def handle(self, *args, **options):
gen = DocumentGenerator()
user_count = 1
index = 1
num_notes = None
user = None
while True:
if index == 1:
user = User.objects.create_user(
email=f'{user_count}@email.com')
num_notes = random.randint(20, 100)
elif index > num_notes:
index = 1
user_count += 1
print(f'Created Notes for User [{user_count}/10000]', end='\r')
continue
note = Note.objects.create(user=user,
title=gen.sentence(),
content=gen.paragraph())
note.tags = gen.word()
index += 1
self.stdout.write(self.style.SUCCESS('Successfully loaded data'))
class WordGenerator:
def __init__(self):
self.gen = DocumentGenerator()
def next_sentence(self):
return self.gen.sentence()
def nect_word(self):
return self.gen.word()
class TestCaseGenerator:
def __init__(
self,
sample_letters=None,
enabled_repetition=False,
enabled_alphanumeric=False,
enabled_special_character=False,
):
self.gen = DocumentGenerator()
self.sample_letters = sample_letters
self.enabled_repetition = enabled_repetition
self.enabled_alphanumeric = enabled_alphanumeric
self.enabled_special_character = enabled_special_character
def parametric_test_case_init(self):
if self.sample_letters == None:
if self.enabled_special_character:
self.sample_letters = (string.ascii_letters + string.digits +
string.punctuation)
elif self.enabled_alphanumeric:
self.sample_letters = string.ascii_letters + string.digits
else:
self.sample_letters = string.ascii_letters
def generate_random_number(self, digits=None):
range_start = 10**(digits - 1)
range_end = (10**digits) - 1
return random.randint(range_start, range_end)
# print(self.test_case_gen.generate_random_number(digits=4))
def generate_random_useful_word(self, length=None):
return self.gen.word()
# print(self.test_case_gen.generate_random_useful_word())
def generate_random_useless_word(self, length=None):
if self.enabled_repetition:
self.parametric_test_case_init()
sample_list = list(self.sample_letters)
random.shuffle(sample_list)
final_string = "".join(sample_list)
return final_string
else:
return "".join(random.sample(self.sample_letters, length))
# print(self.test_case_gen.generate_random_useless_word())
def generate_random_sentence(self):
return self.gen.sentence()
# print(self.test_case_gen.generate_random_sentence())
def generate_random_paragraph(self):
return self.gen.paragraph()
# print(self.test_case_gen.generate_random_paragraph())
def generate_random_choice_from_list(self, col, choices):
return random.sample(col, choices)
def generate_games(file):
print("Start generating Games")
file.write("\n\n*****************************model Games*****************************\n")
file.write("name,description,price,systemRequirements,creatorID\n")
word_site = "http://svnweb.freebsd.org/csrg/share/dict/words?view=co&content-type=text/plain"
response = requests.get(word_site)
gen = DocumentGenerator()
for i in range(NUM_OF_GAMES):
game_name = ""
num_of_word_in_name_game = randint(1,3)
for j in range(num_of_word_in_name_game):
game_name += gen.word()
game_name =remove_enter(game_name)
game_description =gen.sentence()
game_description = remove_enter(game_description)
game_system_requirements = gen.word()
game_system_requirements = remove_enter(game_system_requirements)
game_price = round(random.uniform(5.5,1000.5),2)
creator_id =randint(1,NUM_OF_CREATORS)
file.write(str(game_name)+","+str(game_description)+","+str(game_price)+","+str(game_system_requirements)+","+str(creator_id)+"\n")
print("End generating Games")
clean = [f.get() for f in futures]
for c in clean:
if c is not None:
scraper_sessions[c.proxy] = c
if len(scraper_sessions) > 0:
print(len(scraper_sessions))
c = 0
while True:
thread_pool = Pool(pool_size)
futures = list()
r = random.choice([gen.email(), gen.word()+gen.word(), gen.name()+gen.word()+gen.word()])
#r = get_random_string(random.randrange(120, 500))
request_data = {"doAuth": "1", "login": r.replace(" ", ""), "password": gen.word()+gen.word()+str(gen.small_int())}
for i in range(pool_size):
if proxy_index < len(proxies):
proxy = proxies[proxy_index]
proxy_index += 1
else:
proxy = proxies[0]
proxy_index = 1
if proxy in scraper_sessions:
futures.append(thread_pool.apply_async(post_proxy, [url, proxy, request_data, proxies, (None, scraper_sessions[proxy])[cloudflare]]))
clean = [f.get() for f in futures]
for x in clean:
type = input(Fore.BLACK +
' [1] SINGLE EMAIL \n [2] MULTIPLE EMAILS \n [3] QUIT \n')
if type == '1':
try:
many = input('ENTER VICTIM EMAIL: ')
numbers = input('HOW MANY EMAILS: ')
if '@' in many:
print('RUNNING.....')
options = Options()
options.headless = True
web = webdriver.Chrome()
numbers1 = 0
for x in range(int(numbers)):
emailss = gen.word()
#print(emailss)
addition = random.randint(00000, 99999)
email = emailss + str(addition) + '@hotmail.com'
numbers1 += 1
web.get('https://emkei.cz/')
web.find_element_by_xpath('//*[@id="fromname"]').send_keys(
'Marcus')
web.find_element_by_xpath('//*[@id="from"]').send_keys(
email)
web.find_element_by_xpath('//*[@id="rcpt"]').send_keys(
many)
web.find_element_by_xpath('//*[@id="subject"]').send_keys(
'Park Meeting')
web.find_element_by_xpath('//*[@id="text"]').send_keys(
dt.date(2021, 1, 1) + dt.timedelta(days=rd.randrange(0, 30))
for _ in range(num_ads)
],
'LSH label': [label_num for _ in range(num_ads)]
})
dfs = []
num_ads = 0
cluster_label = 0
city_ids = get_city_ids(2)
for metacluster in range(2):
gen = DocumentGenerator()
metadata_dict = {
'phones': [gen.phone() for _ in range(rd.randrange(1, 20))],
'images':
[rd.randrange(10000, 99999) for _ in range(rd.randrange(1, 20))],
'social': [gen.word() for _ in range(rd.randrange(1, 20))],
'emails': [gen.email() for _ in range(rd.randrange(1, 20))]
}
for _ in range(rd.randrange(10, 15)):
cluster_size = rd.randrange(20, 100)
print(metacluster, cluster_size)
dfs.append(
gen_cluster(num_ads, cluster_size, cluster_label, city_ids,
metadata_dict))
cluster_label += 1
num_ads += cluster_size
pd.concat(dfs).to_csv('data/synthetic_data.csv', index=False)
def generate_key():
gen = DocumentGenerator()
return gen.word()
