Last active
November 25, 2017 18:59
-
-
Save jQwotos/4b8d8f3a7b030c0814c3de74031fb701 to your computer and use it in GitHub Desktop.
Extracts email addresses from CUHacking Registration emails.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Usage Instructions | |
# 1. Download the emails from Zoho | |
# 2. Extract them into the proper folder name, default is Emails | |
# 3. Run the script (in python3) and done! | |
from os import chdir | |
from glob import glob | |
import re | |
import csv | |
EMAILS_FOLDER = 'Emails' | |
TARGET_TEXT = 'Someone just submitted your form on cuhacking.com/. Here\'s what they had to=' | |
AVOID_TEXT = 'description:' | |
CSV_FILE = 'emails.csv' | |
# Awesome email regex pat from user2032663 on https://stackoverflow.com/questions/16053797/regex-to-find-email-address-from-a-string | |
EMAIL_PAT = r'(?:[a-z0-9!#$%&\'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&\'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])</pre>' | |
def _read_file(fname): | |
f = open(fname, 'r') | |
f_content = f.read() | |
f.close() | |
return f_content | |
def retrieve_emails(EMAILS_FOLDER = EMAILS_FOLDER): | |
chdir(EMAILS_FOLDER) | |
all_email_names = glob("*.eml") | |
data = [_read_file(x) for x in all_email_names] | |
chdir('..') | |
return data | |
def _validate_email(email): | |
return True if TARGET_TEXT in email and AVOID_TEXT not in email else False | |
def filter_emails(emails): | |
return [x for x in emails if _validate_email(x)] | |
def _find_user_email_addr(email): | |
return re.search(EMAIL_PAT, email).group().replace('</pre>', '') | |
def remove_duplicates(emails): | |
return list(set(emails)) | |
def save_to_csv(email_addrs, CSV_FILE = CSV_FILE): | |
f = open(CSV_FILE, 'w') | |
csv_writer = csv.writer(f, delimiter=',') | |
csv_writer.writerow(['Email']) | |
for email_addr in email_addrs: | |
csv_writer.writerow([email_addr]) | |
f.close() | |
def main(): | |
emails = filter_emails(retrieve_emails()) | |
email_addrs = [_find_user_email_addr(email) for email in emails] | |
email_addrs = remove_duplicates(email_addrs) | |
save_to_csv(email_addrs) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment