import csv
import os
import random
import pandas as pd
from collections import defaultdict
from pymongo import MongoClient
import numpy as np
from tqdm import tqdm

# client = MongoClient('mongodb+srv://miami:miami6033626@cluster0.lodffed.mongodb.net/?retryWrites=true&w=majority')
# db = client['miami-database']
# csv_collection = db['csv']
# record_collection = db['record']
# csv_list = [f'list_{str(i + 1)}.csv' for i in range(697)]
#
# query0 = record_collection.count_documents({"count": {'$eq': 0}})
# query1 = record_collection.count_documents({"count": {'$eq': 1}})
# query2 = record_collection.count_documents({"count": {'$eq': 2}})
# query3 = record_collection.count_documents({"count": {'$eq': 3}})
# query4 = record_collection.count_documents({"count": {'$eq': 4}})
# query5 = record_collection.count_documents({"count": {'$eq': 5}})
# print(query0 * 6 + query1 * 5 + query2 * 4 + query3 * 3 + query4 * 2 + query5 * 1)
# with open('../bam122/a.txt', 'a', encoding='utf-8') as file:
#     for x in record_collection.find({"count": {'$lt': 6}}):
#         file.write(x['name'] + '\n')
# res = []
# for x in record_collection.find({}):
#     res.append([x['name'], x['count'], x['prolific_ids']])
#
# with pd.ExcelWriter('summary_from_mongodb.xlsx') as writer:
#     df = pd.DataFrame(res, columns=['list_name', 'count', 'prolific_ids'])
#     df.to_excel(writer)
#
# data_path = "../../data_collected"
# filenames = ['oTree_Miami_2023-03-25.xlsx', 'oTree_Miami_2023-03-29.xlsx', 'oTree_Miami_2023-04-01.xlsx',
#              'oTree_Miami_2023-04-04.xlsx', 'oTree_Miami_2023-04-06.xlsx', 'oTree_Miami_2023-04-07.xlsx',
#              'oTree_Miami_2023-04-08.xlsx', 'oTree_Miami_2023-04-11.xlsx', 'oTree_Miami_2023-04-12.xlsx',
#              'oTree_Miami_2023-04-13.xlsx', 'oTree_Miami_2023-04-14.xlsx', 'oTree_Miami_2023-04-18.xlsx',
#              'oTree_Miami_2023-04-19.xlsx', 'oTree_Miami_2023-04-20.xlsx', 'oTree_Miami_2023-04-21.xlsx',
#              'oTree_Miami_2023-04-23.xlsx', 'oTree_Miami_2023-04-25.xlsx']
#
# bl = []
# bll = []
# list_count = defaultdict(int)
# list_id = defaultdict(list)
# with open(os.path.join(data_path, 'Duplicates.csv')) as f:
#     player_csv = csv.reader(f)
#     for row in player_csv:
#         if row[4] == '1':
#             if row[0] not in bl:
#                 list_count[row[2]] += 1
#                 list_id[row[2]].append(row[0])
#                 bl.append(row[0])
#
# accept_ids = []
# txt_file = open('accept_ids.txt', 'r')
# lines = txt_file.readlines()
# for line in lines:
#     accept_ids.append(line.rstrip('\n'))
# ac_ids = []
# for filename in tqdm(filenames):
#     df = pd.read_excel(os.path.join(data_path, filename),
#                        usecols=['participant.label', 'bam122.51.player.AC_Correctness',
#                                 'bam122.51.player.csv_file_used'])
#     df_li = df.values.tolist()
#     for label, acc, csv_n in df_li:
#         # if csv_n == 'list_453.csv':
#         #     print('find_one!')
#         if acc >= 0.5 and csv_n != 0:
#             if label not in bl:
#                 list_id[csv_n].append(label)
#                 list_count[csv_n] += 1
#                 bl.append(label)
#         else:
#             if label in accept_ids and csv_n != 0:
#                 # ac_ids.append([label, csv_n, filename])
#                 if label not in bl:
#                     list_id[csv_n].append(label)
#                     list_count[csv_n] += 1
#                     bl.append(label)
#
# # v = list(set(bl))
#
#
# csv_list = [f'list_{str(i + 1)}.csv' for i in range(697)]
# res = []
# for cl in csv_list:
#     res.append([cl, list_count[cl], list_id[cl]])
#
# with pd.ExcelWriter('summary_from_data1.xlsx') as writer:
#     df = pd.DataFrame(res, columns=['list_name', 'count', 'prolific_ids'])
#     df.to_excel(writer)

# with pd.ExcelWriter('summary_for_accepted_ids2.xlsx') as writer:
#     df = pd.DataFrame(ac_ids, columns=['ids', 'csv_used', 'filename'])
#     df.to_excel(writer)

csv_list = [f'list_{str(i + 1)}.csv' for i in range(697)]
total_urls = dict()
for csv_name in csv_list:
    df = pd.read_csv(csv_name, header=None)
    ll = df.iloc[:, 0].tolist()
    ids = []
    for lli in ll:
        ids.append(lli.split('/')[-1].rstrip('.jpg'))
    total_urls[csv_name] = ids

res = set()
with open('./2.txt', 'r', encoding='utf-8') as file:
    for line in tqdm(file):
        tmp = line.strip('\n').split('/')[-1].rstrip('.jpg')
        for csv_name in csv_list:
            if tmp in total_urls[csv_name]:
                res.add(csv_name)

print(res)