Spaces:
Running
Running
| def Talabat_Json_extract(url): | |
| import json | |
| import requests | |
| import json | |
| from bs4 import BeautifulSoup | |
| import pandas as pd | |
| from urllib.parse import urlparse | |
| from io import BytesIO | |
| def extract_choices(item_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: | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| choice_data = json.loads(soup.string.strip()) | |
| return choice_data | |
| else: | |
| print("Failed to retrieve choices for item ID:", item_id) | |
| return None | |
| # url = input("enter retro 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) | |
| 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'] | |
| items = [] | |
| for item in 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'] | |
| item_info = { | |
| 'category': original_section, | |
| 'category_postion': 1, | |
| 'item_name': name, | |
| 'item_position': 1, | |
| 'original_image': original_image, | |
| 'description': description, | |
| 'price': price, | |
| 'item_id': item_id, | |
| } | |
| if has_choices: | |
| option_groups_info = [] | |
| choice_data = extract_choices(item_id,restaurant_id) | |
| if choice_data: | |
| choice_for_item = choice_data["result"]['choiceForItem'][0] # Accessing the first element of the list | |
| choice_sections = choice_for_item['choiceSections'] | |
| for option_group in choice_sections: | |
| option_group_info = { | |
| 'option_group_name': option_group['nm'], | |
| 'min_quantity': option_group['mnq'], | |
| 'max_quantity': option_group['mxq'], | |
| 'option_group_names': [] | |
| } | |
| if 'ich' in option_group: | |
| option_group_names = option_group['ich'] | |
| for option_group_name in option_group_names: | |
| option_group_name_info = { | |
| 'option_name': option_group_name['nm'], | |
| 'option_price': option_group_name['pr'] | |
| } | |
| option_group_info['option_group_names'].append(option_group_name_info) | |
| option_groups_info.append(option_group_info) | |
| item_info['option_groups'] = option_groups_info | |
| items.append(item_info) | |
| # with open(f"{restaurant_name}.json", "w") as json_file: | |
| # json.dump(items, json_file, indent=4) | |
| json_content = json.dumps(items, indent=4) | |
| # Create BytesIO object to hold the JSON content | |
| output = BytesIO() | |
| output.write(json_content.encode('utf-8')) | |
| output.seek(0) | |
| return restaurant_name,output | |
| else: | |
| print("Script tag with id '__NEXT_DATA__' not found.") | |
| else: | |
| print("Failed to retrieve the webpage. Status code:", response.status_code) | |
| return True | |