Last active
July 10, 2018 13:50
-
-
Save raitisd/90dbe8d6a5f6a91da7c0229407f66310 to your computer and use it in GitHub Desktop.
Sort out valid and invalid addresses
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
import json | |
import re | |
with open('failed_chunks.json', 'r') as f: | |
parsed_file = json.load(f) | |
email_addresses = [] | |
for chunk_object in parsed_file: | |
for email_address in chunk_object['chunk']: | |
email_addresses.append(email_address) | |
valid_addresses = [] | |
invalid_addresses = [] | |
for email_address in email_addresses: | |
if re.match(r"(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)", email_address): | |
valid_addresses.append(email_address) | |
else: | |
invalid_addresses.append(email_address) | |
with open('valid-addresses.json', 'w') as f: | |
json.dump(valid_addresses, f) | |
with open('invalid-addresses.json', 'w') as f: | |
json.dump(invalid_addresses, f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment