added Nulled forum and Kerberos market (both unfinished)

Forums/Nulled/crawler_selenium.py

@@ -0,0 +1,281 @@
+__author__ = 'DarkWeb'
+
+'''
+nulled 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
+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 Forums.Initialization.prepare_parser import new_parse
+from Forums.Nulled.parser import nulled_links_parser
+from Forums.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'https://www.nulled.to'
+
+
+# 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):
+    time.sleep(3)
+
+
+# Returns the name of the website
+def getForumName():
+    name = 'Nulled'
+    return name
+
+
+# Return the link of the website
+def getFixedURL():
+    url = 'https://www.nulled.to'
+    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.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)
+        # time.sleep(3)
+        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'..\Nulled\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'..\Nulled\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 = []
+
+    # Cracking Tools
+    links.append('https://www.nulled.to/forum/90-cracking-tools/')
+    # # Cracking Tutorials
+    # links.append('https://www.nulled.to/forum/98-cracking-tutorials/')
+    # # Releases
+    # links.append('https://www.nulled.to/forum/209-releases/')
+    # # Newbi.Net Frameworkse
+    # links.append('https://www.nulled.to/forum/51-net-framework/')
+    # # html css js php
+    # links.append('https://www.nulled.to/forum/54-html-css-js-php/')
+    # # C C++
+    # links.append('https://www.nulled.to/forum/52-cc/')
+    # # other languages
+    # links.append('https://www.nulled.to/forum/135-other-languages/')
+
+    return links
+
+
+def crawlForum(driver):
+    print("Crawling the Nulled 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.XPATH, value='/html/body/div[4]/div[3]/div/div[3]/div[4]')
+                    temp = temp.find_element(by=By.CLASS_NAME, value='pagination')
+                    link = temp.find_element(by=By.CLASS_NAME, value='next')
+                    link = link.find_element(by=By.TAG_NAME, value='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.message)
+        i += 1
+
+    # finalTime = time.time()
+    # print finalTime - initialTime
+
+    input("Crawling Nulled forum done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is Topic link
+def isDescriptionLink(url):
+    if 'topic/' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+def isListingLink(url):
+    if 'forum/' 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 nulled_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

Forums/Nulled/parser.py

@@ -0,0 +1,355 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from Forums.Utilities.utilities import *
+from datetime import date
+from datetime import timedelta
+import re
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+# This is the method to parse the Description Pages (one page to each topic in the Listing Pages)
+
+def nulled_description_parser(soup):
+
+    # Fields to be parsed
+
+    topic = "-1"           # topic name
+    user = []              # all users of each post
+    addDate = []           # all dated of each post
+    feedback = []          # all feedbacks of each vendor (this was found in just one Forum and with a number format)
+    status = []            # all user's authority in each post such as (adm, member, dangerous)
+    reputation = []        # all users's karma in each post (usually found as a number)
+    sign = []              # all user's signature in each post (usually a standard message after the content of the post)
+    post = []              # all messages of each post
+    interest = []          # all user's interest in each post
+
+    # Finding the topic (should be just one coming from the Listing Page)
+
+    li = soup.find("td", {"class": "thead"}).find('strong')
+    topic = li.text
+    topic = re.sub("\[\w*\]", '', topic)
+
+    topic = topic.replace(",","")
+    topic = topic.replace("\n","")
+    topic = cleanString(topic.strip())
+    print(topic)
+    # Finding the repeated tag that corresponds to the listing of posts
+
+    # posts = soup.find("form", {"name": "quickModForm"}).findAll('div', {"class": "windowbg"}) + \
+    #         soup.find("form", {"name": "quickModForm"}).findAll('div', {"class": "windowbg2"})
+
+    try:
+        posts = soup.find('table', {"class": "tborder tfixed clear"}).find('td', {"id": "posts_container"}).find_all(
+            'div', {"class": "post"})
+        # print(len(posts))
+
+        # For each message (post), get all the fields we are interested to:
+
+        for ipost in posts:
+
+            # Finding a first level of the HTML page
+
+            # post_wrapper = ipost.find('div', {"class": "post_wrapper"}).find('div', {"class": "poster"})
+            post_wrapper = ipost.find('span', {"class": "largetext"})
+            # Finding the author (user) of the post
+
+            # author = post_wrapper.find('h4')
+            author = post_wrapper.text.strip()
+            # print("author " + author)
+            user.append(cleanString(author))  # Remember to clean the problematic characters
+
+            # Finding the status of the author
+
+            smalltext = ipost.find('div', {"class": "post_author"})
+
+            # Testing here two possibilities to find this status and combine them
+            if ipost.find('div', {"class": "deleted_post_author"}):
+                status.append(-1)
+                interest.append(-1)
+                reputation.append(-1)
+                addDate.append(-1)
+                post.append("THIS POST HAS BEEN REMOVED!")
+                sign.append(-1)
+                feedback.append(-1)
+                continue
+
+            # nulled does have membergroup and postgroup
+
+            membergroup = smalltext.find('div', {"class": "profile-rank"})
+            postgroup = smalltext.find('div', {"class": "postgroup"})
+            if membergroup != None:
+                membergroup = membergroup.text.strip()
+                if postgroup != None:
+                    postgroup = postgroup.text.strip()
+                    membergroup = membergroup + " - " + postgroup
+            else:
+                if postgroup != None:
+                    membergroup = postgroup.text.strip()
+                else:
+                    membergroup = "-1"
+
+            status.append(cleanString(membergroup))
+            # print("status " + cleanString(membergroup))
+            # Finding the interest of the author
+            # CryptBB does not have blurb
+            blurb = smalltext.find('li', {"class": "blurb"})
+            if blurb != None:
+                blurb = blurb.text.strip()
+            else:
+                blurb = "-1"
+            interest.append(cleanString(blurb))
+
+            # Finding the reputation of the user
+            # CryptBB does have reputation
+            author_stats = smalltext.find('div', {"class": "author_statistics"})
+            karma = author_stats.find('strong')
+            if karma != None:
+                karma = karma.text
+                karma = karma.replace("Community Rating: ", "")
+                karma = karma.replace("Karma: ", "")
+                karma = karma.strip()
+            else:
+                karma = "-1"
+            reputation.append(cleanString(karma))
+            # print("karma " + cleanString(karma))
+            # Getting here another good tag to find the post date, post content and users' signature
+
+            postarea = ipost.find('div', {"class": "post_content"})
+
+            dt = postarea.find('span', {"class": "post_date"}).text
+            # dt = dt.strip().split()
+            dt = dt.strip()
+            day=date.today()
+            if "Yesterday" in dt:
+                yesterday = day - timedelta(days=1)
+                yesterday = yesterday.strftime('%m-%d-%Y')
+                stime = dt.replace('Yesterday,','').strip()
+                date_time_obj = yesterday+ ', '+stime
+                date_time_obj = datetime.strptime(date_time_obj,'%m-%d-%Y, %I:%M %p')
+            elif "hours ago" in dt:
+                day = day.strftime('%m-%d-%Y')
+                date_time_obj = postarea.find('span', {"class": "post_date"}).find('span')['title']
+                date_time_obj = datetime.strptime(date_time_obj, '%m-%d-%Y, %I:%M %p')
+            else:
+                date_time_obj = datetime.strptime(dt, '%m-%d-%Y, %I:%M %p')
+                stime = date_time_obj.strftime('%b %d, %Y')
+                sdate = date_time_obj.strftime('%I:%M %p')
+
+
+            addDate.append(date_time_obj)
+            # print("date " + str(date_time_obj))
+            # Finding the date of the post
+            # date_time_obj = datetime.strptime(dt, '%a %b %d, %Y %I:%M %p')
+            # smalltext = postarea.find('div', {"class": "flow_hidden"}).find('div', {"class": "keyinfo"})\
+            #     .find('div', {"class": "smalltext"})
+            # sdatetime = smalltext.text
+            # sdatetime = sdatetime.replace(u"\xab","") # Removing unnecessary characters
+            # sdatetime = sdatetime.replace(u"\xbb","") # Removing unnecessary characters
+            # sdatetime = sdatetime.split("on: ")       # Removing unnecessary characters
+            # sdatetime = sdatetime[1].strip()
+            # stime = sdatetime[:-12:-1]                # Finding the time of the post
+            # stime = stime[::-1]
+            # sdate = sdatetime.replace(stime,"")       # Finding the date of the post
+            # sdate = sdate.replace(",","")
+            # sdate = sdate.strip()
+
+            # Covert the date of the post that can be informed as: "12 February 2016", "today", "yesterday". We need
+            # a date format here as "mm/dd/yyyy"
+
+            # addDate.append(convertDate(sdate,"english", crawlerDate) + " " + stime)
+
+            # Finding the post
+
+            inner = postarea.find('div', {"class": "post_body scaleimages"})
+            inner = inner.text.strip()
+            # print(inner)
+            post.append(cleanString(inner))
+
+            # Finding the users's signature
+
+            # signature = ipost.find('div', {"class": "post_wrapper"}).find('div', {"class": "moderatorbar"}).find('div', {"class": "signature"})
+            signature = ipost.find('div', {"class": "signature scaleimages"})
+            if signature != None:
+                signature = signature.text.strip()
+                # print(signature)
+            else:
+                signature = "-1"
+            sign.append(cleanString(signature))
+
+            # As no information about users's feedback was found, just assign "-1" to the variable
+
+            feedback.append("-1")
+    except:
+        if soup.find('td', {"class": "trow1"}).text == " You do not have permission to access this page. ":
+            user.append("-1")
+            status.append(-1)
+            interest.append(-1)
+            reputation.append(-1)
+            addDate.append(-1)
+            post.append("NO ACCESS TO THIS PAGE!")
+            sign.append(-1)
+            feedback.append(-1)
+
+
+    # Populate the final variable (this should be a list with all fields scraped)
+
+    row = (topic, post, user, addDate, feedback, status, reputation, sign, interest)
+
+    # Sending the results
+
+    return row
+
+# This is the method to parse the Listing Pages (one page with many posts)
+
+def nulled_listing_parser(soup):
+
+    board = "-1"       # board name (the previous level of the topic in the Forum categorization tree.
+                       # For instance: Security/Malware/Tools to hack Facebook. The board here should be Malware)
+
+    nm = 0             # this variable should receive the number of topics
+    topic = []         # all topics
+    user = []          # all users of each topic
+    post = []          # number of posts of each topic
+    view = []          # number of views of each topic
+    addDate = []       # when the topic was created (difficult to find)
+    href = []          # this variable should receive all cleaned urls (we will use this to do the marge between
+                       # Listing and Description pages)
+
+    # Finding the board (should be just one)
+
+    board = soup.find('span', {"class": "active"}).text
+    board = cleanString(board.strip())
+
+    # Finding the repeated tag that corresponds to the listing of topics
+
+    itopics = soup.find_all('tr', {"class": "inline_row"})
+    index = 0
+    for itopic in itopics:
+
+        # For each topic found, the structure to get the rest of the information can be of two types. Testing all of them
+        # to don't miss any topic
+
+
+        # Adding the topic to the topic list
+        try:
+            topics = itopic.find('span', {"class": "subject_old"}).find('a').text
+        except:
+            topics = itopic.find('span', {"class": "subject_new"}).find('a').text
+        topics = re.sub("\[\w*\]", '', topics)
+        topic.append(cleanString(topics))
+
+        # Counting how many topics we have found so far
+
+        nm = len(topic)
+
+        # Adding the url to the list of urls
+        try:
+            link = itopic.find('span', {"class": "subject_old"}).find('a').get('href')
+        except:
+            link = itopic.find('span',{"class": "subject_new"}).find('a').get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the author of the topic
+        ps = itopic.find('div', {"class":"author smalltext"}).find('a').text
+        author = ps.strip()
+        user.append(cleanString(author))
+
+        # Finding the number of replies
+        columns = itopic.findChildren('td',recursive=False)
+        posts = columns[3].text
+
+        post.append(cleanString(posts))
+
+        # Finding the number of Views
+        tview = columns[4].text
+        view.append(cleanString(tview))
+
+
+
+        # If no information about when the topic was added, just assign "-1" to the variable
+        #dt = itopic.find('div', {"class": "responsive-hide"}).text.split('»')[1]
+        #dt = dt.strip()
+        #date_time_obj = datetime.strptime(dt,'%a %b %d, %Y %I:%M %p')
+        #addDate.append(date_time_obj)
+        addDate.append("-1")
+
+
+
+        index += 1
+    return organizeTopics("Nulled", nm, topic, board, view, post, user, addDate, href)
+
+        # if len(tag) > 0:
+        #
+        #     # Finding the topic
+        #
+        #     tds = tds[0].find(tag[0])
+        #     topics = tds.text
+        #     topics = topics.replace(u"\xbb","")
+        #     topics = topics.strip()
+        #     topic.append(cleanString(topics))
+        #
+        #     # Counting how many topics we have found so far
+        #
+        #     nm = len(topic)
+        #
+        #     # Adding the url to the list of urls
+        #
+        #     link = tds.findAll('a', href=True)
+        #     link = link[0].get('href')
+        #     link = cleanLink(link)
+        #     href.append(link)
+        #
+        #     # Finding the author of the topic
+        #
+        #     ps = itopic.find('td', {"class": tag[1]}).find('p').find('a')
+        #     if ps == None:
+        #        ps = itopic.find('td', {"class": tag[1]}).find('p')
+        #        ps = ps.text.replace("Started by ","")
+        #     else:
+        #        ps = ps.text
+        #     author = ps.strip()
+        #     user.append(cleanString(author))
+        #
+        #     # Finding the number of replies
+        #
+        #     statistics = itopic.find('td', {"class": tag[2]})
+        #     statistics = statistics.text
+        #     statistics = statistics.split("Replies")
+        #     posts = statistics[0].strip()
+        #     post.append(cleanString(posts))
+        #
+        #     # Finding the number of Views
+        #
+        #     views = statistics[1]
+        #     views = views.replace("Views","")
+        #     views = views.strip()
+        #     view.append(cleanString(views))
+        #
+        #     # As no information about when the topic was added, just assign "-1" to the variable
+        #
+        #     addDate.append("-1")
+
+    #return organizeTopics("TheMajesticGarden", nm, topic, board, view, post, user, addDate, href)
+
+def nulled_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    #print(soup.find('table', {"class": "tborder clear"}).find(
+     #   'tbody').find_all('tr', {"class": "inline_row"}))
+    listing = soup.find('tbody')
+    listing=listing.find_all('tr',id=True)
+
+    for a in listing:
+        listing_rows = a.find_all('td')
+        link = listing_rows[1]
+        link = link.find('a',{'class':'topic_title'})
+        link = link['href']
+
+        href.append(link)
+
+    return href

MarketPlaces/Kerberos/crawler_selenium.py

@@ -0,0 +1,337 @@
+__author__ = 'DarkWeb'
+
+'''
+Kerberos 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, time
+from datetime import date
+import subprocess
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.Kerberos.parser import kerberos_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion'
+
+
+# Opens Tor Browser, crawls the website
+def startCrawling():
+    opentor()
+    # marketName = getMarketName()
+    driver = getAccess()
+
+    if driver != 'down':
+        captcha(driver)
+        login(driver)
+        crawlForum(driver)
+
+    # new_parse(marketName, False)
+    closetor(driver)
+
+
+# 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
+
+
+def captcha(driver):
+    # wait for captcha page
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div/div/img")))
+
+    # too hard to code, requires manual completion
+
+    # wait for login page
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[1]/div[2]/div/form/div[10]/button")))
+
+
+# Login using premade account credentials and do login captcha manually
+def login(driver):
+    #wait for login page
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[1]/div[2]/div/form/div[10]/button")))
+
+    #entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[1]')
+    #Username here
+    usernameBox.send_keys('blabri')
+    passwordBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[2]')
+    #Password here
+    passwordBox.send_keys('fishowal')
+
+    # wait for captcha page show up
+    # WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+    #     (By.XPATH, "/html/body/div/img[24]")))
+    time.sleep(10)
+
+    # save captcha to local
+    driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/div[6]').screenshot(
+        r'..\Kerberos\captcha.png')
+
+    # This method will show image in any image viewer
+    im = Image.open(r'..\Kerberos\captcha.png')
+
+    im.show()
+
+    # wait until input space show up
+    inputBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div/form/input[3]')
+
+    # ask user input captcha solution in terminal
+    userIn = input("Enter solution: ")
+
+    # send user solution into the input space
+    inputBox.send_keys(userIn)
+
+    # click the verify(submit) button
+    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
+    driver.find_element(by=By.XPATH, value="/html/body/div[1]/div[2]/div/form/div[10]/button").click()
+
+    # wait for listing page show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '//*[@id="breadcrumb"]')))
+
+
+# Returns the name of the website
+def getMarketName():
+    name = 'Kerberos'
+    return name
+
+
+# Return the link of the website
+def getFixedURL():
+    url = 'http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.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.quit()
+    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", False)
+    ff_prof.update_preferences()
+
+    service = Service(executable_path=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'..\Kerberos\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'..\Kerberos\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 = []
+
+    # Services - Hacking
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/99/block/price-none/ww/ww/1/')
+    # Tutorials - Hacking
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/122/block/price-none/ww/ww/1/')
+    # Tutorials - Guides
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/124/block/price-none/ww/ww/1/')
+    # Tutorials - Other
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/126/block/price-none/ww/ww/1/')
+    # Software and Malware - Botnets
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/129/block/price-none/ww/ww/1/')
+    # Software and Malware - Malware
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/130/block/price-none/ww/ww/1/')
+    # Software and Malware - Trojans
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/131/block/price-none/ww/ww/1/')
+    # Software and Malware - Exploits / Kits
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/133/block/price-none/ww/ww/1/')
+    # Software and Malware - Other
+    links.append('http://kerberosazmnfrjinmftp3im3cr7hw4nxbavm4ngofn64g24be7h3kqd.onion/categories/136/block/price-none/ww/ww/1/')
+
+    return links
+
+
+def crawlForum(driver):
+    print("Crawling the Kerberos market")
+
+    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 = productPages(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:
+                    nav = driver.find_element(by=By.XPATH, value=
+                        '/html/body/div[3]/div[4]/div[4]/div/div[1]/div[28]')
+                    a = nav.find_element(by=By.LINK_TEXT, value="Next")
+                    link = 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 Kerberos market done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is Topic link
+def isDescriptionLink(url):
+    if 'item' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+def isListingLink(url):
+    if 'categories' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return kerberos_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/Kerberos/parser.py

@@ -0,0 +1,249 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
+def kerberos_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name y
+    describe = "-1"                     # 1 Product_Description y
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft y
+    escrow = "-1"                       # 11 Vendor_Warranty y
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name y
+    sold = "-1"                         # 14 Product_QuantitySold y
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice y
+    USD = "-1"                          # 19 Product_USD_SellingPrice y
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    bae = soup.find('div', {'class': "col-9"})
+
+    # Finding Product Name
+    name = bae.find('h2').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    mb = bae.findAll('div', {"class": "mb-1"})
+
+    # Finding Vendor
+    vendor = mb[0].text
+    vendor = vendor.replace(",", "")
+    vendor = vendor.replace("Sold by:", "")
+    vendor = vendor.strip()
+
+    # # Finding Vendor Rating
+    # full_stars = bae[2].find_all('i', {'class': "fas fa-star"})
+    # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"})
+    # rating = len(full_stars) + (0.5 if half_star is not None else 0)
+
+    # Finding Warranty
+    escrow = mb[2].text
+    escrow = escrow.replace("Payment:", "")
+    escrow = escrow.strip()
+
+    # Finding Quantity Sold and Left
+    temp = mb[4].text.split(',')
+
+    sold = temp[0].replace("sold", "")
+    sold = sold.strip()
+
+    left = temp[1].replace("in stock", "")
+    left = left.strip()
+
+    # Finding USD
+    USD = bae.find('div', {"class": "h3 text-secondary"}).text
+    USD = USD.replace("$", "")
+    USD = USD.strip()
+
+    # Finding BTC
+    temp = bae.find('div', {"class": "small"}).text.split("BTC")
+
+    BTC = temp[0].strip()
+
+    # shipping_info = bae[4].text
+    # if "Digital" not in shipping_info:
+    #     shipping_info = shipping_info.split("  ")
+    #
+    #     # Finding Shipment Information (Origin)
+    #     shipFrom = shipping_info[0].strip()
+    #
+    #     # Finding Shipment Information (Destination)
+    #     shipTo = shipping_info[1].strip()
+
+    # Finding the Product description
+    describe = bae.find('div', {"class": "card border-top-0"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.replace("\r", " ")
+    describe = describe.strip()
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
+       sold, addDate, available, endDate, BTC, USD, rating, success, EURO)
+
+    # Sending the results
+    return row
+
+
+# This is the method to parse the Listing Pages
+def kerberos_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "Kerberos"                      # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name y
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category y
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews y
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice y
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor y
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 24 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card product-card mb-3"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    # Finding Category
+    cat = soup.find("div", {"class": "col-9"})
+    cat = cat.find("h2").text
+    cat = cat.replace("Category: ", "")
+    cat = cat.replace(",", "")
+    cat = cat.strip()
+
+    for card in listing:
+        category.append(cat)
+
+        bae = card.findAll('a')
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding Product Name
+        product = bae[1].text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.strip()
+        name.append(product)
+
+        # Finding Vendor
+        vendor_name = bae[2].text
+        vendor_name = vendor_name.replace(",", "")
+        vendor_name = vendor_name.strip()
+        vendor.append(vendor_name)
+
+        # Finding USD
+        usd = card.find('div', {"class": "mb-1"}).text
+        usd = usd.replace("$", "")
+        usd = usd.strip()
+        USD.append(usd)
+
+        # Finding Reviews
+        num = card.find("span", {"class": "rate-count"}).text
+        num = num.replace("(", "")
+        num = num.replace("review)", "")
+        num = num.replace("reviews)", "")
+        num = num.strip()
+        reviews.append(num)
+
+        # Searching for CVE and MS categories
+        cve = card.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue="-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue=cee
+        CVE.append(cveValue)
+        
+        ms = card.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue="-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue=me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
+                     BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+
+
+def kerberos_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+    href = []
+
+    content = soup.find('div', {"id": "content-pos"})
+    listing = content.findAll('div', {"class": "item-block"})
+
+    for div in listing:
+
+        ae = div.find('div', {"ae zx300"})
+        links = ae.findAll('a')
+        href.append(links[1]['href'])
+
+    return href