def test_subdomain(self):
"""
email-split splitting an email on a subdomain
returns the local part
returns the domain part (including subdomain)
"""
email = email_split('*****@*****.**')
self.assertEqual(email.local, 'you')
self.assertEqual(email.domain, 'are.super.cool')
def test_top_level_domain(self):
"""
email-split splitting an email with a top-level domain
returns the local part
returns the domain part
"""
email = email_split('*****@*****.**')
self.assertEqual(email.local, 'todd')
self.assertEqual(email.domain, 'underdog.io')
def test_top_level_domain(self):
"""
email-split splitting an email with a top-level domain
returns the local part
returns the domain part
"""
email = email_split('*****@*****.**')
self.assertEqual(email.local, 'todd')
self.assertEqual(email.domain, 'underdog.io')
def test_subdomain(self):
"""
email-split splitting an email on a subdomain
returns the local part
returns the domain part (including subdomain)
"""
email = email_split('*****@*****.**')
self.assertEqual(email.local, 'you')
self.assertEqual(email.domain, 'are.super.cool')
def getDomain(email):
if email is None or email.strip() == "":
return None
# change sth (special characters)
for o, n in email_replace_strs.items():
email = email.replace(o, n)
email = email.replace(r"\s", "").lower()
email_splits = email_split(email.strip())
domain = email_splits.domain
if domain == "":
return None
return domain
def cleanMatches(self, matchFrame):
stopwords = {'the'}
for index, row in matchFrame.iterrows():
tempString = cleanco(
matchFrame.iloc[index]['company'].lower()).clean_name()
resultwords = [
word for word in re.split("\W+", tempString)
if word.lower() not in stopwords
]
result = ' '.join(resultwords)
matchFrame.at[index, 'Clean Company'] = result.translate(
None, string.punctuation)
try:
matchFrame.at[index, 'Email Domain'] = email_split(
row['email']).domain
except Exception as e:
print 'error ' + str(e)
print 'no email'
pass
def identify_o365(email_domain):
email_domain = email_split(open(args.list).readline().rstrip())
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36',
'Sec-Fetch-Dest': 'document'
}
url_structure = "https://login.microsoftonline.com/{}/.well-known/openid-configuration".format(
email_domain.domain)
r = requests.get(url_structure, headers=headers)
subscribed = re.search('token_endpoint', r.text)
# AADSTS90002 InvalidTenantName - The tenant name wasn't found in the data store. Check to make sure you have the correct tenant ID.
if '"error_codes":[90002]' in r.text: #If not subscribed
print("The domain isn't using o365")
exit()
if subscribed:
pass
def prepare_email(email):
return email_split(email).local, email_split(email).domain
def extract_email(email):
""" extract the email addresses from a user-friendly email address"""
addresses = email_split(email)
return addresses[0] if addresses else ''
def get_possible_email(contact_name, email):
split_name_parts = []
try:
split_name_parts = pp.parse(contact_name, type='person')
except TypeError as e:
logger.error("possible_email: " + str(e) + ' - ' +
json.dumps(contact_name))
given_name = ''
surname = ''
for split_name_part in split_name_parts:
if split_name_part[1] == 'Surname':
surname = split_name_part[0].lower()
if split_name_part[1] == 'GivenName':
given_name = split_name_part[0].lower()
email = email.lower()
email_parts = email_split(email)
possible_emails = {}
domain = email_parts.domain
surname_first_letter = surname[0] if len(surname) else ''
given_name_first_letter = given_name[0] if len(given_name) else ''
possible_emails['given_name|surname'] = "%s%s@%s" % (given_name, surname,
domain)
possible_emails['given_name|.|surname'] = "%s.%s@%s" % (given_name,
surname, domain)
possible_emails['given_name|-|surname'] = "%s-%s@%s" % (given_name,
surname, domain)
possible_emails['given_name|_|surname'] = "%s_%s@%s" % (given_name,
surname, domain)
possible_emails['surname|given_name'] = "%s%s@%s" % (given_name, surname,
domain)
possible_emails['surname|.|given_name'] = "%s.%s@%s" % (surname,
given_name, domain)
possible_emails['surname|-|given_name'] = "%s-%s@%s" % (surname,
given_name, domain)
possible_emails['surname|_|given_name'] = "%s_%s@%s" % (surname,
given_name, domain)
possible_emails['surname0|.|given_name'] = "%s.%s@%s" % (
surname_first_letter, given_name, domain)
possible_emails['surname0|given_name'] = "%s%s@%s" % (surname_first_letter,
given_name, domain)
possible_emails['surname0|-|given_name'] = "%s-%s@%s" % (
surname_first_letter, given_name, domain)
possible_emails['surname0|_|given_name'] = "%s_%s@%s" % (
surname_first_letter, given_name, domain)
possible_emails['given_name0|.|surname'] = "%s.%s@%s" % (
given_name_first_letter, surname, domain)
possible_emails['given_name0|surname'] = "%s%s@%s" % (
given_name_first_letter, surname, domain)
possible_emails['given_name0|-|surname'] = "%s-%s@%s" % (
given_name_first_letter, surname, domain)
possible_emails['given_name0|_|surname'] = "%s_%s@%s" % (
given_name_first_letter, surname, domain)
possible_emails['given_name|.|surname0'] = "%s.%s@%s" % (
given_name, surname_first_letter, domain)
possible_emails['given_name|surname0'] = "%s%s@%s" % (
given_name, surname_first_letter, domain)
possible_emails['given_name|-|surname0'] = "%s-%s@%s" % (
given_name, surname_first_letter, domain)
possible_emails['given_name|_|surname0'] = "%s_%s@%s" % (
given_name, surname_first_letter, domain)
possible_emails['surname|.|given_name0'] = "%s.%s@%s" % (
surname, given_name_first_letter, domain)
possible_emails['|surname|given_name0'] = "%s%s@%s" % (
surname, given_name_first_letter, domain)
possible_emails['surname|-|given_name0'] = "%s-%s@%s" % (
surname, given_name_first_letter, domain)
possible_emails['surname|_|given_name0'] = "%s_%s@%s" % (
surname, given_name_first_letter, domain)
possible_emails['surname0|given_name0'] = "%s%s@%s" % (
surname_first_letter, given_name_first_letter, domain)
possible_emails['given_name0|surname0'] = "%s%s@%s" % (
given_name_first_letter, surname_first_letter, domain)
possible_emails['surname'] = "%s@%s" % (surname, domain)
possible_emails['given_name'] = "%s@%s" % (given_name, domain)
for possible_pattern, possible_email in possible_emails.items():
if possible_email == email:
pattern = possible_pattern
return {'pattern': pattern, 'email': possible_email}
domain_split = email.split('@')
if len(domain_split):
email_domain = domain_split[0]
if surname and given_name and surname in email_domain and given_name in email_domain:
return {'pattern': '_surname_given_name_', 'email': email}
return None
