dark_web_forums/MarketPlaces/TheDarkMarket/crawler_selenium.py

__author__ = 'DarkWeb'

'''
Royal Marketplace Crawler (Selenium)
'''

from selenium import webdriver
from selenium.webdriver.support.select import Select
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
from selenium.webdriver.firefox.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from PIL import Image


import urllib.parse as urlparse
import os, re, time
from datetime import date
import subprocess
from bs4 import BeautifulSoup
from MarketPlaces.Initialization.prepare_parser import new_parse
from MarketPlaces.TheDarkMarket.parser import thedarkmarket_links_parser
from MarketPlaces.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://dark3xolguutzr2cn5twjyu6c3db2z3ai3aqyqascml5cdrleh3s2hqd.onion/'


# Opens Tor Browser, crawls the website
def startCrawling():
    marketName = getMarketName()
    driver = getAccess()

    if driver != 'down':
        try:
            crawlForum(driver)
        except Exception as e:
            print(driver.current_url, e)
        closeDriver(driver)

    new_parse(marketPlace=marketName, url=baseURL, createLog=True)


def captcha(driver):
    '''
    # wait for captcha page
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/div[2]/div/div/div/div/form/div/div[2]/button")))

    inputChars = driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div/div/form/div/div[2]/div[1]/input')
    inputNum = driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div/div/form/div/div[2]/div[2]/input')

    driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div/div/form/div/div[1]/div/div').screenshot(
        r'..\Royal\captcha1.png')

    im = Image.open(r'..\Royal\captcha1.png')
    im.show()

    chars = input("Enter characters: ")
    inputChars.send_keys(chars)

    num = input("Enter number of wrong puzzle pieces: ")
    inputNum.send_keys(num)

    # click the verify(submit) button
    driver.find_element(by=By.XPATH, value="/html/body/div[2]/div/div/div/div/form/div/div[2]/button").click()
    '''
    input("Press ENTER when CAPTCHA is completed\n")

    # wait for login page
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/div[2]/div/div/div[2]/h1")))

    '''
    temp = driver.find_element(by=By.XPATH, value='/html/body/div/div/form/div[1]')
    boxes = temp.find_elements(by=By.TAG_NAME, value='input')

    for box in boxes:
        # click box to update captcha image
        box.click()

        # save clock captcha to local
        time.sleep(1)
        driver.find_element(by=By.XPATH, value='/html/body/div/div/form/div[1]/div').screenshot(
            r'..\Royal\captcha1.png')

        im = Image.open(r'..\Royal\captcha1.png')
        im.show()

        letter = input("Enter letter: ")
        box.send_keys(letter)

    # click the verify(submit) button
    driver.find_element(by=By.XPATH, value="/html/body/div/div/form/button[1]").click()

    # wait for login page
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/div[1]/div/div/div[2]/form/input[3]")))
    '''


# Login using premade account credentials and do login captcha manually
def login(driver):
    # wait for login page
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/div[2]/div/div/div[2]/form/div[4]")))

    # entering username and password into input boxes
    usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
    # Username here
    usernameBox.send_keys('blabri')
    passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
    # Password here
    passwordBox.send_keys('fishowal')

    # click "Login"
    driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div[2]/form/div[4]').click()

    '''
    # wait for captcha page show up
    time.sleep(3)

    # save captcha to local
    driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div[2]/form/div[4]/label/div/div').screenshot(
        r'..\Royal\captcha2.png')

    # This method will show image in any image viewer
    im = Image.open(r'..\Royal\captcha2.png')
    im.show()

    # ask user input captcha solution in terminal
    userIn = input("Enter location of wrong pieces (squares are numbered 1-24 left to right, # # #): ")
    squares = userIn.split()

    # send user solution into the input space
    for id in squares:
        driver.find_element(by=By.XPATH, value='//*[@id="cl[' + str((int(id)-1)) + ']"]').click()

    # click the verify(submit) button
    driver.find_element(by=By.XPATH, value="/html/body/div[2]/div/div/div[2]/form/div[4]/label/div/div/div/button").click()
    '''
    input("Press ENTER when CAPTCHA is completed\n")

    # wait for listing page show up (This Xpath may need to change based on different seed url)
    WebDriverWait(driver, 50).until(EC.visibility_of_element_located(
        (By.XPATH, '/html/body/div[3]/div/div[5]/div[1]')))


# Returns the name of the website
def getMarketName():
    name = 'TheDarkMarket'
    return name


# Return the link of the website
def getFixedURL():
    url = 'http://dark3xolguutzr2cn5twjyu6c3db2z3ai3aqyqascml5cdrleh3s2hqd.onion/'

    return url


# Closes Tor Browser
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


# Creates FireFox 'driver' and configure its 'Profile'
# to use Tor proxy and socket
def createFFDriver():
    from MarketPlaces.Initialization.markets_mining import config

    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))

    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
    ff_prof.set_preference("places.history.enabled", False)
    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
    ff_prof.set_preference("signon.rememberSignons", False)
    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
    # ff_prof.set_preference("network.dns.disablePrefetch", True)
    # ff_prof.set_preference("network.http.sendRefererHeader", 0)
    ff_prof.set_preference("permissions.default.image", 3)
    ff_prof.set_preference("browser.download.folderList", 2)
    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
    ff_prof.set_preference('network.proxy.type', 1)
    ff_prof.set_preference("network.proxy.socks_version", 5)
    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
    ff_prof.set_preference('network.proxy.socks_port', 9150)
    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
    ff_prof.set_preference("javascript.enabled", False)
    ff_prof.update_preferences()

    service = Service(config.get('TOR', 'geckodriver_path'))

    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
    
    driver.maximize_window()

    return driver


def getAccess():
    url = getFixedURL()
    driver = createFFDriver()
    try:
        driver.get(url)
        return driver
    except:
        driver.close()
        return 'down'


# Saves the crawled html page
def savePage(driver, page, url):
    cleanPage = cleanHTML(driver, page)
    filePath = getFullPathName(url)
    os.makedirs(os.path.dirname(filePath), exist_ok=True)
    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
    return


# Gets the full path of the page to be saved along with its appropriate file name
def getFullPathName(url):
    from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE

    mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getMarketName() + "/HTML_Pages")
    fileName = getNameFromURL(url)
    if not isListingLink(url):
        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html')
    else:
        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html')
    return fullPath


# Creates the file name from passed URL
def getNameFromURL(url):
    global counter
    name = ''.join(e for e in url if e.isalnum())
    if name == '':
        name = str(counter)
        counter = counter + 1
    return name


def getInterestedLinks():
    links = []

    # Digital - Fraud Software
    links.append(baseURL + 'product-category/hacking/')
    # # Digital - Guides and Tutorials
    # links.append('http://royalrnpvfbodtt5altnnzano6hquvn2d5qy55oofc2zyqciogcevrad.onion/category/Guides%20&%20Tutorials')
    # # Digital - Legitimate Software
    # links.append('http://royalrnpvfbodtt5altnnzano6hquvn2d5qy55oofc2zyqciogcevrad.onion/category/Legitimiate%20Software')
    # # Services - Carding
    # links.append('http://royalrnpvfbodtt5altnnzano6hquvn2d5qy55oofc2zyqciogcevrad.onion/category/Carding')

    return links


def crawlForum(driver):
    print("Crawling The Dark Market")

    linksToCrawl = getInterestedLinks()

    i = 0
    while i < len(linksToCrawl):
        link = linksToCrawl[i]
        print('Crawling :', link)
        try:
            has_next_page = True
            count = 0

            while has_next_page:
                try:
                    driver.get(link)
                except:
                    driver.refresh()
                html = driver.page_source
                savePage(driver, html, link)

                list = productPages(html)
                for item in list:
                    itemURL = urlparse.urljoin(baseURL, str(item))
                    try:
                        driver.get(itemURL)
                    except:
                        driver.refresh()
                    savePage(driver, driver.page_source, item)
                    driver.back()

                    # comment out
                    # break

                # comment out
                # if count == 1:
                #     break
                
                # Try finding next page
                try:
                    nav = driver.find_element(by=By.XPATH, value='/html/body/div[2]/div/div/div[1]/div[2]/nav')
                    li = nav.find_elements(by=By.TAG_NAME, value='li')
                    a = li[-1].find_element(by=By.TAG_NAME, value='a')
                    link = a.get_attribute('href')
                    if link == "":
                        raise NoSuchElementException
                    count += 1

                except NoSuchElementException:
                    has_next_page = False

        except Exception as e:
            print(link, e)
        i += 1

    input("Crawling Royal forum done sucessfully. Press ENTER to continue\n")


# Returns 'True' if the link is Topic link
def isDescriptionLink(url):
    if '/product/' in url:
        return True
    return False


# Returns True if the link is a listingPage link
def isListingLink(url):
    if 'category' in url:
        return True
    return False


# calling the parser to define the links
def productPages(html):
    soup = BeautifulSoup(html, "html.parser")
    return darkmarket_links_parser(soup)


def crawler():
    startCrawling()
    # print("Crawling and Parsing BestCardingWorld .... DONE!")