dark_web_forums/Forums/DarkNetArmy/crawler_selenium.py

__author__ = 'DarkWeb'

'''
DarkNetArmy 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

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

counter = 1
baseURL = 'http://darknet77vonbqeatfsnawm5jtnoci5z22mxay6cizmoucgmz52mwyad.onion/'


# Opens Tor Browser, crawls the website, then parses, then closes tor
#acts like the main method for the crawler, another function at the end of this code calls this function later
def startCrawling():
    forumName = getForumName()
    # driver = getAccess()
    #
    # if driver != 'down':
    #     try:
    #         crawlForum(driver)
    #     except Exception as e:
    #         print(driver.current_url, e)
    #     closeDriver(driver)

    new_parse(forumName, baseURL, True)


# Returns the name of the website
#return: name of site in string type
def getForumName():
    name = 'DarkNetArmy'
    return name


# Return the base link of the website
#return: url of base site in string type
def getFixedURL():
    url = 'http://darknet77vonbqeatfsnawm5jtnoci5z22mxay6cizmoucgmz52mwyad.onion/'
    return url


# Closes Tor Browser
#@param: current selenium driver
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 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)#might need to turn off
    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)

    driver.maximize_window()

    return driver


#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
#return: return the selenium driver or string 'down'
def getAccess():
    url = getFixedURL()
    driver = createFFDriver()
    try:
        driver.get(url)
        return driver
    except:
        driver.close()
        return 'down'


# Saves the crawled html page, makes the directory path for html pages if not made
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
#@param: raw url as crawler crawls through every site
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, gives distinct name if can't be made unique after cleaned
#@param: raw url as crawler crawls through every site
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


# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
#in this example, there are a couple of categories some threads fall under such as
#exploits, malware, and hacking tutorials
def getInterestedLinks():
    links = []

    # rats, malware, ransomware
    links.append('http://darknet77vonbqeatfsnawm5jtnoci5z22mxay6cizmoucgmz52mwyad.onion/forums/rats-malwares-key-loggers-ransomware-tools.24/')
    # hacking tutorials
    links.append('http://darknet77vonbqeatfsnawm5jtnoci5z22mxay6cizmoucgmz52mwyad.onion/forums/hacking-cracking-tutorials-courses-methods.45/')
    # # hacking
    # links.append('http://darknet77vonbqeatfsnawm5jtnoci5z22mxay6cizmoucgmz52mwyad.onion/forums/hacking-cracking-tools-apps.21/')
    return links


# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
#topic and description pages are crawled through here, where both types of pages are saved
#@param: selenium driver
def crawlForum(driver):
    print("Crawling the BestCardingWorld forum")

    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)

                topics = topicPages(html)
                for topic in topics:
                    has_next_topic_page = True
                    counter = 1
                    page = topic

                    while has_next_topic_page:
                        itemURL = urlparse.urljoin(baseURL, str(page))
                        try:
                            driver.get(itemURL)
                        except:
                            driver.refresh()
                        
                        if isListingLink(driver.current_url):
                            break

                        savePage(driver, driver.page_source, topic + f"page{counter}")  # very important

                        # comment out
                        # if counter == 2:
                        #     break

                        try:
                            page = link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "Next")]').get_attribute('href')
                            if page == "":
                                raise NoSuchElementException
                            counter += 1

                        except NoSuchElementException:
                            has_next_topic_page = False

                    # making sure we go back to the listing page (browser back button simulation)
                    try:
                        driver.get(link)
                    except:
                        driver.refresh()

                    # comment out
                    # break

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

                try:
                    link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "Next")]').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 DarkNetArmy forum done.")


# Returns 'True' if the link is a description link
#@param: url of any url crawled
#return: true if is a description page, false if not
def isDescriptionLink(url):
    if 'threads' in url:
        return True
    return False


# Returns True if the link is a listingPage link
#@param: url of any url crawled
#return: true if is a Listing page, false if not
def isListingLink(url):
    if 'forums' in url:
        return True
    return False


# calling the parser to define the links, the html is the url of a link from the list of interested link list
#@param: link from interested link list
#return: list of description links that should be crawled through
def topicPages(html):
    soup = BeautifulSoup(html, "html.parser")
    #print(soup.find('div', {"class": "forumbg"}).find('ul', {"class": "topiclist topics"}).find('li', {"class": "row bg1"}).find('a', {"class": "topictitle"}, href=True))
    return darknetarmy_links_parser(soup)


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