dark_web_forums/MarketPlaces/HiddenMarket/crawler_selenium.py

__author__ = 'DarkWeb'

'''
HiddenMarket Market Crawler (Selenium)
'''

from selenium import webdriver
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
import subprocess
import configparser
from bs4 import BeautifulSoup
from MarketPlaces.Initialization.prepare_parser import new_parse
from MarketPlaces.HiddenMarket.parser import hiddenmarket_links_parser
from MarketPlaces.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/'


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

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

    new_parse(marketName, baseURL, True)


# Opens Tor Browser
def opentor():
    from MarketPlaces.Initialization.markets_mining import config

    global pid
    print("Connecting Tor...")
    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
    pid = pro.pid
    time.sleep(7.5)
    input('Tor Connected. Press ENTER to continue\n')
    return


# 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[3]/div[3]")))

    # entering username and password into input boxes
    # usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
    # Username here
    # usernameBox.send_keys('ct1234')
    # passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
    # Password here
    # passwordBox.send_keys('DementedBed1230')

    '''
    # wait for captcha page show up
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img")))

    # save captcha to local
    driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img').screenshot(
        r'..\captcha.png')

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

    im.show()

    # wait until input space show up
    inputBox = driver.find_element(by=By.XPATH, value='//*[@id="captcha"]')

    # 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.find_element(by=By.XPATH, value="/html/body/main/div/div/div/div/div/form/div[4]/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, 100).until(EC.visibility_of_element_located(
    #     (By.XPATH, '/html/body/main/div/div/div[1]/div/div[1]/div/h5')))


# Returns the name of the website
def getMKTName():
    name = 'HiddenMarket'
    return name


# Return the link of the website
def getFixedURL():
    url = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/'

    return url


# Closes Tor Browser
def closetor(driver):
    # global pid
    # os.system("taskkill /pid " + str(pro.pid))
    # os.system("taskkill /t /f /im tor.exe")
    print('Closing Tor...')
    driver.quit()
    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/" + getMKTName() + "/HTML_Pages")
    fileName = getNameFromURL(url)
    if isDescriptionLink(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 = []

    # # Civil Software
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/civil_softwares')
    # # Tutorials - Carding
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/carding')
    # Digital - Hacks
    links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/hacks')
    # # Digital - Exploit Kit
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/exploit_kit')
    # # 0Day
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/0day')
    # # Digital Forensics
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/digital_forensics')
    # # Tutorials - Mining
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/mining')
    # # Tutorials - Worms
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/worms')
    # # Tutorials - Viruses
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/viruses')
    # # Tutorials - Trojans
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/trojans')
    # # Tutorials - Botnets
    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/botnets')

    return links


def crawlForum(driver):
    print("Crawling the HiddenMarket market")

    linksToCrawl = getInterestedLinks()

    i = 0
    while i < len(linksToCrawl):
        link = linksToCrawl[i]
        print('Crawling :', link)
        categoryLink = link
        maxNumPages = 0 # temp value.
        try:
            has_next_page = True
            count = 0
            pageCount = 1

            while has_next_page:
                try:
                    driver.get(link)
                    if pageCount == 1:
                        maxNumPages = int(driver.find_element(by=By.CLASS_NAME, value='main')
                                          .find_element(by=By.CLASS_NAME, value='pages')
                                          .find_elements(By.CLASS_NAME, value='page')[-1].text)
                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:
                    pageCount += 1
                    if pageCount > maxNumPages:
                        raise NoSuchElementException
                    pageLink = "/" + str(pageCount) + "/"
                    link = categoryLink + pageLink
                    count += 1

                except NoSuchElementException:
                    has_next_page = False

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

    print("Crawling the HiddenMarket market done.")


# 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 hiddenmarket_links_parser(soup)


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