dark_web_forums/Forums/HiddenAnswers/crawler_selenium.py

__author__ = 'Helium'

'''
HiddenAnswers 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
from datetime import date
import configparser
import subprocess
from bs4 import BeautifulSoup
from Forums.Initialization.prepare_parser import new_parse
from Forums.HiddenAnswers.parser import hiddenanswers_links_parser
from Forums.Utilities.utilities import cleanHTML

counter = 1
baseURL = 'http://7eoz4h2nvw4zlr7gvlbutinqqpm546f5egswax54az6lt2u7e3t6d7yd.onion/'


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

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

    # new_parse(forumName, baseURL, False)


# Opens Tor Browser
def opentor():
    from Forums.Initialization.forums_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 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[2]/div[2]/div/div[2]/div[4]/div/ul/li[14]/a')))


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


# Return the link of the website
def getFixedURL():
    url = 'http://7eoz4h2nvw4zlr7gvlbutinqqpm546f5egswax54az6lt2u7e3t6d7yd.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():
    from Forums.Initialization.forums_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", True)
    ff_prof.update_preferences()

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

    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:
        driver.close()
        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):
    from Forums.Initialization.forums_mining import config, CURRENT_DATE

    mainDir = os.path.join(config.get('Project', 'shared_folder'), "Forums/" + getForumName() + "/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 = []

    # Hacks
    links.append('http://7eoz4h2nvw4zlr7gvlbutinqqpm546f5egswax54az6lt2u7e3t6d7yd.onion/index.php/questions/hacking')

    return links


def crawlForum(driver):
    print("Crawling the HiddenAnswers 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()
                    '''
                    #variable to check if there is a next page for the topic
                    has_next_topic_page = True
                    counter = 1

                    # check if there is a next page for the topics
                    while has_next_topic_page:
                        # try to access next page of th topic
                        itemURL = urlparse.urljoin(baseURL, str(item))
                        try:
                            driver.get(itemURL)
                        except:
                            driver.refresh()
                        savePage(driver.page_source, item)

                        # if there is a next page then go and save....
                        # next page in the topic?
                        try:
                            temp = driver.find_element(By.XPATH, '/html/body/div/div[2]/div/div[2]/div') # /html/body/div/div[2]/div/div[2]/div/
                            item = temp.find_element(by=By.CLASS_NAME, value='pagination_next').get_attribute('href') #/html/body/div/div[2]/div/div[2]/div

                            if item == "":
                                raise NoSuchElementException
                                has_next_topic_page = False
                            else:
                                counter += 1
                        except NoSuchElementException:
                            has_next_topic_page = False

                    # end of loop
                    for i in range(counter):
                        driver.back()
                    '''
                    # comment out
                    break

                # comment out
                if count == 1:
                    count = 0
                    break

                try:
                    link = driver.find_element(by=By.XPATH, value = '/html/body/div[2]/div[2]/div/div[3]/div[3]/ul/li[7]/a').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)
        i += 1

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


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


# Returns 'True' if the link is Topic link
def isDescriptionLink(url):
    if 'index.php' in url and 'questions' not in url:
        return True
    return False


# Returns True if the link is a listingPage link
def isListingLink(url):
    if 'questions' 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 hiddenanswers_links_parser(soup)


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