import script

import_script.py

import csv
import json

import pandas as pd

from crawler.spider_runner import SpiderRunner
from crawler.spiders.main_spider import Spider
from services.encryption import Encryption

types = {
    'Beauty': 'Professional Beauty',
    'homeservices': 'Home Services'
}

match_map = {
    'EXACT': 3,
    'STRONG': 2,
    'WEAK': 1,
    'NO MATCH': 0
}


class ImportLicenses:

    def __init__(self, path):
        self.path = path

    def read_file(self):
        if self.path.endswith('.xlsx'):
            df = pd.read_excel(self.path)
            df.fillna('', inplace=True)
        else:
            return

        csvfile1 = open('detailed_result.csv', 'w')
        writer1 = csv.writer(csvfile1)
        csvfile2 = open('result.csv', 'w')
        writer2 = csv.writer(csvfile2)
        headers = list(df.columns.values)
        writer2.writerow(headers + ['# of Results', 'Best Match'])
        headered = False
        for item in df.iloc:
            if item['state'] != 'WA':
                continue
            search_request = dict()
            search_request['business_name'] = item['business_name']
            search_request['license_category'] = types[item['category']]
            search_request['address'] = item['address']
            search_request['city'] = item['city']
            search_request['zip_code'] = str(item['zip']).split('.')[0]
            search_request['phone_number'] = str(item['phone'])[1:]
            results = []
            lic_numbers_set = set()
            if item.get('lic_number_primary', '').replace('na', '') or item.get('lic_number_secondary', '').replace('-', ''):
                for lic_number_primary in item['lic_number_primary'].split(','):
                    if not lic_number_primary.replace('na', ''):
                        continue
                    lic_number = lic_number_primary.replace('na', '').strip()
                    lic_numbers_set.add(lic_number)
                    search_request['license'] = lic_number
                    print(search_request)
                    results += SpiderRunner('washington', **search_request).get_results()

                for lic_number_secondary in item['lic_number_secondary'].split(','):
                    lic_number = lic_number_secondary.replace('-', '')
                    if not lic_number.strip() or lic_number.strip() in lic_numbers_set:
                        continue
                    search_request['license'] = lic_number_secondary.replace('-', '').strip()
                    search_request['secondary'] = True
                    print(search_request)
                    sec_result = SpiderRunner('washington', **search_request).get_results()
                    print(sec_result)
                    results += sec_result
            else:
                print(search_request)
                results += SpiderRunner('washington', **search_request).get_results()

            search = list(item)
            best_result = 'NO MATCH'
            if results:
                result = results[0]
                viewstate = result['viewstate']
                decoded_result = Encryption(viewstate).decrypt()
                decoded_details = json.loads(decoded_result)
                decoded_details = Spider().pipeline(decoded_details)
                decoded_details['match_details'] = result['match_details']
                if not headered:
                    headered = True
                    writer1.writerow(headers + ['strength'] + list(decoded_details.keys()))
                for result in results:
                    viewstate = result['viewstate']
                    strength = result['match_details']['strength']
                    decoded_result = Encryption(viewstate).decrypt()
                    decoded_details = json.loads(decoded_result)
                    decoded_details = Spider().pipeline(decoded_details)
                    decoded_details['match_details'] = result['match_details']
                    result = [strength] + list(decoded_details.values())
                    writer1.writerow(search + result)
                    if match_map[strength] > match_map[best_result]:
                        best_result = strength
            else:
                writer1.writerow(search)
            writer2.writerow(search + [len(results), best_result])


if __name__ == '__main__':
    ImportLicenses('businesses-ca.xlsx').read_file()