dark_web_forums/MarketPlaces/RobinhoodMarket/crawler_selenium.py

__author__ = 'chris'

'''
RobinhoodMarket 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.RobinhoodMarket.parser import Robinhood_links_parser
from MarketPlaces.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://ilr3qzubfnx33vbhal7l5coo4ftqlkv2tboph4ujog5crz6m5ua2b2ad.onion/'


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

    driver = getAccess()

    if driver != 'down':
        try:
            # Captcha
            input("Press ENTER when website has loaded")
            # Robinhood doesn't need login
            # login(driver)
            crawlForum(driver)
        except Exception as e:
            print(driver.current_url, e)
        closeDriver(driver)

    new_parse(marketName, baseURL, True)


# Login is not needed in Robinhood
def login(driver):
    pass


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


# Return the link of the website
def getFixedURL():
    url = 'http://ilr3qzubfnx33vbhal7l5coo4ftqlkv2tboph4ujog5crz6m5ua2b2ad.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.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 = []

    # Hacking
    links.append('http://ilr3qzubfnx33vbhal7l5coo4ftqlkv2tboph4ujog5crz6m5ua2b2ad.onion/product-category/hacking/')
    # Other Software
    links.append('http://ilr3qzubfnx33vbhal7l5coo4ftqlkv2tboph4ujog5crz6m5ua2b2ad.onion/product-category/other-software/')

    return links


def crawlForum(driver):
    print("Crawling the Robinhood 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 c, item in enumerate(list):

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

                    # comment out
                    # if c == 4:
                    #     break

                # comment out
                # if count == 1:
                #     break

                # go to next page of market
                try:
                    nav = driver.find_element(by=By.XPATH, value="//a[@class='next page-numbers']")
                    link = nav.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 Robinhood market done.")


# Returns 'True' if the link is Topic link
def isDescriptionLink(url):
    if 'product' in url and 'category' not 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 Robinhood_links_parser(soup)


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


if __name__ == '__main__':
    startCrawling()