def test_api():
access_token = 'access_token_here'
# get access token from: http://www.imagetyperz.com/Forms/ClientHome.aspx
ita = ImageTyperzAPI(access_token) # init imagetyperz api obj
# legacy way, will get deprecated at some point
# ita.set_user_password('your_username', 'your_password')
# check account balance
# ---------------------------
balance = ita.account_balance() # get account balance
print('Balance: {}'.format(balance)) # print balance
# solve image captcha
# --------------------
# works with URL as well, if authenticated with token
print('Solving captcha ...')
captcha_text = ita.solve_captcha('captcha.jpg')
# optional parameters for image captcha
# captcha_text = ita.solve_captcha('captcha.jpg', is_case_sensitive = False, is_phrase = False, digits_only = False, letters_only = True, is_math = False, min_length = 2, max_length = 10)
print('Captcha text: {}'.format(captcha_text))
# solve recaptcha
# check https://github.com/imagetyperz-api/API-docs#submit-recaptcha for more details
# -----------------------------------------------------------------------------------------------
recaptcha_params = {
'page_url':
'page_url_here', # add --capy or --hcaptcha at the end, to submit capy or hCaptcha
'sitekey': 'sitekey_here',
'type':
1, # optional, 1 - normal recaptcha, 2 - invisible recaptcha, 3 - v3 recaptcha, default: 1
#'v3_min_score' : .3, # optional
#'v3_action' : 'homepage', # optional
#'proxy': '126.45.34.53:345', # or 126.45.34.53:123:joe:password
#'user_agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0', # optional
#'data-s': 'data-s-value-here' # optional
}
captcha_id = ita.submit_recaptcha(
recaptcha_params) # submit captcha first, to get ID
# check if it's still in progress (waiting to be solved), every 10 seconds
print('Waiting for recaptcha to be solved ...')
while ita.in_progress(): # while it's still in progress
sleep(10) # sleep for 10 seconds and recheck
recaptcha_response = ita.retrieve_recaptcha(
captcha_id
) # captcha_id is optional, if not given, will use last captcha id submited
print('Recaptcha response: {}'.format(
recaptcha_response)) # print google response
def solve_captcha(URL_CAPTCHA, SITEKEY):
access_token = CONFIG[
'CAPTCHA_CREDENTIALS'] # Get the credential token to imagetyperZ
ita = ImageTyperzAPI(access_token) # Connect to imagetyperZ API
recaptcha_params = {
'page_url': URL_CAPTCHA,
'sitekey': SITEKEY,
'proxy': '126.45.34.53:345',
}
captcha_id = ita.submit_recaptcha(
recaptcha_params) # Creates a task to imagetyperZ
while ita.in_progress(): # Wait imagetyperz response
time.sleep(2)
recaptcha_response = ita.retrieve_recaptcha(
captcha_id) # Gets the response
return recaptcha_response
def test_api():
access_token = 'access_token_here'
# get access token from: http://www.imagetyperz.com/Forms/ClientHome.aspx
ita = ImageTyperzAPI(access_token) # init imagetyperz api obj
# check account balance
balance = ita.account_balance() # get account balance
print('Balance: {}'.format(balance)) # print balance
captcha_params = {
'page_url': 'https://your-site.com',
'sitekey': '7LrGJmcUABBAALFtIb_FxC0LXm_GwOLyJAfbbUCL',
# reCAPTCHA type(s) - optional, defaults to 1
# ---------------------------------------------
# 1 - v2
# 2 - invisible
# 3 - v3
# 4 - enterprise v2
# 5 - enterprise v3
#
# 'type' : 1,
#
# #'v3_min_score' : .3, # optional
# #'v3_action' : 'homepage', # optional
# #'proxy': '126.45.34.53:345', # or 126.45.34.53:123:joe:password
# #'user_agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0', # optional
# #'data-s': 'data-s-value-here' # optional
# #'cookie_input': 'a=b;c=d' # optional
}
captcha_id = ita.submit_recaptcha(captcha_params) # submit captcha first, to get ID
# check if it's still in progress (waiting to be solved), every 10 seconds
print('Waiting for captcha to be solved ...')
response = None
while not response: # while it's still in progress
sleep(10) # sleep for 10 seconds and recheck
response = ita.retrieve_response(captcha_id)
print('Response: {}'.format(response)) # print response of captcha
print('Balance: {}'.format(balance))
recaptcha_params = {
'page_url':
'https://www.receita.fazenda.gov.br/PessoaJuridica/CNPJ/cnpjreva/cnpjreva_solicitacao2.asp',
'sitekey':
'6LcT2zQUAAAAABRp8qIQR2R0Y2LWYTafR0A8WFbr',
'type':
2, # optional, 1 - normal recaptcha, 2 - invisible recaptcha, 3 - v3 recaptcha, default: 1
'v3_min_score':
.3, # optional
'v3_action':
'homepage', # optional
'proxy':
'126.45.34.53:345', # or 126.45.34.53:123:joe:password
'user_agent':
'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0' # optional
}
captcha_id = ita.submit_recaptcha(recaptcha_params)
# print balance
# check if it's still in progress (waiting to be solved), every 10 seconds
while ita.in_progress(): # while it's still in progress
time.sleep(10) # sleep for 10 seconds and recheck
recaptcha_response = ita.retrieve_recaptcha(
captcha_id
) # captcha_id is optional, if not given, will use last captcha id submited
print('Recaptcha response: {}'.format(
recaptcha_response)) # print google response
def shopify_gen(website, email):
# if shopify_check(website) == False:
# return "ERROR, NOT A VALID SHOPIFY URL"
firstname = names.get_first_name()
lastname = names.get_last_name()
randomnums = random.randint(100, 2000)
email = firstname + lastname + str(randomnums) + email
data = {
'form_type': 'create_customer',
'utf8': '',
'customer[first_name]': firstname,
'customer[last_name]': lastname,
'customer[email]': email,
'customer[password]': password,
}
if website.endswith('/') == False:
account_url = website + '/account'
challenge_url = website + '/challenge'
else:
account_url = website + 'account'
challenge_url = website + 'challenge'
pass
session = requests.session()
submit_account = session.post(account_url, data=data, headers=headers)
if submit_account.url == challenge_url:
print('CAPTCHA REQUESTED, PLEASE WAIT...\n')
sitekey = '6LeoeSkTAAAAAA9rkZs5oS82l69OEYjKRZAiKdaF'
captcha_url = website
api_key = captcha_api
ita = ImageTyperzAPI(captcha_api) # init imagetyperz api obj
recaptcha_params = {
'page_url': captcha_url,
'sitekey': sitekey,
'type': 1
} # optional, 1 - normal recaptcha, 2 - invisible recaptcha, 3 - v3 recaptcha, default: 1
auth_token = find_auth_token(submit_account.text)
captcha_id = ita.submit_recaptcha(recaptcha_params)
try:
while ita.in_progress():
print('waiting for captcha...')
sleep(10)
except:
print("Took too long to solve captcha")
return ("Took too long to solve captcha")
recaptcha_response = ita.retrieve_recaptcha(captcha_id)
print('Recaptcha response: {}'.format(recaptcha_response))
captcha_data = {
'utf-8': '',
'authenticity_token': auth_token,
'g-recaptcha-response': recaptcha_response
}
submit_captcha = session.post(account_url,
data=captcha_data,
headers=headers,
verify=False)
if submit_captcha.status_code == 200 or 302 \
and submit_captcha.url != challenge_url:
return email + ':' + password
else:
return 'ERROR'
else:
return email + ':' + password
class RoboBrasilia():
path = '/home/files/BRASILIA/{}/{}/'.format(datetime.now().strftime('%d_%m_%y'),
datetime.now().strftime('%H%M%S%f'))
planilha = '/home/henrique/Planilhas/fazendaBrasilia2.xls'
consultar_anos_anteriores = True
log = logging.basicConfig(format='%(asctime)s %(message)s', datefmt='%d/%m/%Y %H:%M:%S',
filename='brasilia.log',
level=logging.INFO)
def __init__(self):
workbook = xlrd.open_workbook(self.planilha)
worksheet = workbook.sheet_by_index(0)
imovels = []
# con = Connection('localhost','imob','postgres','P2a3u0l9')
keys = [v.value for v in worksheet.row(0)]
for row_number in range(worksheet.nrows):
if row_number == 0:
continue
row_data = {}
for col_number, cell in enumerate(worksheet.row(row_number)):
row_data[keys[col_number]] = str(cell.value).replace('.0', '')
# con.insertParametro(row_data, '00000000000000')
imovels.append(row_data)
quantidade_imovels = len(imovels)
logging.info(str(quantidade_imovels) + " Imoveis para processamento")
try:
self.captcha = ImageTyperzAPI(token.TOKEN)
print(self.captcha.account_balance())
options = Options()
# options.headless = True
driver = webdriver.Firefox(options=options)
contador = 0
for imovel in imovels:
self.create_file(self.path + "/boletos")
try:
logging.info('Processando {} {} de {}'.format(imovel, contador, quantidade_imovels))
if self.efetuar_login(driver, imovel):
imovel['faturas'] = []
imovel['status'] = 'COM DÉBITO'
wait = WebDriverWait(driver, 10)
wait.until(
cond.element_to_be_clickable((By.XPATH, '//button/span[contains(text()," Imprimir ")]')))
while True:
btns_imprimir = driver.find_elements_by_xpath(
"//button/span[contains(text(),' Imprimir ')]")
aba_atual = driver.window_handles[0]
for btn_imprimir in btns_imprimir:
try:
btn_imprimir.click()
if len(driver.find_elements_by_xpath("//*[contains(@id,'cdk-overlay-')]")) >= 1:
driver.find_element_by_xpath("//button[text()='Confirmar']").click()
wait.until(cond.new_window_is_opened)
driver.switch_to.window(driver.window_handles[1])
wait.until(cond.text_to_be_present_in_element(
(By.XPATH, '//*[@id="htmlDar"]/div/button/strong'),
'Imprimir'))
wait.until(cond.invisibility_of_element_located((By.XPATH,
'//*[contains(@class,"mat-progress-spinner-indeterminate-animation")]')))
self.extrair_dados(driver, imovel)
except Exception as py_ex:
logging.error(py_ex)
logging.error(py_ex.args)
finally:
driver.close()
driver.switch_to.window(aba_atual)
btn_next = driver.find_element_by_xpath(
"//button[contains(@class,'mat-paginator-navigation-next')]")
if btn_next.is_enabled():
btn_next.click()
else:
break
except Exception as py_ex:
imovel['status'] = 'REPROCESSAR'
logging.error(py_ex)
logging.error(py_ex.args)
logging.info(imovel)
contador += 1
except Exception as py_ex:
logging.error(py_ex)
logging.error(py_ex.args)
finally:
driver.quit()
fildnames = ['codImovel', 'inscricao', 'status']
for imovel in imovels:
try:
for field in [*imovel['faturas'][0]]:
fildnames.append(field)
break
except:
pass
try:
workbook = xlwt.Workbook()
worksheet = workbook.add_sheet(u'Resultado')
cabecalhoFatura = ['Nome ou Razão Social',
'CPF/CNPJ', 'Endereço', 'Vencimento', 'Cod. Barras', 'Cod Receita',
'Cota ou Refer', 'Exercício', 'Valor', 'Multa', 'Juros', 'Outros', 'Valor Total',
'Tributo']
cabecalhoImovel = ['codigoImovel', 'numeroContrato', 'inscricao', 'status']
for i, val in enumerate(cabecalhoImovel + cabecalhoFatura):
worksheet.write(0, i, val)
novaLinha = 1;
for imovel in imovels:
if ('NUMERO DA INSCRICAO DE IMOVEL INCORRETO' == imovel['status'] or imovel['faturas'] is None):
for i, val in enumerate(cabecalhoImovel):
worksheet.write(novaLinha, i, imovel[val])
novaLinha += 1
else:
for fatura in imovel['faturas']:
for i, val in enumerate(cabecalhoImovel):
worksheet.write(novaLinha, i, imovel[val])
for i, val in enumerate(cabecalhoFatura):
worksheet.write(novaLinha, i + 4, fatura[val])
novaLinha += 1
workbook.save(self.path + '/resultado.xls')
except IOError as e:
logging.error(e)
logging.error(e.args)
print("I/O error")
def extrair_dados(self, driver, imovel):
time.sleep(0.5)
fatura = {}
text = driver.find_element_by_xpath("//body").text
fatura['Cod Receita'] = self.find('Cod Receita (.+?)\\n', text, 1)
fatura['Cota ou Refer'] = self.find('Refer. (.+?)\\n', text, 1)
fatura['Vencimento'] = self.find('Vencimento. (.+?)\\n', text, 1)
fatura['Exercício'] = self.find('Exercício. (.+?)\\n', text, 1)
fatura['CPF/CNPJ'] = self.find('CPF/CNPJ (.+?)\\n', text, 1)
fatura['Valor'] = self.find('Principal - R\\$ (.+?)\\n', text, 1)
fatura['Multa'] = self.find('Multa - R\\$ (.+?)\\n', text, 1)
fatura['Juros'] = self.find('Juros - R\\$ (.+?)\\n', text, 1)
fatura['Outros'] = self.find('Outros - R\\$ (.+?)\\n', text, 1)
fatura['Valor Total'] = self.find('Valor Total - R\\$ (.+?)\\n', text, 1)
fatura['Cod. Barras'] = self.find('\\n(.+?)\\n01.CF/DF', text, 1).replace(' ', '')
fatura['Nome ou Razão Social'] = self.find('Razão Social\\n(.+?)\\n', text, 1)
fatura['Endereço'] = self.find('Endereço\n(.+?)\\n', text, 1)
tributos = {}
if self.find('VLR IPTU: (.+?)\\n', text, 1) != None:
tributos['IPTU'] = self.find('VLR IPTU: (.+?)\\n', text, 1)
if self.find('VLR TLP : (.+?)\\n', text, 1) != None:
tributos['LIXO'] = self.find('VLR TLP : (.+?)\\n', text, 1)
fatura['Tributo'] = '/'.join([*tributos])
file_name = '{}_{}_{}.pdf'.format(imovel['codigoImovel'], imovel['inscricao'],
fatura['Cota ou Refer'])
file_name = re.sub(r"/", "-", file_name)
self.gera_pdf(driver, file_name)
imovel['faturas'].append(fatura)
return imovel
def gera_pdf(self, driver, file_name):
img = Image.open(BytesIO(driver.find_element_by_tag_name('body').screenshot_as_png))
rgb = Image.new('RGB', img.size, (255, 255, 255))
rgb.paste(img, mask=img.split()[3])
rgb.save(self.path + "/boletos/" + file_name, "PDF", quality=100)
def efetuar_login(self, driver, imovel):
driver.get("https://ww1.receita.fazenda.df.gov.br/emissao-segunda-via/iptu")
inscricao_input = driver.find_element_by_id('mat-input-0')
inscricao_input.send_keys(imovel['inscricao'])
if self.consultar_anos_anteriores:
driver.find_element_by_id('exercicio').click()
driver.find_element_by_id('mat-option-1').click()
self.resolve_captcha(driver)
consultar_btn = driver.find_element_by_xpath("//button[@color='primary']")
consultar_btn.click()
time.sleep(3)
try:
mensagem = driver.find_element_by_xpath('//*[contains(@class ,"alert-info")]|//*[contains(@id ,"mat-error")]').text
if 'NAO EXISTEM DEBITOS PARA ESSE IMOVEL' in mensagem:
imovel['status'] = 'NÃO POSSUI DÉBITOS'
else :
imovel['status'] = 'NUMERO DA INSCRICAO DE IMOVEL INCORRETO'
return False
except:
return True
def create_file(self, path):
if not os.path.isdir(path):
os.makedirs(path)
print('Pasta criada')
def find(self, regex, text, group, flag=0):
search = re.search(regex, text, flag)
try:
return search.group(group)
except Exception as e:
return None
def resolve_captcha(self, driver):
data = {
'page_url': 'https://ww1.receita.fazenda.df.gov.br/emissao-segunda-via/iptu',
'sitekey': '6LfqGcIUAAAAAL_iFUaRq21hMxF9-AyZst-UQ9ly',
'type': 2
}
captcha_id = self.captcha.submit_recaptcha(data)
contador = 0
while self.captcha.in_progress(captcha_id):
time.sleep(10)
contador += 10
logging.info('{}s Esperando Recaptcha'.format(contador))
recaptcha_response = self.captcha.retrieve_recaptcha(captcha_id)
print('Recaptcha response: {}'.format(recaptcha_response))
query = "document.getElementById('recaptcha-token').innerHTML = '{}';".format(recaptcha_response)
query2 = "document.getElementById('g-recaptcha-response').innerHTML = '{}';".format(recaptcha_response)
driver.execute_script(query2)
driver.switch_to.frame(driver.find_element_by_xpath('//iframe'))
driver.execute_script(query)
driver.find_element_by_xpath("//span[@id='recaptcha-anchor']").click()
driver.switch_to.default_content()
time.sleep(3)