def mailDownloader(mnt, dst, tsv):
with open(tsv) as tsvfile:
reader = csv.reader(tsvfile, delimiter='\t')
array = []
for row in reader:
try:
fulldomain = getaddresses([
row[2],
])
except:
print("[ERROR] Can't parse the following row, skipping it : " +
', '.join(row))
pass
if fulldomain:
email = fulldomain.pop()[1]
contact = email.split("@")[0]
domain = email.split("@")[-1]
fileprefix = row[0][1:3]
URI = "/" + domain + "/" + contact + "/" + fileprefix + "/" + row[
0]
fullpath = mnt + URI
localfile = "/home/learning/" + args.bayes + "-archive/" + row[
0]
if isFileExist(localfile) == False:
try:
shutil.copy2(mnt + URI, dst)
if args.debug == True:
print("GET :", fullpath)
except:
pass
def emailFromAdmin(recipient, sub, content, wholelist=False):
if not bballdb.getSendEmails():
logging.info("Emails are disabled; not sending email To: %s Subject: %s" % (recipient, sub) )
# logging.info(content)
return
logging.info("Sent email To: %s Subject: %s" % (recipient, sub) )
logging.info(content)
if recipient is not None:
to = [recipient]
else:
to = []
if wholelist:
# Add the A List recipients
to.extend(email.split()[0] for name,email in bballdb.loadAList(onlySendEmail=True)) # only use first name on a line
# Add the B List recipients
to.extend(email.split()[0] for name,email in bballdb.loadBList(onlySendEmail=True)) # only use first name on a line
# Only unique entries, sorted
to = list(sorted(set([i.lower() for i in to])))
if not to:
logging.warning('No recipients, not sending email')
return
mail.send_mail(sender=ADMIN_EMAIL,
to=to,
subject=sub,
body=content)
def preprocessEmailData(self):
'''
this method is used as a driver that calls different methods for processing data
:return: void
'''
parser = Parser() # Added for extracting only the body of the email
tokens = self.Ngram.loadCorpus()
email = parser.parsestr(tokens) # Added for extracting only the body of the email
email_body_list = [email.split('Body:')[-1] for email in tokens.split('##########################################################')] # Added for extracting only the body of the email
tokendata=[]
for txt in email_body_list:
tokendata.append(nltk.wordpunct_tokenize(txt))
merged = list(itertools.chain.from_iterable(tokendata)) # flattening the tokendata which is a list of list.
preprocessedText = self.Ngram.preprocessData(merged)
stemmedwords = self.Ngram.stemWords(preprocessedText)
self.Ngram.writeToFile(stemmedwords,'preprocessedEmailBody')
posTaggedList = self.Ngram.createPOSTagging(stemmedwords)
preprocessedListwithoutNouns = self.Ngram.removeProperNouns(posTaggedList)
print 'removed proper nouns'
print datetime.strftime(datetime.now(), '%Y-%m-%d %H:%M:%S')
bigramslist = self.Ngram.createBigrams(preprocessedListwithoutNouns)
print 'bigrams created successfully'
print datetime.strftime(datetime.now(), '%Y-%m-%d %H:%M:%S')
trigramslist = self.Ngram.createTrigrams(preprocessedListwithoutNouns)
print 'trigrams created successfully'
self.Ngram.writeToFile(bigramslist,'emailbigramList')
self.Ngram.writeToFile(trigramslist,'emailtrigramList')
print datetime.strftime(datetime.now(), '%Y-%m-%d %H:%M:%S')
def signin(cls, email, type):
if not '@' in email:
raise EmailError("malformed e-mail")
hash = hashlib.md5(email).hexdigest()
image = 'http://0.gravatar.com/avatar/%s' % hash
name = string.capwords(email.split('@')[0].replace('.', ' '))
# prevents double signin...
previous_signin = db.GqlQuery(
"SELECT * FROM Signin WHERE email = '%s' AND active = true" %
email).get()
if previous_signin:
try:
cls.deactivate_staffer(email)
except:
logging.info("Failed deactivating old Signin object.")
s = Signin(email=email, type=type, image_url=image, name=name)
DailyCount.increment_and_get()
s.put()
if "mark.hutsell" in email or "some.other.evilguy" in email:
mail.send_mail(sender="Signin Machine <*****@*****.**>",
to="Emergency Paging System <*****@*****.**>",
subject="Sign-in: " + email,
body="Sign in")
urlfetch.fetch(
"http://www.dustball.com/call/call.php?str=Sign+in+" + email)
return s
def matchEmailstoAddresses(email):
matched = False
matches = []
# finds match of the brand in the email, can have several
for brand_entry in brands_dict.keys():
clean = email.replace(".com","")
if brand_entry[1] in clean:
matches.append(brand_entry)
matched = True;
# cleans up the email address
email = email.split('<')
email = email[len(email)-1].strip('>')
# if there are matches match to the longest brand name
if matched:
longest = matches[0]
for match in matches:
if (len(match[1]) > len(longest[1])):
longest = match
brands_dict[longest] = email
return longest[0]
# else add to list of unmatched brands
else:
unmatched.append(email)
return unmatchedIndex ##UNMATCHED in the db is 1
def _get_host(self, email):
'''
Extracts imap host and port number based on the email address. If the
domain of the email is not recognized, it will try 'imap.domain.com'
which is fairly standard.
Parameters
==========
email: str, the email address. E.g. '*****@*****.**'
Notes
=====
Please note that Gmail by default does not allow users to access
their email in this way. You can change this setting here:
https://support.google.com/mail/accounts/answer/78754
'''
#extract domain, e.g. 'yahoo.com'
domain = email.split('@')[1]
#Dict of known host/port tuples
imap = {
'yahoo.com': ('imap.mail.yahoo.com', 993),
'gmail.com': ('imap.gmail.com', 993)
}
if imap.get(domain):
return imap.get(domain)
else:
msg = 'Domain "%s" not recognized. Trying "imap.%s"'
raise Warning(msg % (domain, domain))
return ('imap.%s' % domain, 993)
def validate_email(email: str) -> bool:
"""
Checks correctness of a username
Throws exception if the syntax does not fit,
the domain is blacklistet or is already in use
:email name: Users email (Case sensitive)
:return: true if no error occured
"""
# check for correct email syntax
if not EMAIL_REGEX.match(email):
raise ApiException([Error(ErrorCode.INVALID_EMAIL, email)])
# check for blacklisted email domains (we don't like disposable email)
with db.connection:
cursor = db.connection.cursor()
cursor.execute("SELECT lower(domain) FROM email_domain_blacklist")
rows = cursor.fetchall()
# Get list of blacklisted domains (so we can suffix-match incoming emails
# in sublinear time)
blacklisted_email_domains = marisa_trie.Trie(map(lambda x: x[0], rows))
domain = email.split("@")[1].lower()
if domain in blacklisted_email_domains:
raise ApiException([Error(ErrorCode.BLACKLISTED_EMAIL, email)])
# ensue that email adress is unique
cursor.execute("SELECT id FROM `login` WHERE LOWER(`email`) = %s",
(email.lower(),))
if cursor.fetchone() is not None:
raise ApiException([Error(ErrorCode.EMAIL_REGISTERED, email)])
return True
def sendNotification(df):
import smtplib, ssl
companyEmail = pd.unique(df['Email'])
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
port = 465 # For SSL
smtp_server = "smtp.gmail.com"
sender_email = "*****@*****.**" # Enter your address
password = '******'
context = ssl.create_default_context()
for email in companyEmail:
print('Sending Email to ', email)
grouped = df.groupby('Email').get_group(email)
str_msg = "recieved {} files ".format(grouped['Title'].count())
print(grouped)
email2 = email.split('@')
message = """\
Subject: VH-Files recieved from """ + email2[0] + """
We have recieved your files: \n""" + str(
grouped['Title'].to_string()).split(' ')[1] + ' ' + str(
grouped['File Size'].to_string()).split(
' ')[1] + ' ' + str(datetime.now())
with smtplib.SMTP_SSL(smtp_server, port, context=context) as server:
server.login(sender_email, password)
server.sendmail(sender_email, email, message)
def __get_tokens(self, rcptto):
c = self.get_cursor()
format_strings = ','.join(['%s'] * len(rcptto))
recipients = tuple([re.sub(r'^(drop|bucket)-comment-', r'', email.split('@')[0]) for email in rcptto])
c.execute("""select `type`, `data`
from `auth_tokens`
where token in (%s)""" % format_strings, recipients)
return [(token_type, json.loads(data)) for token_type, data in c.fetchall()]
def from_email_parse(msg):
email = str(make_header(decode_header(msg['From'])))
name = ''
fields = email.split("<")
if len(fields) > 1:
name = fields[0]
email = fields[1].replace(">", "")
return name, email
def _parse_email_address(self, email):
"""
Returns 'email' as:
... (address_name, address_domain)
E.g. _parse_email_address('*****@*****.**')
... will return: ('account', 'dom.com')
Essentially just splits the string at '@'
"""
return email.split('@')
def get_pop3host(email):
try:
pop3_host = 'pop3.%s' % (email.split('@')[-1])
return pop3_host
except:
return ''
def __get_rivers(self, rcptto):
c = self.get_cursor()
format_strings = ','.join(['%s'] * len(rcptto))
c.execute(
"""select `id`
from `rivers`
where river_active = 1
and email_id in (%s)""" % format_strings,
tuple([email.split('@')[0] for email in rcptto]))
return [river_id for river_id, in c.fetchall()]
def get_smtphost(email):
try:
smtp_host='smtp.'+email.split('@')[-1]
return smtp_host
except:
return ''
def create_user(self,
email: str,
username: str = None,
password: str = None,
is_staff: bool = False,
is_superuser: bool = False) -> UserHandle:
"""Add the specified user to the database, with email confirmed.
Keyword arguments:
username -- string (default user portion of email)
password -- string (default email)
is_staff -- bool (default False)
is_superuser -- bool (default False)
"""
if not username:
username = email.split('@')[0]
if not password:
password = email
hmac = hashlib.pbkdf2_hmac('sha256', password.encode('utf-8'), b'salt',
1)
hmac_base64 = binascii.b2a_base64(hmac, newline=False)
password_hash = '$'.join(
['pbkdf2_sha256', '1', 'salt',
hmac_base64.decode('ascii')])
self._sql("""
WITH u AS (
INSERT INTO auth_user (
first_name, last_name, is_active, date_joined,
email, username, password, is_staff, is_superuser
)
VALUES (
'First', 'Last', TRUE, NOW(),
%(email)s, %(username)s, %(password_hash)s,
%(is_staff)s, %(is_superuser)s
)
RETURNING id, email
)
INSERT INTO account_emailaddress (
verified, "primary", user_id, email
)
SELECT TRUE, TRUE, u.id, u.email
FROM u
""",
email=email,
username=username,
password_hash=password_hash,
is_staff=is_staff,
is_superuser=is_superuser)
return UserHandle(username, password, email)
def _get_email(self, email):
'''Given an email address, check the email_remapping table to see if the email
should be sent to a different address. This function also handles overriding
the email domain if ignore_vcs_email_domain is set or the domain was missing'''
if email in self.email_remapping:
return self.email_remapping[email]
prefix, domain = email.split("@", 2)
if prefix in self.email_remapping:
return self.email_remapping[prefix]
if "." not in domain or config.ignore_vcs_email_domain:
return "%s@%s" % (prefix, config.email_domain_name)
return email
def save_developer(email):
# add if we dont exist
if not Developer.objects.filter(email=email).first():
names = email.split('.')
first_name = ""
last_name = ""
if len(names) > 1:
first_name = names[0]
last_name = names[1].split('@')[0]
dev = Developer(email=email, first_name=first_name, last_name=last_name)
dev.save()
def _validate(email):
"""validate an email field"""
if email:
if "," in email:
email = email.split(",")[-1]
if not validate_email_add(email):
# try extracting the email part and set as sender
new_email = extract_email_id(email)
if not (new_email and validate_email_add(new_email)):
webnotes.msgprint("%s is not a valid email id" % email,
raise_exception = 1)
email = new_email
return email
def __get_tokens(self, rcptto):
c = self.get_cursor()
format_strings = ','.join(['%s'] * len(rcptto))
recipients = tuple([
re.sub(r'^(drop|bucket)-comment-', r'',
email.split('@')[0]) for email in rcptto
])
c.execute(
"""select `type`, `data`
from `auth_tokens`
where token in (%s)""" % format_strings, recipients)
return [(token_type, json.loads(data))
for token_type, data in c.fetchall()]
def _validate(email):
"""validate an email field"""
if email:
if "," in email:
email = email.split(",")[-1]
if not validate_email_add(email):
# try extracting the email part and set as sender
new_email = extract_email_id(email)
if not (new_email and validate_email_add(new_email)):
webnotes.msgprint("%s is not a valid email id" % email,
raise_exception=1)
email = new_email
return email
def check_email_catchall(email):
try:
from_address = EMAIL_HOST_USER
# Get domain for DNS lookup
domain = email.split('@')[-1]
# experimental part
# we make a deliberately non-existent email with the required domain
first_part, second_part = email.split('@')
fake_email = first_part + 'ashdfabebdfjksjakuahfka' + '@' + second_part
# MX record lookup
records = dns.resolver.resolve(domain, 'MX')
mx_record = records[0].exchange
mx_record = str(mx_record)
# SMTP lib setup (use debug level for full output)
server = smtplib.SMTP()
server.set_debuglevel(0)
# SMTP Conversation
server.connect(mx_record)
server.helo(server.local_hostname
) # server.local_hostname(Get local server hostname)
server.mail(from_address)
code, message = server.rcpt(str(fake_email))
server.quit()
# Assume SMTP response 250 is success
if code == 250:
return True
else:
return False
except Exception:
return False
def get_pop3_host(email):
"""获取邮箱对应的服务商的 POP3 服务器地址"""
maps = {
'qq.com': 'pop.qq.com',
'gmail.com': 'pop.gmail.com',
'126.com': 'pop.126.com',
'163.com': 'pop.163.com',
'sohu.com': 'pop3.sohu.com',
'sina.com': 'pop3.sina.com',
'139.com': 'pop.139.com',
'foxmail.com': 'pop.foxmail.com'
}
tail = email.split('@')[1]
return maps[tail] if tail in maps else None
def save_developer(email):
# add if we dont exist
if not Developer.objects.filter(email=email).first():
names = email.split('.')
first_name = ""
last_name = ""
if len(names) > 1:
first_name = names[0]
last_name = names[1].split('@')[0]
dev = Developer(email=email,
first_name=first_name,
last_name=last_name)
dev.save()
def email_cleaning(text):
# Data cleaning
email = text.lower()
# clean and tokenize document string
email_content = email.split()
word_list = []
for i in email_content:
x = 0
if (('http' not in i) and ('@' not in i) and ('<.*?>' not in i)
and i.isalnum() and (not i in stop_words)):
word_list += [i]
return word_list
def tagEmail(self, email, tags='All', fullName=None):
newTagList = tags.split(',')
if fullName == None:
fullName = email.split('@')[0]
# trying to guess the full name.
fullName = fullName.replace('.', ' ')
fullName = fullName.replace('_', ' ')
if self.emailDict.has_key(email):
fullName, tagList = self.emailDict[email]
newTagList.extend(tagList)
newTagList = list(set(newTagList))
self.emailDict[email] = (fullName, newTagList)
def eom(self):
''' End of Message '''
self.fp.seek(0)
msg = email.message_from_file(self.fp)
msg_id = msg.get('In-Reply-To', None)
if msg_id is None:
self.log('No In-Reply-To, keep going')
return Milter.CONTINUE
# Ensure we don't get extra lines in the message-id
msg_id = msg_id.split('\n')[0].strip()
self.log('msg-ig %s' % msg_id)
self.log('To %s' % msg['to'])
self.log('Cc %s' % msg.get('cc'))
self.log('From %s' % msg['From'])
# Ensure the user replied to his/her own notification, not that
# they are trying to forge their ID into someone else's
salt = pagure.APP.config.get('SALT_EMAIL')
m = hashlib.sha512('%s%s%s' % (msg_id, salt, clean_item(msg['From'])))
email = msg['to']
if 'reply+' in msg.get('cc'):
email = msg['cc']
if not 'reply+' in email:
self.log('No valid recipient email found in To/Cc: %s' % email)
tohash = email.split('@')[0].split('+')[-1]
if m.hexdigest() != tohash:
self.log('hash: %s' % m.hexdigest())
self.log('tohash: %s' % tohash)
self.log('Hash does not correspond to the destination')
return Milter.CONTINUE
if msg['From'] and msg['From'] == pagure.APP.config.get('FROM_EMAIL'):
self.log("Let's not process the email we send")
return Milter.CONTINUE
msg_id = clean_item(msg_id)
if msg_id and '-ticket-' in msg_id:
self.log('Processing issue')
return self.handle_ticket_email(msg, msg_id)
elif msg_id and '-pull-request-' in msg_id:
self.log('Processing pull-request')
return self.handle_request_email(msg, msg_id)
else:
self.log('Not a pagure ticket or pull-request email, let it go')
return Milter.CONTINUE
def _get_email(self, email):
'''Given an email address, check the email_remapping table to see if the email
should be sent to a different address. This function also handles overriding
the email domain if ignore_vcs_email_domain is set or the domain was missing'''
if not email or "@" not in email:
return None
if email in self.email_remapping.remap:
return self.email_remapping.remap[email]
prefix, domain = email.split("@", 2)
if prefix in self.email_remapping.remap:
return self.email_remapping.remap[prefix]
if "." not in domain or config.ignore_vcs_email_domain:
return "%s@%s" % (prefix, config.email_domain_name)
return email
def valid (self, email: str, company_id: Optional[int] = None) -> None:
"""Validate an ``email'' address for ``company_id''"""
self.setup (company_id = company_id)
if not email:
raise error ('empty email')
email = email.strip ()
if not email:
raise error ('empty email (just whitespaces)')
parts = email.split ('@')
if len (parts) != 2:
raise error ('expect exactly one "@" sign')
(user, domain) = parts
self.valid_user (user)
self.valid_domain (domain)
self.check_blacklist (email, company_id)
def normalize_email(email):
if not email:
return None
result = ""
for token in email.split():
if token == "dot":
result += "."
elif token == "at":
result += "@"
else:
result += token
return result
def preprocess(emails):
"""
Performs preprocessing operations such as:
1. Removing signature lines (only English emails are supported)
2. Removing new line characters.
"""
n_emails = len(emails)
for i in range(n_emails):
email = emails[i]
email, _ = extract_signature(email)
lines = email.split('\n')
for j in reversed(range(len(lines))):
lines[j] = lines[j].strip()
if lines[j] == '':
lines.pop(j)
emails[i] = ' '.join(lines)
def signin(cls, email, type):
if not '@' in email:
raise EmailError("malformed e-mail")
hash = hashlib.md5(email).hexdigest()
image = 'http://0.gravatar.com/avatar/%s' % hash
name = string.capwords(email.split('@')[0].replace('.', ' '))
# prevents double signin...
previous_signin = db.GqlQuery("SELECT * FROM Signin WHERE email = '%s' AND active = true" % email).get()
if previous_signin:
try:
cls.deactivate_staffer(email)
except:
logging.info("Failed deactivating old Signin object.")
s = Signin(email=email, type=type, image_url=image, name=name)
s.put()
return s
def _initializePath(self, email):
basePath = os.path.join( os.environ['HOME'], 'rapp_platform_files', 'emails' )
if not os.path.exists( basePath ):
RappUtilities.rapp_print("Language temporary directory does not exist. " + \
'Path: ' + basePath)
os.makedirs( basePath )
username = email.split('@')[0]
## The temporary directory containing the configurations
finalPath = tempfile.mkdtemp( prefix=username + '_', dir = basePath)
RappUtilities.rapp_print('Email receiver path: ' + finalPath, 'DEBUG')
# Delete temp file at termination
# TODO: Check whether files are preserved long enough for the agent to collect
atexit.register(shutil.rmtree, finalPath)
return finalPath
def _initializePath(self, email):
basePath = os.path.join(os.environ['HOME'], 'rapp_platform_files',
'emails')
if not os.path.exists(basePath):
RappUtilities.rapp_print("Language temporary directory does not exist. " + \
'Path: ' + basePath)
os.makedirs(basePath)
username = email.split('@')[0]
## The temporary directory containing the configurations
finalPath = tempfile.mkdtemp(prefix=username + '_', dir=basePath)
RappUtilities.rapp_print('Email receiver path: ' + finalPath, 'DEBUG')
# Delete temp file at termination
# TODO: Check whether files are preserved long enough for the agent to collect
atexit.register(shutil.rmtree, finalPath)
return finalPath
def detect_server(email, password, ssl=True):
"Attempt to figure out the server protocol, hostname and username."
def generate_hosts(domain):
"Use heuristics to guess the valid hostname."
for hostname in HOSTNAMES:
yield '%s.%s' % (hostname, domain)
yield domain
def generate_users(email):
"Use heuristics to guess the valid username."
yield email
username = email.split('@')[0]
yield username
# TODO: try splitting on common stuff like '.' or '-'.
# TODO: this should be done in parallel. I am using a short timeout to
# minimize the overall time, but if the last combo is the winning one, it
# will have take a LONG time to find out.
username, domain = email.split('@')
protocol, hostname = None, None
# By default, try non-SSL first.
protocols = [('imap', 'pop3'), ('imaps', 'pop3s')]
if ssl:
# Reverse order, try SSL first.
protocols.reverse()
# Try hosts until we find one that works.
for imap, pop3 in protocols:
for tryhost in generate_hosts(domain):
imapclient, pop3client = PROTOCOLS[imap], PROTOCOLS[pop3]
try:
client = imapclient(tryhost)
except (imaplib.IMAP4.error, socket.error), e:
try:
client = pop3client(tryhost)
except (poplib.error_proto, socket.error), e:
continue
else:
protocol, hostname = pop3, tryhost
break
else:
protocol, hostname = imap, tryhost
break
def get_students_from_gmail( ):
# This portion downloads from the spreadsheet
try: import gspread
except ImportError:
print "Install gpsread library (on github @ https://github.com/burnash/gspread)"
print "Note - library is super easy to install!"
return
user = get_credentials()
# Login with your Google account
gc = gspread.login(user[0],user[1])
# Spreadsheets can be opened by their title in Google Docs
spreadsheet = gc.open(spreadsheet_name)
# Select worksheet by index
worksheet = spreadsheet.get_worksheet(0)
# Update cell with your form value
#worksheet.update_cell(1, 2, 'woot!')
ncells = 'A2:A' + str(num_students+1)
cell_list = worksheet.range(ncells)
names = []
for cell in cell_list:
names.append(cell.value)
ncells = 'B2:B' + str(num_students+1)
cell_list = worksheet.range(ncells)
emails = []
for cell in cell_list:
emails.append(cell.value)
tokenized_emails = []
for email in emails:
tokenized_emails.append(email.split(' '))
students = zip(names, tokenized_emails)
return students
def signin(cls, email, type):
if not '@' in email:
raise EmailError("malformed e-mail")
hash = hashlib.md5(email).hexdigest()
image = 'http://0.gravatar.com/avatar/%s' % hash
name = string.capwords(email.split('@')[0].replace('.', ' '))
# prevents double signin...
previous_signin = db.GqlQuery("SELECT * FROM Signin WHERE email = '%s' AND active = true" % email).get()
if previous_signin:
try:
cls.deactivate_staffer(email)
except:
logging.info("Failed deactivating old Signin object.")
s = Signin(email=email, type=type, image_url=image, name=name)
DailyCount.increment_and_get()
s.put()
if "xxxxx.xxxxx" in email or "yyyy.yyyy" in email:
mail.send_mail(sender="Signin Machine <*****@*****.**>", to="Emergency Paging System <*****@*****.**>",
subject="Sign-in: " + email, body="Sign in")
urlfetch.fetch("http://www.dustball.com/call/call.php?str=Sign+in+"+email)
return s
def calculateWordWeights(email,wordWeights,emailVector):
importantWordsFromEmail = {}
sum = 0
#count the number of words that are not stopwords and how often they occur
for word in email.split():
#TODO: Use regex to remove all punctuation here
if word not in stopwords:
importantWordsFromEmail[word] = importantWordsFromEmail.get(word,0)+1
sum+=1
#update the global count of each words
for word in importantWordsFromEmail.keys():
wordWeights[word] = wordWeights.get(word,0)+importantWordsFromEmail[word]
#update the total number of words
wordWeights["totalNumbers"] = wordWeights.get("totalNumbers",0) + sum
#create a vector representing the email
emailVector = vector(importantWordsFromEmail,wordWeights)
return emailVector
def calculateWordWeights(email,wordWeights,emailVector):
importantWordsFromEmail = {}
sum = 0
#count the number of words that are not stopwords and how often they occur
for word in email.split():
#TODO: Use regex to remove all punctuation here
if word not in stopwords:
importantWordsFromEmail[word] = importantWordsFromEmail.get(word,0)+1
sum+=1
#update the global count of each words
for word in importantWordsFromEmail.keys():
wordWeights[word] = wordWeights.get(word,0)+importantWordsFromEmail[word]
#update the total number of words
wordWeights["totalNumbers"] = wordWeights.get("totalNumbers",0) + sum
#create a vector representing the email
emailVector = vector(importantWordsFromEmail,wordWeights)
return emailVector
def fill_database(self, recipients_count, scheduled_start=None, scheduled_end=None, scheduled_duration=None,
real_start=None, satellite_group=None):
mq = factories.MailingFactory(satellite_group=satellite_group)
for i in range(recipients_count):
email = '*****@*****.**' % i
MailingRecipient.create(mailing=mq, email=email, domain_name=email.split('@', 1)[1],
contact=repr({'email': email, 'firstname': 'Cedric%d' % i}),
next_try=datetime.utcnow())
mq.status = MAILING_STATUS.READY
if scheduled_start:
mq.scheduled_start = scheduled_start
if scheduled_end:
mq.scheduled_end = scheduled_end
if scheduled_duration:
mq.scheduled_duration = scheduled_duration
if real_start:
mq.status = MAILING_STATUS.RUNNING
mq.start_time = real_start
mq.update_stats()
mq.save()
def __init__(self, email, password, username=None, domain=None, use_ssl=True):
# validate email
if basic_email_re.match(email):
emailparts = email.split("@")
else:
raise ImapDbException(["EMAIL-VALIDATION"])
# get the username from the email address
if not username:
username = emailparts[0]
# get the domain name from the email address
if not domain:
domain = emailparts[1]
# TODO: on failure automatically try various ways of connecting (Non-SSL, common server subdomains, etc.)
# try to connect to the IMAP server
# TODO: timeout? if you incorrectly connect to some servers with no SSL they hang
IMAPClient.__init__(self, domain, use_uid=True, ssl=use_ssl)
# try to log in with the username and password provided
try:
self.login(username, password)
# IMAPClient.Error
except Exception, e:
raise ImapDbException(["AUTH", e.message])
def create_user(self,
email: str,
username: str = None,
password: str = None) -> UserHandle:
"""Add the specified user to the database.
When done with the User, `account_admin.destroy_user(user)`
Keyword arguments:
username -- string (default user portion of email)
password -- string (default email)
"""
if username is None: username = email.split('@')[0]
if password is None: password = email
var = self._execute_setvar('\n'.join([
f'VAR = User.objects.create_user(',
f' username={repr(username)},',
f' password={repr(password)},',
f' email={repr(email)}',
f')',
]))
return UserHandle(var, username, password, email)
def check_email_valid(self, email):
"""Check if email is valid. Check @ and .
:email str
return True/False
"""
def get_validate_email(email):
if not re.match(
r"^[A-Za-z0-9\.\+_-]+@[A-Za-z0-9\._-]+\.[a-zA-Z]*$",
email):
return False
return True
if not email:
return False
emails = email.split(',')
if len(emails) > 0:
for email in emails:
if not get_validate_email(email.strip()):
return False
break
return True
def get_email_author(self, msg):
"Returns author's name and email if any"
try:
header_from = msg['From']
splits = header_from.split('<', 1)
name, email = splits if len(splits) == 2 else ('', header_from)
email = email.split('>', 1)[0]
if name:
name, encoding = decode_header(name.strip(' "\''))[0]
name = self.decode(name, encoding)
name = name.strip(' \'"')
except:
email = name = None
if not email:
try:
email = msg['Return-path']
email.strip(' \'"<>')
except Exception:
email = None
return name, email
def get_email_author(self, msg):
"Returns author's name and email if any"
try:
header_from = msg['From']
splits = header_from.split('<', 1)
name, email = splits if len(splits) == 2 else ('', header_from)
email = email.split('>', 1)[0]
if name:
name, encoding = decode_header(name.strip(' "\''))[0]
name = self.decode(name, encoding)
name = name.strip(' \'"')
except:
email = name = None
if not email:
try:
email = msg['Return-path']
email.strip(' \'"<>')
except Exception:
email = None
return name, email
def post(self):
email = self.request.get('email')
if not '@' in email:
email = '*****@*****.**' % email
if email:
hash=hashlib.md5(email).hexdigest()
# Defaults
image = 'http://0.gravatar.com/avatar/%s' % hash
name = email.split('@')[0].replace('.', ' ')
say = '%s, %s' % (random.choice(GREETINGS), name.split(' ')[0])
text = "Welcome back to Hacker Dojo, %s!" % name.split(' ')[0]
# If on staff
if 'Staff' in self.request.get('type'):
response = urlfetch.fetch('http://dojo.pbworks.com/api_v2/op/GetUserInfo/_type/jsontext/email/%s/token/%s' % (urllib.quote(email), get_token())).content
if not 'appenginebot' in response:
response = parse_json(response)
image = response['image']
name = response['name']
say = "Staff member, %s" % name
text = "Welcome back, %s. Remember to check out when you leave!" % name.split(' ')[0]
else:
# TODO: contact signup app
# if member
# say = "member" + name
# else...
# If new visitor
s = Signin.all().filter('email =', email).get()
if not s:
say = "Welcome to Hacker Dojo!"
text = "Congrats on your first visit, %s!" % name
s = Signin(email=email, type=self.request.get('type'), image_url=image, name=name)
s.put()
broadcast(text=text, say=say)
self.redirect('/')
def tokenize_to(to):
""" Parse the To field and extract elements that should be anonymized """
emails = set()
tokens = set()
# Get both aliases and email addresses
fields = TKENSEP.split(to.lower())
for token in fields:
token = clean_token(token)
if "@" in token:
emails.add(token)
elif len(token) != 0:
tokens.add(token)
# For every email address, extract element of interest (name, surname, domain…)
for email in emails:
fulluser, todom = email.split("@", 1)
for user_part in USERSEP.split(fulluser, 4):
if len(user_part) > 2:
tokens.add(user_part)
tokens.add(todom)
return tokens
def check_email(): #查看邮件也可以用IMAP服务来实现，这里用POP3 =。=
import poplib
import email
from email.parser import Parser
from email.header import decode_header
from email.utils import parseaddr
def guess_charset(msg):
# 先从msg对象获取编码:
charset = msg.get_charset()
# 如果获取不到，再从Content-Type字段获取:
if charset is None:
content_type = msg.get('Content-Type', '').lower()
pos = content_type.find('charset=')
if pos >= 0:
charset = content_type[pos + 8:].strip()
return charset
#邮件的Subject或者Email中包含的名字都是经过编码后的str，要正常显示，就必须decode
def decode_str(s):
value, charset = decode_header(s)[0]
if charset:
value = value.decode(charset)
return value
#这个Message对象本身可能是一个MIMEMultipart对象，即包含嵌套的其他MIMEBase对象，嵌套可能还不止一层。
#所以我们要递归地打印出Message对象的层次结构：
# indent用于缩进显示:
def print_info(msg, indent=0):
if indent == 0:
# 邮件的From, To, Subject存在于根对象上:
for header in ['From', 'To', 'Subject']:
value = msg.get(header, '')
if value:
# 需要解码Subject字符串:
if header=='Subject':
value = decode_str(value)
# 需要解码Email地址:
else:
hdr, addr = parseaddr(value)
name = decode_str(hdr)
value = u'%s <%s>' % (name, addr)
if header == 'From':
print(u'%s发件人：%s' % (' ' * indent, value))
elif header == 'To':
print(u'%s收件人：%s' % (' ' * indent, value))
elif header == 'Subject':
print(u'%s主题：%s' % (' ' * indent, value))
# 如果邮件对象是一个MIMEMultipart,
# get_payload()返回list，包含所有的子对象:
if (msg.is_multipart()):
parts = msg.get_payload()
for n, part in enumerate(parts):
print('%spart %s' % (' ' * indent, n))
print('%s--------------------' % (' ' * indent))
# 递归打印每一个子对象:
print_info(part, indent + 1)
# 邮件对象不是一个MIMEMultipart,
# 就根据content_type判断:
else:
content_type = msg.get_content_type()
if content_type=='text/plain' or content_type=='text/html':
# 纯文本或HTML内容:
content = msg.get_payload(decode=True)
# 要检测文本编码:
charset = guess_charset(msg)
if charset:
content = content.decode(charset)
print(u'%s正文: %s' % (' ' * indent, content + '...'))
# 不是文本,作为附件处理:
else:
print(u'%s附件: %s' % (' ' * indent, content_type))
# 输入邮件地址,密码和POP3服务器地址:
print u'请输入邮箱地址：',
email = raw_input().strip()
print u'请输入密码：',
password = pwd_input()
mail_check = (email.split('@'))[-1].split('.')[0]
pop_check = 'pop.%s.com' % mail_check
print u'已检测到您使用的是%s邮箱,已为您自动填写POP服务器地址:[%s]\n是否需要修改?[y/n]' % (mail_check,pop_check),
ifchange = raw_input()
if ifchange == 'y' or ifchange == 'Y':
print u'好的,请修改POP服务器地址'
print u'请输入POP服务器地址：',
pop_server = raw_input().strip()
else:
pop_server = pop_check
print u'是否使用SSL加密传输方式?[y/n]',
ifuserssl = raw_input()
if ifuserssl == 'y' or ifuserssl == 'Y':
print u'好的,正在使用SSL加密服务...'
else:
print u'好的,不使用SSL加密服务...'
k = 0
while True:
try:
# 连接到POP3服务器:
if ifuserssl == 'y' or ifchange == 'Y':
server = poplib.POP3_SSL(pop_server)
else:
server = poplib.POP3(pop_server)
# 可以打开或关闭调试信息:
#server.set_debuglevel(1)
# 可选:打印POP3服务器的欢迎文字:
#print(server.getwelcome())
# 身份认证:
print u'正在进行身份认证...'
server.user(email)
server.pass_(password)
print u'正在获取邮箱信息...'
# stat()返回邮件数量和占用空间:
print(u'邮件数量: %s 占用空间: %s' % server.stat())
# list()返回所有邮件的编号:
resp, mails, octets = server.list()
# 可以查看返回的列表类似['1 82923', '2 2184', ...]
#print(mails)
print u'正在获取最新一封邮件...'
# 获取最新一封邮件, 注意索引号从1开始:
resp, lines, octets = server.retr(len(mails))
#index = len(mails)
#resp,lines,octets = server.retr(index)
# lines存储了邮件的原始文本的每一行,
# 可以获得整个邮件的原始文本:
#msg_content = '\r\n'.join(lines)#
# 解析邮件:
#msg = Parser().parsestr(msg_content)#
msg = Parser().parsestr('\r\n'.join(lines))
#用POP3获取邮件其实很简单，要获取所有邮件，只需要循环使用retr()把每一封邮件内容拿到即可。
#真正麻烦的是把邮件的原始内容解析为可以阅读的邮件对象。
# 打印邮件内容:
print_info(msg)
# 慎重:可以根据邮件索引号直接从服务器删除邮件:
# server.dele(len(mails))
# 关闭连接:
server.quit()
print u'读取成功...'
print u'正在返回菜单...'
break
except:
print u'获取失败...'
k+=1
if k != 4:
print u'正在重试(第%s次)...' % str(k)
else:
print u'重试次数已达到3次,正在返回菜单...'
break
def generate_users(email):
"Use heuristics to guess the valid username."
yield email
username = email.split('@')[0]
yield username
def getMailIDs(self, mails):
self.mailIDs = []
for email in mails:
email = email.split()
self.mailIDs.append(int(email[0]))
return self.mailIDs
