class PiiAnalyzer(object):
def __init__(self, filepath):
self.filepath = filepath
self.parser = CommonRegex()
self.standford_ner = StanfordNERTagger(
'classifiers/english.conll.4class.distsim.crf.ser.gz')
def analysis(self):
people = []
organizations = []
locations = []
emails = []
phone_numbers = []
street_addresses = []
credit_cards = []
ips = []
data = []
with open(self.filepath, 'rU') as filedata:
reader = csv.reader(filedata)
for row in reader:
data.extend(row)
for text in row:
emails.extend(self.parser.emails(text))
phone_numbers.extend(
self.parser.phones("".join(text.split())))
street_addresses.extend(self.parser.street_addresses(text))
credit_cards.extend(self.parser.credit_cards(text))
ips.extend(self.parser.ips(text))
for title, tag in self.standford_ner.tag(set(data)):
if tag == 'PERSON':
people.append(title)
if tag == 'LOCATION':
locations.append(title)
if tag == 'ORGANIZATION':
organizations.append(title)
return {
'people': people,
'locations': locations,
'organizations': organizations,
'emails': emails,
'phone_numbers': phone_numbers,
'street_addresses': street_addresses,
'credit_cards': credit_cards,
'ips': ips
}
class PiiAnalyzer(object):
def __init__(self, filepath):
self.filepath = filepath
self.parser = CommonRegex()
self.standford_ner = StanfordNERTagger('classifiers/english.conll.4class.distsim.crf.ser.gz')
def analysis(self):
people = []
organizations = []
locations = []
emails = []
phone_numbers = []
street_addresses = []
credit_cards = []
ips = []
data = []
with open(self.filepath, 'rU') as filedata:
reader = csv.reader(filedata)
for row in reader:
data.extend(row)
for text in row:
emails.extend(self.parser.emails(text))
phone_numbers.extend(self.parser.phones("".join(text.split())))
street_addresses.extend(self.parser.street_addresses(text))
credit_cards.extend(self.parser.credit_cards(text))
ips.extend(self.parser.ips(text))
for title, tag in self.standford_ner.tag(set(data)):
if tag == 'PERSON':
people.append(title)
if tag == 'LOCATION':
locations.append(title)
if tag == 'ORGANIZATION':
organizations.append(title)
return {'people': people, 'locations': locations, 'organizations': organizations,
'emails': emails, 'phone_numbers': phone_numbers, 'street_addresses': street_addresses,
'credit_cards': credit_cards, 'ips': ips
}
def extractEntries(zipCode, page):
entries = driver.find_elements_by_css_selector("td")
countNewEntries = 0
countDupes = 0
countElements = 0
pageDupes = set()
for entry in entries:
children = entry.find_elements_by_css_selector("div b a")
if len(children) != 1:
continue
countElements += 1
nameElements = entry.find_elements_by_css_selector("div b a")
name = None
phone = None
address = None
email = None
url = None
if nameElements:
possibleNames = [elem.text for elem in nameElements if elem.text]
if possibleNames:
name = possibleNames[0]
lines = entry.text.splitlines()
for line in lines:
parsed_text = CommonRegex(line)
valid_urls = []
if hasattr(parsed_text.links, '__call__'):
if parsed_text.links():
valid_urls = [link for link in parsed_text.links() if 'gmail' not in link and 'yahoo' not in link and 'hotmail' not in 'link']
else:
if parsed_text.links:
valid_urls = [link for link in parsed_text.links if 'gmail' not in link and 'yahoo' not in link and 'hotmail' not in 'link']
if valid_urls:
url = valid_urls[0]
if hasattr(parsed_text.emails, '__call__'):
if parsed_text.emails():
email = parsed_text.emails()[0]
else:
if parsed_text.emails:
email = parsed_text.emails[0]
if hasattr(parsed_text.phones, '__call__'):
if parsed_text.phones():
phone = parsed_text.phones()[0]
else:
if parsed_text.phones:
phone = parsed_text.phones[0]
if hasattr(parsed_text.street_addresses, '__call__'):
if parsed_text.street_addresses():
address = parsed_text.street_addresses()[0]
else:
if parsed_text.street_addresses:
address = parsed_text.street_addresses[0]
dataText = entry.text.replace("\n", " --- ")
if name or phone or email:
data = {
"name": name,
"phone": phone,
"address": address,
"email": email,
"zip": zipCode,
"url": url,
"data": dataText
}
dedupeKey = str(data['name']) + str(data['email'])
if dedupeKey not in dedupeKeys:
countNewEntries += 1
extracted.append(data)
dedupeKeys.add(dedupeKey)
elif dedupeKey not in pageDupes:
countDupes += 1
pageDupes.add(dedupeKey)
print(f" {zipCode}@{page}: Added {countNewEntries} new entries. Had {countDupes} dupes. Examined {countElements} elements")
return countNewEntries > 0
locations = []
emails = []
phone_numbers = []
street_addresses = []
credit_cards = []
ips = []
data = []
with open('sample-data.csv', 'r') as filedata:
reader = csv.reader(filedata)
for row in reader:
data.extend(row)
for text in row:
emails.extend(parser.emails(text))
phone_numbers.extend(parser.phones("".join(text.split())))
street_addresses.extend(parser.street_addresses(text))
credit_cards.extend(parser.credit_cards(text))
ips.extend(parser.ips(text))
for title, tag in standford_ner.tag(set(data)):
if tag == 'PERSON':
people.append(title)
if tag == 'LOCATION':
locations.append(title)
if tag == 'ORGANIZATION':
organizations.append(title)
sa = {
'people': people,
'locations': locations,
'organizations': organizations,
class PiiAnalyzer(object):
def __init__(self, filepath):
self.filepath = filepath
self.parser = CommonRegex()
self.standford_ner = StanfordNERTagger('classifiers/english.conll.4class.distsim.crf.ser.gz')
#def analysis(self, people = False, organizations = False,locations = False, emails = False, phone_numbers = False, street_addresses = False, credit_cards = False, ips=False):
def analysis(self, **kwargs):
people = []
organizations = []
locations = []
emails = []
phone_numbers = []
street_addresses = []
credit_cards = []
ips = []
data = []
get_all = len(kwargs)==0
get_people = get_all or kwargs.get('people',False)
get_organizations = get_all or kwargs.get('organizations',False)
get_locations = get_all or kwargs.get('locations',False)
get_emails = get_all or kwargs.get('emails',False)
get_phone_numbers = get_all or kwargs.get('phone_numbers',False)
get_street_addresses = get_all or kwargs.get('street_addresses',False)
get_credit_cards = get_all or kwargs.get('credit_cards',False)
get_ips = get_all or kwargs.get('ips',False)
with open(self.filepath, 'rU') as filedata:
reader = csv.reader(filedata)
for row in reader:
data.extend(row)
for text in row:
if(get_emails):
emails.extend(self.parser.emails(text))
if(get_phone_numbers):
phone_numbers.extend(self.parser.phones("".join(text.split())))
if(get_street_addresses):
street_addresses.extend(self.parser.street_addresses(text))
if(get_credit_cards):
credit_cards.extend(self.parser.credit_cards(text))
if(get_ips):
ips.extend(self.parser.ips(text))
for title, tag in self.standford_ner.tag(set(data)):
if get_people and tag == 'PERSON':
people.append(title)
if get_locations and tag == 'LOCATION':
locations.append(title)
if get_organizations and tag == 'ORGANIZATION':
organizations.append(title)
pii_results = dict()
if people is not None: pii_results['people'] = people
if locations is not None: pii_results['locations'] = locations
if organizations is not None: pii_results['organizations'] = organizations
if emails is not None: pii_results['emails'] = emails
if phone_numbers is not None: pii_results['phone_numbers'] = phone_numbers
if street_addresses is not None: pii_results['street_addresses'] = street_addresses
if credit_cards is not None: pii_results['credit_cards'] = credit_cards
if ips is not None: pii_results['ips'] = ips
return pii_results
