Skip to content

Adds ability to run parallel windows with multiprocessing #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
BigweldIndustries wants to merge 2 commits into from
Closed

Adds ability to run parallel windows with multiprocessing #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e6245a5
Add multiproccessing
BigweldIndustries Dec 12, 2021
9971eb0
Fixed for latest version
BigweldIndustries Dec 15, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
251 changes: 120 additions & 131 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,124 +1,60 @@
import requests
import functools
import os
import subprocess
import random
import re
import sys
import time
import argparse
from selenium.webdriver.chrome import options

import speech_recognition as sr
from faker import Faker
from selenium import webdriver
from selenium.webdriver.support.ui import Select
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.ui import Select, WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from resume_faker import make_resume
from pdf2image import convert_from_path

from webdriver_manager.chrome import ChromeDriverManager
os.environ['WDM_LOG_LEVEL'] = '0'

from concurrent.futures import ThreadPoolExecutor
executor = ThreadPoolExecutor(max_workers=500)
processes = []

from constants.common import *
from constants.fileNames import *
from constants.classNames import *
from constants.elementIds import *
from constants.email import *
from constants.location import *
from constants.parser import *
from constants.urls import *
from constants.xPaths import *

os.environ["PATH"] += ":/usr/local/bin" # Adds /usr/local/bin to my path which is where my ffmpeg is stored

fake = Faker()

# Change default in module for print to flush
# Add printf: print with flush by default. This is for python 2 support.
# https://stackoverflow.com/questions/230751/how-can-i-flush-the-output-of-the-print-function-unbuffer-python-output#:~:text=Changing%20the%20default%20in%20one%20module%20to%20flush%3DTrue
print = functools.partial(print, flush=True)

r = sr.Recognizer()

def audioToText(mp3Path):
# deletes old file
try:
os.remove(CAPTCHA_WAV_FILENAME)
except FileNotFoundError:
pass
# convert wav to mp3
subprocess.run(f"ffmpeg -i {mp3Path} {CAPTCHA_WAV_FILENAME}", shell=True, timeout=5)

with sr.AudioFile(CAPTCHA_WAV_FILENAME) as source:
audio_text = r.listen(source)
try:
text = r.recognize_google(audio_text)
print('Converting audio transcripts into text ...')
return(text)
except Exception as e:
print(e)
print('Sorry.. run again...')
printf = functools.partial(print, flush=True)

def saveFile(content,filename):
with open(filename, "wb") as handle:
for data in content.iter_content():
handle.write(data)
#Option parsing
parser = argparse.ArgumentParser(SCRIPT_DESCRIPTION,epilog=EPILOG)
parser.add_argument('--debug',action='store_true',default=DEBUG_DISABLED,required=False,help=DEBUG_DESCRIPTION,dest='debug')
parser.add_argument('--mailtm',action='store_true',default=MAILTM_DISABLED,required=False,help=MAILTM_DESCRIPTION,dest='mailtm')
args = parser.parse_args()
# END TEST

def solveCaptcha(driver):
# Logic to click through the reCaptcha to the Audio Challenge, download the challenge mp3 file, run it through the audioToText function, and send answer
googleClass = driver.find_elements_by_class_name(CAPTCHA_BOX)[0]
time.sleep(2)
outeriframe = googleClass.find_element_by_tag_name('iframe')
time.sleep(1)
outeriframe.click()
time.sleep(2)
allIframesLen = driver.find_elements_by_tag_name('iframe')
time.sleep(1)
audioBtnFound = False
audioBtnIndex = -1
for index in range(len(allIframesLen)):
driver.switch_to.default_content()
iframe = driver.find_elements_by_tag_name('iframe')[index]
driver.switch_to.frame(iframe)
driver.implicitly_wait(2)
try:
audioBtn = driver.find_element_by_id(RECAPTCHA_AUDIO_BUTTON) or driver.find_element_by_id(RECAPTCHA_ANCHOR)
audioBtn.click()
audioBtnFound = True
audioBtnIndex = index
break
except Exception as e:
pass
if audioBtnFound:
try:
while True:
href = driver.find_element_by_id(AUDIO_SOURCE).get_attribute('src')
response = requests.get(href, stream=True)
saveFile(response, CAPTCHA_MP3_FILENAME)
response = audioToText(CAPTCHA_MP3_FILENAME)
print(response)
driver.switch_to.default_content()
iframe = driver.find_elements_by_tag_name('iframe')[audioBtnIndex]
driver.switch_to.frame(iframe)
inputbtn = driver.find_element_by_id(AUDIO_RESPONSE)
inputbtn.send_keys(response)
inputbtn.send_keys(Keys.ENTER)
time.sleep(2)
errorMsg = driver.find_elements_by_class_name(AUDIO_ERROR_MESSAGE)[0]
if errorMsg.text == "" or errorMsg.value_of_css_property('display') == 'none':
print("reCaptcha defeated!")
break
except Exception as e:
print(e)
print('Oops, something happened. Check above this message for errors or check the chrome window to see if captcha locked you out...')
else:
print('Button not found. This should not happen.')

time.sleep(2)
driver.switch_to.default_content()

def start_driver(random_city):
driver = webdriver.Chrome(ChromeDriverManager().install())
def initialize_driver(random_city, driver):
driver.get(CITIES_TO_URLS[random_city])
driver.implicitly_wait(10)
time.sleep(2)
time.sleep(15)
#WebDriverWait(driver, 10).until(expected_conditions.presence_of_element_located((By.XPATH, CREATE_AN_ACCOUNT_BUTTON)))
driver.find_element_by_xpath(APPLY_NOW_BUTTON_1).click()
driver.find_element_by_xpath(APPLY_NOW_BUTTON_2).click()
driver.find_element_by_xpath(CREATE_AN_ACCOUNT_BUTTON).click()
Expand All @@ -130,18 +66,18 @@ def generate_account(driver, fake_identity):

email = fake.free_email()
password = fake.password()

for key in XPATHS_2.keys():
match key:
case 'email' | 'email-retype':
info = fake_identity['email']
case 'pass' | 'pass-retype':
info = password
case 'first_name':
info = fake_identity['first_name']
case 'last_name':
info = fake_identity['last_name']
case 'pn':
info = fake.phone_number()
if key in ('email', 'email-retype'):
info = fake_identity['email']
elif key in ('pass', 'pass-retype'):
info = password
elif key == 'first_name':
info = fake_identity['first_name']
elif key == 'last_name':
info = fake_identity['last_name']
elif key == 'pn':
info = fake.phone_number()

driver.find_element_by_xpath(XPATHS_2.get(key)).send_keys(info)

Expand All @@ -155,46 +91,67 @@ def generate_account(driver, fake_identity):
time.sleep(1.5)
driver.find_element_by_xpath(ACCEPT_BUTTON).click()
time.sleep(2)
solveCaptcha(driver)
driver.find_element_by_xpath(CREATE_ACCOUNT_BUTTON).click()
time.sleep(1.5)
for i in range(120):
time.sleep(1.5)
if (args.mailtm == MAILTM_DISABLED):
mail = requests.get(f'https://api.guerrillamail.com/ajax.php?f=check_email&seq=1&sid_token={fake_identity.get("sid")}').json().get('list')

print(f"successfully made account for fake email {email}")
if mail:
passcode = re.findall('(?<=n is ).*?(?=<)', requests.get(f'https://api.guerrillamail.com/ajax.php?f=fetch_email&email_id={mail[0].get("mail_id")}&sid_token={fake_identity.get("sid")}').json().get('mail_body'))[0]
break

elif (args.mailtm == MAILTM_ENABLED):
mail = requests.get("https://api.mail.tm/messages?page=1", headers={'Authorization':f'Bearer {fake_identity.get("sid")}'}).json().get('hydra:member')

def fill_out_application_and_submit(driver, random_city, fake_identity):
driver.implicitly_wait(10)
if mail:
passcode = re.findall('(?<=n is ).*', requests.get(f'https://api.mail.tm{mail[0].get("@id")}', headers={'Authorization':f'Bearer {fake_identity.get("sid")}'}).json().get('text'))[0]
break
else:
args.mailtm ^= True
main() # I should probably find a better way to do this.

driver.find_element_by_xpath(VERIFY_EMAIL_INPUT).send_keys(passcode)
driver.find_element_by_xpath(VERIFY_EMAIL_BUTTON).click()

printf(f"successfully made account for fake email {email}")


def fill_out_application_and_submit(driver, random_city, fake_identity):
# make resume
resume_filename = fake_identity['last_name']+'-Resume'
make_resume(fake_identity['first_name']+' '+fake_identity['last_name'], fake_identity['email'], resume_filename+'.pdf')
images = convert_from_path(resume_filename+'.pdf')
images[0].save(resume_filename+'.png', 'PNG')

# wait for page to load
WebDriverWait(driver, 10).until(expected_conditions.presence_of_element_located((By.XPATH, PROFILE_INFORMATION_DROPDOWN)))

# fill out form parts of app
driver.find_element_by_xpath(PROFILE_INFORMATION_DROPDOWN).click()
driver.find_element_by_xpath(CANDIDATE_SPECIFIC_INFORMATION_DROPDOWN).click()

for key in XPATHS_1.keys():

match key:
case 'resume':
driver.find_element_by_xpath(UPLOAD_A_RESUME_BUTTON).click()
info = os.getcwd() + '/'+resume_filename+'.png'
case 'addy':
info = fake.street_address()
case 'city':
info = random_city
case 'zip':
info = CITIES_TO_ZIP_CODES[random_city]
case 'job':
info = fake.job()
case 'salary':
info = random.randint(15, 35)
if key == 'resume':
driver.find_element_by_xpath(UPLOAD_A_RESUME_BUTTON).click()
info = os.getcwd() + '/'+resume_filename+'.png'
elif key == 'addy':
info = fake.street_address()
elif key == 'city':
info = random_city
elif key == 'zip':
info = CITIES_TO_ZIP_CODES[random_city]
elif key == 'job':
info = fake.job()
elif key == 'salary':
first = random.randrange(15000, 30000, 5000)
info = f'{format(first, ",")}-{format(random.randrange(first + 5000, 35000, 5000), ",")}'

driver.find_element_by_xpath(XPATHS_1.get(key)).send_keys(info)

print(f"successfully filled out app forms for {random_city}")
printf(f"successfully filled out app forms for {random_city}")

# fill out dropdowns
select = Select(driver.find_element_by_id(CITIZEN_QUESTION_LABEL))
Expand Down Expand Up @@ -227,7 +184,7 @@ def fill_out_application_and_submit(driver, random_city, fake_identity):

time.sleep(5)
driver.find_element_by_xpath(APPLY_BUTTON).click()
print(f"successfully submitted application")
printf(f"successfully submitted application")

# take out the trash
os.remove(resume_filename+'.pdf')
Expand All @@ -238,53 +195,74 @@ def random_email(name=None):
name = fake.name()

mailGens = [lambda fn, ln, *names: fn + ln,
lambda fn, ln, *names: fn + "." + ln,
lambda fn, ln, *names: fn + "_" + ln,
lambda fn, ln, *names: fn[0] + "." + ln,
lambda fn, ln, *names: fn[0] + "_" + ln,
lambda fn, ln, *names: fn + ln + str(int(1 / random.random() ** 3)),
lambda fn, ln, *names: fn + "." + ln + str(int(1 / random.random() ** 3)),
lambda fn, ln, *names: fn + "_" + ln + str(int(1 / random.random() ** 3)),
lambda fn, ln, *names: fn[0] + "." + ln + str(int(1 / random.random() ** 3)),
lambda fn, ln, *names: fn[0] + "_" + ln + str(int(1 / random.random() ** 3)), ]

emailChoices = [float(line[2]) for line in EMAIL_DATA]

return random.choices(mailGens, MAIL_GENERATION_WEIGHTS)[0](*name.split(" ")).lower() + "@" + \
random.choices(EMAIL_DATA, emailChoices)[0][1]
requests.get('https://api.mail.tm/domains').json().get('hydra:member')[0].get('domain')

def run():
try:
options = Options()
if (args.debug == DEBUG_DISABLED):
options.add_argument(f"user-agent={USER_AGENT}")
options.add_argument('disable-blink-features=AutomationControlled')
options.headless = True
driver = webdriver.Chrome(ChromeDriverManager().install(),options=options)
driver.set_window_size(1440, 900)
elif (args.debug == DEBUG_ENABLED):
driver = webdriver.Chrome(ChromeDriverManager().install())
except:
print(f"FAILED TO START DRIVER: {e}")
# No pass, this error is fatal


def main():
while True:
random_city = random.choice(list(CITIES_TO_URLS.keys()))
try:
driver = start_driver(random_city)
initialize_driver(random_city, driver)
except Exception as e:
print(f"FAILED TO START DRIVER: {e}")
print(f"FAILED TO INITIALIZE DRIVER: {e}")
pass

time.sleep(2)

fake_first_name = fake.first_name()
fake_last_name = fake.last_name()
fake_email = random_email(fake_first_name+' '+fake_last_name)
if (args.mailtm == MAILTM_DISABLED):
printf(f"USING GUERRILLA TO CREATE EMAIL")
response = requests.get('https://api.guerrillamail.com/ajax.php?f=get_email_address').json()

fake_email = response.get('email_addr')
mail_sid = response.get('sid_token')
printf(f"EMAIL CREATED")

elif (args.mailtm == MAILTM_ENABLED):
printf(f"USING MAILTM TO CREATE EMAIL")
fake_email = requests.post('https://api.mail.tm/accounts', data='{"address":"'+random_email(fake_first_name+' '+fake_last_name)+'","password":" "}', headers={'Content-Type': 'application/json'}).json().get('address')
mail_sid = requests.post('https://api.mail.tm/token', data='{"address":"'+fake_email+'","password":" "}', headers={'Content-Type': 'application/json'}).json().get('token')
printf(f"EMAIL CREATED")

fake_identity = {
'first_name': fake_first_name,
'last_name': fake_last_name,
'email': fake_email
'email': fake_email,
'sid' : mail_sid
}

try:
generate_account(driver, fake_identity)
except Exception as e:
print(f"FAILED TO CREATE ACCOUNT: {e}")
printf(f"FAILED TO CREATE ACCOUNT: {e}")
pass

try:
fill_out_application_and_submit(driver, random_city, fake_identity)
except Exception as e:
print(f"FAILED TO FILL OUT APPLICATION AND SUBMIT: {e}")
printf(f"FAILED TO FILL OUT APPLICATION AND SUBMIT: {e}")
pass
driver.close()
continue
Expand All @@ -293,6 +271,17 @@ def main():
time.sleep(5)


def main():
global processes
global executor

parallel = int(input("How many parallel windows?: "))

for i in range(parallel):
processes.append(executor.submit(run))

if __name__ == '__main__':
main()
sys.exit()


1 change: 1 addition & 0 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,4 @@ fpdf==1.7.2
pdf2image==1.16.0
SpeechRecognition==3.8.1
pydub==0.25.1
futures==3.0.5