# NOTE: In the case of code not running, you should first check the cookies link in each content

import requests
import time
from tqdm import tqdm
from src.utils.utils import load_json, save_json
import os
import argparse
import logging


URL_TEMPLATE = "https://www.foody.vn/vung-tau/{name}?ds=Restaurant&vt=row&st=1&c=7&page={page_num}&provinceId=223&categoryId={categorie_num}&append=true"

def parser():
    parser = argparse.ArgumentParser(description='Crawling Foody Vung Tau')
    parser.add_argument('--ids_location_path', type=str, help='Specify the path to locations index')
    parser.add_argument("--save_path", type=str, help="Specify the path to save the scraped data")
    args = parser.parse_args()

    return args


class FoodyScraper:
    def __init__(self, args):
        self.headers = self._initialize_headers()
        self.cookies_infos = self._initialize_cookies_infos()
        self.ids_location = load_json(args.ids_location_path)
        self.args = args

        self.max_pages = 10
        self.sleep_duration = 0.5

        self.list_output = []
    

    def _initialize_headers(self):
        return {
            'authority': 'www.foody.vn',
            'accept': 'application/json, text/javascript, */*; q=0.01',
            'accept-language': 'en-US,en;q=0.9',
            'cookie': '',
            'referer': 'https://www.foody.vn/vung-tau/tiec-cuoi-hoi-nghi?CategoryGroup=wedding&c=tiec-cuoi-hoi-nghi',
            'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Microsoft Edge";v="120"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"Linux"',
            'sec-fetch-dest': 'empty',
            'sec-fetch-mode': 'cors',
            'sec-fetch-site': 'same-origin',
            'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',
            'x-foody-user-token': 'null',
            'x-requested-with': 'XMLHttpRequest'
        }

    def _initialize_cookies_infos(self):
        return {
            "food": "bc-jcb=1; flg=vn; __ondemand_sessionid=mgzbsjrydfrpj505xyuuc2su; floc=223; _ga=GA1.2.947999007.1713953117; _gid=GA1.2.1159064546.1713953117; _fbp=fb.1.1713953116606.1641731163; __utmc=257500956; __utmz=257500956.1713953117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); fd.keys=; fd.res.view.223=1000073114; __utma=257500956.947999007.1713953117.1713953117.1713957714.2; __utmt_UA-33292184-1=1; gcat=food; _ga_6M8E625L9H=GS1.2.1713957714.2.1.1713959027.26.0.0; __utmb=257500956.9.10.1713957714",
            "entertain": "bc-jcb=1; flg=vn; __ondemand_sessionid=mgzbsjrydfrpj505xyuuc2su; floc=223; _ga=GA1.2.947999007.1713953117; _gid=GA1.2.1159064546.1713953117; _fbp=fb.1.1713953116606.1641731163; __utmc=257500956; __utmz=257500956.1713953117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); fd.keys=; fd.res.view.223=1000073114; __utma=257500956.947999007.1713953117.1713953117.1713957714.2; __utmt_UA-33292184-1=1; _gat=1; gcat=entertain; __utmb=257500956.14.10.1713957714; _ga_6M8E625L9H=GS1.2.1713957714.2.1.1713959827.15.0.0",
            "shop": "bc-jcb=1; flg=vn; __ondemand_sessionid=mgzbsjrydfrpj505xyuuc2su; floc=223; _ga=GA1.2.947999007.1713953117; _gid=GA1.2.1159064546.1713953117; _fbp=fb.1.1713953116606.1641731163; __utmc=257500956; __utmz=257500956.1713953117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); fd.keys=; fd.res.view.223=1000073114; __utma=257500956.947999007.1713953117.1713953117.1713957714.2; __utmt_UA-33292184-1=1; gcat=shop; _gat=1; __utmb=257500956.13.10.1713957714; _ga_6M8E625L9H=GS1.2.1713957714.2.1.1713959782.60.0.0",
            "travel": "bc-jcb=1; flg=vn; __ondemand_sessionid=mgzbsjrydfrpj505xyuuc2su; floc=223; _ga=GA1.2.947999007.1713953117; _gid=GA1.2.1159064546.1713953117; _fbp=fb.1.1713953116606.1641731163; __utmc=257500956; __utmz=257500956.1713953117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); fd.keys=; fd.res.view.223=1000073114; __utma=257500956.947999007.1713953117.1713953117.1713957714.2; __utmt_UA-33292184-1=1; gcat=travel; __utmb=257500956.12.10.1713957714; _ga_6M8E625L9H=GS1.2.1713957714.2.1.1713959616.49.0.0"
        }
    
    def update_cookie(self, content):
        """
        Update the cookie value in the headers dictionary.

        :param headers: The original headers dictionary.
        :param new_values: A dictionary of cookie values that need to be updated.
        """
        self.headers['cookie'] = self.cookies_infos[content]
    
    def request_data(self, category, page_num, category_id):
        r = requests.get(URL_TEMPLATE.format(
                name=category,
                page_num=page_num,
                categorie_num=category_id),
                headers=self.headers
            )
        return r

    def scrape_category(self, content, category):
        self.update_cookie(content)
        list_json = []
        category_id = self.ids_location[content][category]

        for page_num in range(self.max_pages):
            try:
                response = self.request_data(category, page_num, category_id)
                response_json = response.json()
                if not response_json["searchItems"] or response_json["totalResult"] < 12:
                    list_json.append(response_json)
                    break
                list_json.append(response_json)
                time.sleep(self.sleep_duration)
            except requests.RequestException as e:
                logging.error(f"Request error: {e}")
                break
            except ValueError as e:
                logging.error(f"JSON decoding error: {e}")
                break
        
        os.makedirs(os.path.join(args.save_path, content), exist_ok=True)

        save_json(os.path.join(args.save_path, content, f"{category}.json"), list_json)

    def scrape_data(self):
        for content in tqdm(self.ids_location):
            for category in tqdm(self.ids_location[content]):
                self.scrape_category(content, category)


if __name__ == "__main__":
    args = parser()
    scraper = FoodyScraper(args)
    scraper.scrape_data()