# default boilerplate here. See /python/boilerplate
####################
# 220910 getting final list of all DNEs from xxxxxx campaign from log files

import csv

### set of emails from logs

set_emails_from_log = set()

count_files = 0
count_lines = 0

for root, dirs, files in os.walk("log"):
    for name in files:

        if name.endswith((".txt")):

            count_files += 1

            file_path = f"{root}/{name}"

            with open(file_path, 'r') as df:
                lines = df.readlines()
                count_lines_in_file = 0
                for line in lines:
                    count_lines += 1
                    count_lines_in_file += 1

                    if '\n' in line:
                        line = line.rstrip()

                    # print(repr(line))

                    if '@' in line: # basic but enough here - just taking care of removing any empty row
                        set_emails_from_log.add(line.lower().strip())

                ### DELETE EMPTY FILES / not necessary here, maintenance only
                if count_lines_in_file == 0:
                    os.remove(file_path)
                    print(f"DELETED {file_path} with {count_lines_in_file} lines.")

                ### Check
                # print(f"{file_path}:\t{count_lines_in_file} lines.")

# print(f"\n\nset_emails_from_log:")
# pp.pprint(set_emails_from_log)

### Match with existing XX contacts in Hubspot

csv_file = "data/220911_hubspot-crm-export_my-XX-contacts.csv"

count_row_csv = 0
count_unsubscribe = 0

all_hubspot_emails = []
all_hubspot_unsubscribe_emails = []

with open(csv_file, 'r', newline='', encoding='UTF-8') as h:
    reader = csv.reader(h, delimiter=",")
    next(reader)
    data = list(reader)
    for row in data:
        count_row_csv += 1

        email = row[4]
        unsubscribe = row[5]

        if '@' in email:

            all_hubspot_emails.append(email.lower().strip())

            if unsubscribe != '':
                count_unsubscribe += 1
                # print(f"{count_row_csv} = {email}: {unsubscribe}")
                all_hubspot_unsubscribe_emails.append(email.lower().strip())



list_delta = [] # to collect emails not added to final list / for verification or else. 

final_list_of_new_unsubscribe_emails = []

for email_found in set_emails_from_log:
    if email_found in all_hubspot_emails:
        if email_found not in all_hubspot_unsubscribe_emails:
            final_list_of_new_unsubscribe_emails.append(email_found)
    else:
        list_delta.append(email_found)

# pp.pprint(final_list_of_new_unsubscribe_emails)

### write final file to share with client (CSV)

with open(f"data/{ts_file}_emails_to_unsubscribe_in_hubspot.csv", 'w', newline='', encoding='utf-8') as i:
    writer = csv.writer(i, delimiter=',', quotechar='|', quoting=csv.QUOTE_MINIMAL, lineterminator='\n')
    writer.writerow(['email']) # header row
    for item in final_list_of_new_unsubscribe_emails:
        writer.writerow([item]) # pass list for row, else iterates through string

########################################################################################################
# default boilerplate here. See /python/boilerplate

-------------------------------
220910_XX_list_dne.py

count_files = 12
count_lines = 72090


set_emails_from_log: 762


all_hubspot_emails: 3577
all_hubspot_unsubscribe_emails: 595

final_list_of_new_unsubscribe_emails: 487

-------------------------------
220910_XX_list_dne.py finished in 0.1s.