dark_web_forums/MarketPlaces/Kingdom/crawler_selenium.py

__author__ = 'Helium'

'''
Kingdom 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.common.exceptions import TimeoutException
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.ui import Select
from PIL import Image
import base64
from io import BytesIO


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.Kingdom.parser import kingdom_links_parser
from MarketPlaces.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://kingdomm7v6yed55o2rbspvs4exn5bzfxdizqaav27tw6gw4zc65vdad.onion'


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

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

    new_parse(mktName, baseURL, True)


# Login using premade account credentials and do login captcha manually
def login(driver):

    input("Press ENTER when CAPTCHA is completed\n")

    # wait for login page
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, '//*[@id="login-form"]')))

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

    select = Select(driver.find_element(by=By.XPATH, value='//*[@id="loginformwithcaptcha-sessiontime"]'))
    select.select_by_visible_text('24 hours')

    input("Press ENTER when CAPTCHA and DDOS 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/div/div[3]/div[1]/div/div[3]')))


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


# Return the link of the website
def getFixedURL():
    url = 'http://kingdomm7v6yed55o2rbspvs4exn5bzfxdizqaav27tw6gw4zc65vdad.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/" + 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 = []

    # Software and Malware
    links.append('http://kingdomm7v6yed55o2rbspvs4exn5bzfxdizqaav27tw6gw4zc65vdad.onion/offers?filter_category=127')
    # # Services
    links.append('http://kingdomm7v6yed55o2rbspvs4exn5bzfxdizqaav27tw6gw4zc65vdad.onion/offers?filter_category=45')
    # # guides and tutorials
    links.append('http://kingdomm7v6yed55o2rbspvs4exn5bzfxdizqaav27tw6gw4zc65vdad.onion/offers?filter_category=107')

    return links


def crawlForum(driver):

    print("Crawling the Kingdom 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:
                    link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "»")]').get_attribute('href')
                    if link == "":
                        raise NoSuchElementException
                    count += 1

                except NoSuchElementException:
                    has_next_page = False

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

    print("Crawling the Kingdom market done.")


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


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


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


def crawler():
    startCrawling()