from more_itertools import unique_everseen

import requests, json
import csv
import os
import glob
import pandas as pd

def isMale(name):

    with open('male_names1.csv','r') as maleNames:

        checkList = csv.reader(maleNames, delimiter=',')

        for row in checkList:

           if row[0].lower() == name.lower():
               return 1

        return 0

def excludeBio(line):

    excludedWords = ["specialty", "crafted", "supplies", "domestic", "website", "order", "orders ", "$", "£", "free",
                 "world", "worldwide", "wide", "ship", "shipping", "jewelry", "men", "men's", "guy", "guy's",
                 "business", "days", "return", "returns", "exchange", "exchanges"]

    line = line.replace('\n', '')
    line = line.replace('\t', '')

    lineList = line.split(" ")

    valsLower = [item.lower() for item in lineList]

    l3 = [x for x in valsLower if x not in excludedWords]

    if len(valsLower) != len(l3):
        print(line)
        return 1
    else:
        return 0

def cleanWithFilters(row):


    excludeCategoryList = ["Non-Profits & Religious Organizations", "Content & Apps", "Local Business",
                           "Transportation & Accomodation Services", "Grocery & Convenience Stores", "Auto Dealers",
                           "Business & Utility Services", "Product/Service", "Photographer", "Movie Theater"]

    isOK = 1

    try:
        if int(row[5]) > 3000:
            print("P1")
            isOK = 0
        if int(row[4]) < 30:
            print("P2")
            isOK = 0
        if excludeBio(row[7]):
            print("P3")
        if row[18] in excludeCategoryList:
            print("P4")
            isOK = 0
        if int(row[6]) < 1:
            print("P5")
            isOK = 0
        if not row[10]:
            print("P6")
            isOK = 0
        if isMale(row[2].split(' ')[0]):
            print(row[2].split(' ')[0])
            isOK = 0
        if checkEmailPattern(row[10]):
            print("P7")
            isOK = 0

    except:
        print("except")
        isOK = 0

    return isOK


def checkEmailPattern(email):

    listOfUnwantedEmails = ["hi","info","aloha","service","customerservice","hello", "help", "photo", "photographer", "shop",
                            "customer","contact"]

    emailBegins = email.split('@')[0]

    if emailBegins.lower() in listOfUnwantedEmails:
        return 1
    else:
        return 0



def matchEmails(email):

    with open('mejlovizaproverka.csv','r') as validEmailList:
        emailList = csv.reader(validEmailList, delimiter=',')
        for row in emailList:
           emailContains = 0

           if row[0].lower() == email.lower():
               emailContains = 1
               break

        if emailContains == 1:
            return 1
        else:
            return 0


#call when nothing is done
def mainFunc():

    with open('amy_hetherington_followers_PR6440_1878530020.csv') as csvfile, open('amy_hetherington.csv','w+') as outputfile:
        readCSV = csv.reader(csvfile, delimiter=',')
        writer = csv.writer(outputfile, delimiter=",")
        writer.writerow(next(readCSV))

        for row in readCSV:

            if cleanWithFilters(row):
                writer.writerow(row)


#call after the output file is done
def mergeToMainCsv():

    os.chdir("/Users/nikolasokolov/PycharmProjects/untitled/allbatches")

    extension = 'csv'

    all_filenames = [i for i in glob.glob('*.{}'.format(extension))]

    # combine all files in the list
    combined_csv = pd.concat([pd.read_csv(f) for f in all_filenames])
    # export to csv
    combined_csv.to_csv("combined_csv.csv", index=False, encoding='utf-8-sig')

#remove duplicates from all previous batches compared to this one
def removeDuplicates():

    data = pd.read_csv("/Users/nikolasokolov/PycharmProjects/untitled/allbatches/combined_csv.csv")

    df = pd.DataFrame(data)

    emailList = df['email'].unique().tolist()

    with open('50k.csv') as csvfile, open('50k - FINAL.csv','w+') as outputfile:
        readCSV = csv.reader(csvfile, delimiter=',')
        writer = csv.writer(outputfile, delimiter=",")
        writer.writerow(next(readCSV))

        for row in readCSV:

            if row[10] in emailList:
                print("Duplicate " + row[10])
                continue
            writer.writerow(row)

def addScrapedColumn():

    df = pd.read_csv("stanzie.star_followers_FT433_794983088.csv", error_bad_lines=False)

    df['scrapedFrom'] = "stanzie.star"

    print(df)

    df.to_csv('stanzie.star_followers_FT433_794983088.csv')

#redot na vikanje funkcii e:

#mainFunc() kaj shto ke go smenish file-nameot so toj shto treba da se proveri
#od kako ke gi spoish u sheets i trgnesh duplicates od spoenite
#downloadiraj go batchot shto e spremen i staj go u allbatches
#povikaj removeDuplicates za batchot
#validiraj i prakjaj


mainFunc()