Browse Source

crawler fixed for kerberos, but not checked.

main
Helium 11 months ago
parent
commit
4cacfeebd9
1 changed files with 62 additions and 53 deletions
  1. +62
    -53
      MarketPlaces/Kerberos/crawler_selenium.py

+ 62
- 53
MarketPlaces/Kerberos/crawler_selenium.py View File

@ -1,4 +1,4 @@
__author__ = 'DarkWeb'
__author__ = 'Helium'
''' '''
Kerberos Market Crawler (Selenium) Kerberos Market Crawler (Selenium)
@ -29,17 +29,18 @@ baseURL = 'http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion
# Opens Tor Browser, crawls the website # Opens Tor Browser, crawls the website
def startCrawling(): def startCrawling():
opentor()
# marketName = getMarketName()
mktName = getMKTName()
driver = getAccess() driver = getAccess()
if driver != 'down': if driver != 'down':
captcha(driver)
login(driver)
crawlForum(driver)
try:
login(driver)
crawlForum(driver)
except Exception as e:
print(driver.current_url, e)
closeDriver(driver)
# new_parse(marketName, False)
closetor(driver)
# new_parse(mktName, baseURL, True)
# Opens Tor Browser # Opens Tor Browser
@ -53,24 +54,28 @@ def opentor():
input('Tor Connected. Press ENTER to continue\n') input('Tor Connected. Press ENTER to continue\n')
return return
def captcha(driver): def captcha(driver):
# wait for captcha page
WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, "/html/body/div/div/img")))
# do captchas manually and then wait
input('Complete CAPTCHA\'s manually\nthen press enter when completed')
# too hard to code, requires manual completion
# wait for login page
WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, "/html/body/div[1]/div[2]/div/form/div[10]/button")))
def closeDriver(driver):
# global pid
# os.system("taskkill /pid " + str(pro.pid))
# os.system("taskkill /t /f /im tor.exe")
print('Closing Tor...')
driver.close()
time.sleep(3)
return
# Login using premade account credentials and do login captcha manually # Login using premade account credentials and do login captcha manually
def login(driver): def login(driver):
captcha(driver)
#wait for login page #wait for login page
WebDriverWait(driver, 100).until(EC.visibility_of_element_located( WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, "/html/body/div[1]/div[2]/div/form/div[10]/button")))
(By.XPATH, "/html/body/div[1]/div[2]")))
input("There may be an enter button you need to press.\npress it now then press enter on the keyboard")
#entering username and password into input boxes #entering username and password into input boxes
usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[1]') usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[1]')
@ -80,40 +85,43 @@ def login(driver):
#Password here #Password here
passwordBox.send_keys('fishowal') passwordBox.send_keys('fishowal')
input('complete CAPTCHA, press login, and then press enter on keyboard')
# wait for captcha page show up # wait for captcha page show up
# WebDriverWait(driver, 100).until(EC.visibility_of_element_located( # WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
# (By.XPATH, "/html/body/div/img[24]"))) # (By.XPATH, "/html/body/div/img[24]")))
time.sleep(10)
# time.sleep(10)
# save captcha to local # save captcha to local
driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/div[6]').screenshot(
r'..\Kerberos\captcha.png')
# This method will show image in any image viewer
im = Image.open(r'..\Kerberos\captcha.png')
im.show()
# wait until input space show up
inputBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[3]')
# ask user input captcha solution in terminal
userIn = input("Enter solution: ")
# send user solution into the input space
inputBox.send_keys(userIn)
# click the verify(submit) button
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
driver.find_element(by=By.XPATH, value="/html/body/div[1]/div[2]/div/form/div[10]/button").click()
# wait for listing page show up (This Xpath may need to change based on different seed url)
WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, '//*[@id="breadcrumb"]')))
# driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/div[6]').screenshot(
# r'..\Kerberos\captcha.png')
#
# # This method will show image in any image viewer
# im = Image.open(r'..\Kerberos\captcha.png')
#
# im.show()
#
# # wait until input space show up
# inputBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[3]')
# # ask user input captcha solution in terminal
# userIn = input("Enter solution: ")
#
# # send user solution into the input space
# inputBox.send_keys(userIn)
#
# # click the verify(submit) button
# driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# driver.find_element(by=By.XPATH, value="/html/body/div[1]/div[2]/div/form/div[10]/button").click()
#
# # wait for listing page show up (This Xpath may need to change based on different seed url)
# WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
# (By.XPATH, '//*[@id="breadcrumb"]')))
# Returns the name of the website # Returns the name of the website
def getMarketName():
def getMKTName():
name = 'Kerberos' name = 'Kerberos'
return name return name
@ -139,12 +147,11 @@ def closetor(driver):
# Creates FireFox 'driver' and configure its 'Profile' # Creates FireFox 'driver' and configure its 'Profile'
# to use Tor proxy and socket # to use Tor proxy and socket
def createFFDriver(): def createFFDriver():
file = open('../../path.txt', 'r')
lines = file.readlines()
from MarketPlaces.Initialization.markets_mining import config
ff_binary = FirefoxBinary(lines[0].strip())
ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
ff_prof = FirefoxProfile(lines[1].strip())
ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
ff_prof.set_preference("places.history.enabled", False) ff_prof.set_preference("places.history.enabled", False)
ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True) ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
ff_prof.set_preference("privacy.clearOnShutdown.passwords", True) ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
@ -153,7 +160,7 @@ def createFFDriver():
ff_prof.set_preference("signon.rememberSignons", False) ff_prof.set_preference("signon.rememberSignons", False)
ff_prof.set_preference("network.cookie.lifetimePolicy", 2) ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
ff_prof.set_preference("network.dns.disablePrefetch", True) ff_prof.set_preference("network.dns.disablePrefetch", True)
# ff_prof.set_preference("network.http.sendRefererHeader", 0)
ff_prof.set_preference("network.http.sendRefererHeader", 0)
ff_prof.set_preference("permissions.default.image", 3) ff_prof.set_preference("permissions.default.image", 3)
ff_prof.set_preference("browser.download.folderList", 2) ff_prof.set_preference("browser.download.folderList", 2)
ff_prof.set_preference("browser.download.manager.showWhenStarting", False) ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
@ -166,24 +173,24 @@ def createFFDriver():
ff_prof.set_preference("javascript.enabled", False) ff_prof.set_preference("javascript.enabled", False)
ff_prof.update_preferences() ff_prof.update_preferences()
service = Service(executable_path=lines[2].strip())
service = Service(config.get('TOR', 'geckodriver_path'))
driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
driver.maximize_window()
return driver return driver
def getAccess(): def getAccess():
url = getFixedURL() url = getFixedURL()
driver = createFFDriver() driver = createFFDriver()
try: try:
driver.get(url) driver.get(url)
return driver return driver
except: except:
driver.close()
return 'down' return 'down'
@ -284,6 +291,8 @@ def crawlForum(driver):
break break
try: try:
# /html/body/div[4]/div[4]/div[4]/div/div[1]/div[28]/a[15]
# /html/body/div[4]/div[4]/div[4]/div/div[1]/div[28]/a[16]
nav = driver.find_element(by=By.XPATH, value= nav = driver.find_element(by=By.XPATH, value=
'/html/body/div[3]/div[4]/div[4]/div/div[1]/div[28]') '/html/body/div[3]/div[4]/div[4]/div/div[1]/div[28]')
a = nav.find_element(by=By.LINK_TEXT, value="Next") a = nav.find_element(by=By.LINK_TEXT, value="Next")


Loading…
Cancel
Save