dark_web_forums/Forums/Dread/crawler_selenium.py

__author__ = 'DarkWeb'

'''
Dread Forum 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

import urllib.parse as urlparse
import os, re, time
from datetime import date
import subprocess
from bs4 import BeautifulSoup
from Forums.Initialization.prepare_parser import new_parse
from Forums.Dread.parser import dread_links_parser
from Forums.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/'


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

    if driver != 'down':
        login(driver)
        crawlForum(driver)
        closetor(driver)

    # new_parse(forumName, False)


# Opens Tor Browser
def opentor():
    global pid
    print("Connecting Tor...")
    path = open('../../path.txt').readline().strip()
    pro = subprocess.Popen(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):
    '''
    # code for captcha, for now, it runs too slow so captcha expires
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.CSS_SELECTOR, ".image")))

    inputBoxes = driver.find_elements(by=By.TAG_NAME, value='input')
    for index, inputBox in enumerate(inputBoxes):
        driver.find_element(by=By.CSS_SELECTOR, value='.image').screenshot(r'..\Dread\captcha.png')
        im = Image.open(r'..\Dread\captcha.png')

        im.show()
        userIn = input("Enter character: ")
        inputBox.send_keys(userIn)
        im.close()
        if index != 5:
            inputBoxes[index+1].click()
    driver.find_element(by=By.XPATH, value="/html/body/div/div[2]/div/form/div/input").click()
    '''
    input("Press ENTER when CAPTCHA is completed\n")

    #entering username and password into input boxes
    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
        (By.XPATH, "/html/body/div/div[2]")))


# Returns the name of the website
def getForumName():
    name = 'Dread'
    return name


# Return the link of the website
def getFixedURL():
    url = 'http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.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.close()
    time.sleep(3)
    return


# Creates FireFox 'driver' and configure its 'Profile'
# to use Tor proxy and socket
def createFFDriver():
    file = open('../../path.txt', 'r')
    lines = file.readlines()



    ff_binary = FirefoxBinary(lines[0].strip())

    ff_prof = FirefoxProfile(lines[1].strip())
    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", True)
    ff_prof.set_preference("xpinstall.signatures.required", False);

    ff_prof.update_preferences()

    service = Service(lines[2].strip())

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

    return driver


def getAccess():
    url = getFixedURL()
    driver = createFFDriver()

    try:

        driver.get(url)
        return driver

    except:

        return 'down'


# Saves the crawled html page
def savePage(page, url):
    cleanPage = cleanHTML(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):
    fileName = getNameFromURL(url)
    if isDescriptionLink(url):
        fullPath = r'..\Dread\HTML_Pages\\' + str(
            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
            "%04d" % date.today().year) + r'\\' + r'Description\\' + fileName + '.html'
    else:
        fullPath = r'..\Dread\HTML_Pages\\' + str(
            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
            "%04d" % date.today().year) + r'\\' + 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 = []

    # OpSec
    # links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/OpSec?p=40')
    # links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/OpSec')
    # # Hacking 180
    links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/hacking')
    # # Jobs4Crypto
    links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/Jobs4Crypto')
    # # Hacktown
    links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/HackTown')
    # # Malware
    # links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/malware')
    # # Programming
    links.append('http://dreadytofatroptsdj6io7l3xptbet6onoyno2yv7jicoxknyazubrad.onion/d/programming')

    return links


def crawlForum(driver):
    print("Crawling the Dread forum")

    linksToCrawl = getInterestedLinks()
    visited = set(linksToCrawl)
    initialTime = time.time()

    i = 0
    count = 0
    while i < len(linksToCrawl):
        link = linksToCrawl[i]
        print('Crawling :', link)
        try:
            try:
                driver.get(link)
            except:
                driver.refresh()
            html = driver.page_source
            savePage(html, link)

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

                if count == 1:
                    count = 0
                    break

                try:
                    temp = driver.find_element(by=By.CLASS_NAME, value="pagination")
                    link = temp.find_element(by=By.CLASS_NAME, value="next").get_attribute('href')

                    if link == "":
                        raise NoSuchElementException
                    try:
                        driver.get(link)
                    except:
                        driver.refresh()
                    html = driver.page_source
                    savePage(html, link)
                    count += 1

                except NoSuchElementException:
                    has_next_page = False

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

    # finalTime = time.time()
    # print finalTime - initialTime

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


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


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


# calling the parser to define the links
def topicPages(html):
    soup = BeautifulSoup(html, "html.parser")
    #print(soup.find('div', id="container").find('div', id="content").find('table', {"class": "tborder clear"}).find('tbody').find('tr',{"class": "inline_row"}).find('strong').text)
    return dread_links_parser(soup)


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