ben_200_include

def locate_txt_files(path=os.getcwd):
    """ A function that locates and returns a list of txt files from a given path """

    txt_array = []
    for item in os.listdir(path()):
        if item.endswith(".txt"):
            txt_array.append(item)
    return txt_array


def open_and_prepare_urls(txt_array):
    """ A function that takes in a list of txt files, open each file, split("\n") and returns
        a list of cleaned domains without trailing "\n" """

    domains = []
    for item in txt_array:
        with open(item) as f:
            content = f.readlines()
            domains.extend(content)
    domains = [domain.strip() for domain in domains]
    return domains


def open_and_prepare_urls2(txt_file_array):
    final_domains = []

    for txt_file in txt_file_array:
        with open(txt_file, encoding="utf-8") as f:
            content = f.read()
        content = content.split("au")[0:]
        domain_urls = [item.replace("|", "").replace("\n", "").replace(",", "").strip()+"au" for item in content if "." in item]
        final_domains.extend(domain_urls)
        print(f"Total of {len(domain_urls)} '.au' domains found in {txt_file}")
        print("\n")

    return final_domains






def make_dict(array):
    """ A function that makes a dictionary ready to be fed to pandas """

    a = []
    b = []

    for item in array:
        a.append(item[0])
        b.append(item[1])

    my_dict = {"Domain":pd.Series(a), "Phone Number":pd.Series(b)}

    return my_dict



def make_dict2(result_array, filename="results.csv", path=os.getcwd):
    """ A function that updates an exixting csv file (look at make_dataframe function) """

    df1 = pd.read_csv(filename)
    domains = df1["Domain"].tolist()
    phones = df1["Phone Number"].tolist()

    for item in result_array:
        domains.append(item[0])
        phones.append(item[1])

    my_dict = {"Domain":pd.Series(domains), "Phone Number":pd.Series(phones)}

    return my_dict


def make_dataframe(dic, filename="results.csv", path=os.getcwd):
    """" A function that takes in a dict and makes a pd dataframe """
    try:
        df__ = pd.DataFrame(dic)
        df__ = df__.drop_duplicates()
        return df__
    except Exception as e:
        #print(e)
        pass


def save_dataframe(data_f):
    """ A function that takes in a pandas dataframe and saves it as a csv file """

    data_f.to_csv("results.csv", index=False)
    print("Done")



def check_for_04(arg):
    arg = str(arg).replace(" ", "").replace("(", "").replace("-", "").replace(".", "").strip()
    if arg.startswith("04") or arg.startswith("4"):
        return True
    else:
        return False





def create_04(filename="results.csv", dest_filename="results_04.csv"):

    """ create phones that start with 04 """

    a = []
    b = []

    try:
        df2 = pd.read_csv(dest_filename)
        domains_ = df1["Domain"].tolist()
        phones_ = df1["Phone Number"].tolist()
    except:
        pass


    df1 = pd.read_csv(filename)
    domains = df1["Domain"].tolist()
    phones = df1["Phone Number"].tolist()

    try:
        domains.extend(domains_)
        phones.extend(phones_)

    except:
        pass

    for index, phone in enumerate(phones):
        if check_for_04(phone):
            a.append(phones[index])
            b.append(domains[index])
            del phones[index]
            del domains[index]

    my_dict = {"Domain":pd.Series(b), "Phone Number":pd.Series(a)}
    dframe = make_dataframe(dic=my_dict)

    my_dict2 = {"Domain":pd.Series(domains), "Phone Number":pd.Series(phones)}
    df_2 = make_dataframe(dic=my_dict2)
    save_dataframe(df_2)
    dframe.to_csv(dest_filename, index=False)
    print("Created 04..phone numbers!")




def main():
    #result = [] #list of tuple containing domain and phone

    if filename in os.listdir(path()):
        dict_ = make_dict2(result_array=results)
        dataframe = make_dataframe(dic=dict_)
        save_dataframe(data_f=dataframe)
        create_04()


    else:
        dic = make_dict(array=results)
        dataframe2 = make_dataframe(dic=dic)
        save_dataframe(data_f=dataframe2)
        create_04()


    print("Done!")