |
| } | |
| response = requests.get(url, headers=headers) | |
| j = 0 | |
| category_name_list = [] | |
| if response.status_code == 200: | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| script_tag = soup.find('script', id='__NEXT_DATA__') | |
| if script_tag: | |
| json_content = json.loads(script_tag.string.strip()) | |
| menu_data = json_content['props']['pageProps']['initialMenuState']['menuData']['items'] | |
| menu_items_list = [] | |
| for i,item in enumerate(menu_data): | |
| item_id = item['id'] | |
| name = item['name'] | |
| description = item['description'] | |
| price = item['price'] | |
| original_image = item['originalImage'] | |
| original_section = item['originalSection'] | |
| has_choices = item['hasChoices'] | |
| if original_section not in category_name_list: | |
| category_name_list.append(original_section) | |
| j = j+1 | |
| Category_position = j | |
| else: | |
| Category_position = j | |
| menu_item = { | |
| "Category": original_section, | |
| "Category_position": Category_position, | |
| "Item_name": name, | |
| "Item_position": i+1, | |
| "Image": original_image, | |
| "description": description, | |
| "price": price, | |
| "id": item_id | |
| } | |
| menu_items_list.append(menu_item) | |
| if has_choices: | |
| choice_data = extract_choices(item_id, restaurant_id) | |
| if choice_data: | |
| choice_for_item = choice_data["result"].get('choiceForItem', [])[0] # Accessing the first element of the list if exists | |
| choice_sections = choice_for_item.get('choiceSections', []) | |
| grouped_data = {} | |
| for option_group in choice_sections: | |
| option_group_name = option_group.get('nm', '') | |
| min_quantity = option_group.get('mnq', '') | |
| max_quantity = option_group.get('mxq', '') | |
| options = option_group.get('ich', []) | |
| for option_index, option in enumerate(options, start=1): | |
| option_name = option.get('nm', '') | |
| option_price = option.get('pr', '') | |
| grouped_data.setdefault(option_group_name, { | |
| "Option_group_name": option_group_name, | |
| "Min_quantity": min_quantity, | |
| "Max_quantity": max_quantity | |
| }) | |
| grouped_data[option_group_name][f"Option_{option_index}_Name"] = option_name | |
| grouped_data[option_group_name][f"Option_{option_index}_Price"] = option_price | |
| menu_items_list.extend(grouped_data.values()) | |
| df = pd.DataFrame(menu_items_list) | |
| if 'Max_quantity' in df.columns: | |
| max_column_index = df.columns.get_loc('Max_quantity') | |
| 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') | |
| # excel_file = f"{restaurant_name}_menu.xlsx" | |
| # df.to_excel(excel_file, index=False) | |
| # print(f"Menu items saved to {excel_file}") | |
| excel_file = BytesIO() | |
| df_cleaned.to_excel(excel_file, index=False) | |
| excel_file.seek(0) # Move to the beginning of the BytesIO stream | |
| return excel_file, f"{restaurant_name}_menu.xlsx" | |
| else: | |
| print("Script tag with id '__NEXT_DATA__' not found.") | |
| else: | |
| print(f"Failed to get menu items. Status code: {response.status_code}") | |