hotfix: resolve merge conflicts

.idea/DW_Pipeline_Test.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.11 (venv)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="C:\Users\Helium\anaconda3" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyNamespacePackagesService">

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (venv)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\Helium\anaconda3" project-jdk-type="Python SDK" />
 </project>

Forums/CrackingPro/crawler_selenium.py → Forums/AbyssForum/crawler_selenium.py

@@ -1,7 +1,7 @@
-__author__ = 'DarkWeb'
+__author__ = 'Helium'
 
 '''
-OnniForums Crawler (Selenium)
+AbyssForum Crawler (Selenium)
 '''
 
 from selenium import webdriver
@@ -17,14 +17,17 @@ 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.CrackingPro.parser import crackingPro_links_parser
+from Forums.AbyssForum.parser import abyssForum_links_parser
 from Forums.Utilities.utilities import cleanHTML
 
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
 counter = 1
-baseURL = 'https://www.crackingpro.com/'
+baseURL = 'http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/'
 
 
 # Opens Tor Browser, crawls the website
@@ -41,15 +44,14 @@ def startCrawling():
             print(driver.current_url, e)
         closetor(driver)
 
-    # new_parse(forumName, False)
+    # new_parse(forumName, baseURL, False)
 
 
 # Opens Tor Browser
 def opentor():
     global pid
     print("Connecting Tor...")
-    path = open('../../path.txt').readline().strip()
-    pro = subprocess.Popen(path)
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
     pid = pro.pid
     time.sleep(7.5)
     input('Tor Connected. Press ENTER to continue\n')
@@ -58,40 +60,20 @@ def opentor():
 
 # Login using premade account credentials and do login captcha manually
 def login(driver):
-    '''
-    #click login button
-    login_link = driver.find_element(
-                by=By.ID, value='elUserSignIn').\
-                get_attribute('href')
-    driver.get(login_link)
-
-    #entering username and password into input boxes
-    usernameBox = driver.find_element(by=By.ID, value='auth')
-    #Username here
-    usernameBox.send_keys('cheese_pizza_man')
-    passwordBox = driver.find_element(by=By.ID, value='password')
-    #Password here
-    passwordBox.send_keys('Gr33nSp@m&3ggs')
-
-    '''
-
-    input("Press ENTER when log in is completed\n")
-
-
     # 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/main/div/div/div[1]/section/ol/li[8]')))
+        (By.XPATH, '//*[@id="sn-category-3"]')))
 
 
 # Returns the name of the website
 def getForumName():
-    name = 'CrackingPro'
+    name = 'AbyssForum'
     return name
 
 
 # Return the link of the website
 def getFixedURL():
-    url = 'https://www.crackingpro.com/'
+    url = 'http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/'
     return url
 
 
@@ -101,7 +83,7 @@ def closetor(driver):
     # os.system("taskkill /pid " + str(pro.pid))
     # os.system("taskkill /t /f /im tor.exe")
     print('Closing Tor...')
-    driver.close()# close the current tab
+    driver.close()
     time.sleep(3)
     return
 
@@ -109,12 +91,9 @@ def closetor(driver):
 # 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_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
 
-    ff_prof = FirefoxProfile(lines[1].strip())
+    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)
@@ -122,7 +101,7 @@ def createFFDriver():
     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.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)
@@ -136,21 +115,20 @@ def createFFDriver():
     ff_prof.set_preference("javascript.enabled", True)
     ff_prof.update_preferences()
 
-    service = Service(lines[2].strip())
+    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)# open given url
+        driver.get(url)
         return driver
     except:
-        driver.close()#close the current tab
+        driver.close()
         return 'down'
 
 
@@ -168,11 +146,11 @@ def getFullPathName(url):
     fileName = getNameFromURL(url)
     if isDescriptionLink(url):
         #..\CryptBB\HTML_Pages\\
-        fullPath = r'..\CrackingPro\HTML_Pages\\' + str(
+        fullPath = r'..\AbyssForum\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'..\CrackingPro\HTML_Pages\\' + str(
+        fullPath = r'..\AbyssForum\HTML_Pages\\' + str(
             "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
             "%04d" % date.today().year) + r'\\' + r'Listing\\' + fileName + '.html'
     return fullPath
@@ -191,32 +169,26 @@ def getNameFromURL(url):
 def getInterestedLinks():
     links = []
 
-    # exploiting tutorials
-    links.append('https://www.crackingpro.com/forum/38-exploiting-tutorials/')
-    # Hacking & Cracking questions
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-questions')
-    # Exploit PoCs
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Exploit-PoCs')
-    # Cracked software
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Cracked-software')
-    # Malware-development
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Malware-development')
-    # Carding & Fraud
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Carding-Fraud')
-    # Darknet Discussions
-    # links.append('http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion/forumdisplay.php?fid=88')
-    # OPSEC
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-OPSEC')
-    # Databases
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Databases')
-    # Proxies
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Proxies')
+    # Hacked Database
+    links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=26&sid=6f7add746810784861a7ec31703a3757')
+    # Hire a Hacker
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=27&sid=6f7add746810784861a7ec31703a3757')
+    # # Hacking Tools
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=28&sid=6f7add746810784861a7ec31703a3757')
+    # # Carding Forums
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=30&sid=6f7add746810784861a7ec31703a3757')
+    # # Social Media Hacking
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=32&sid=6f7add746810784861a7ec31703a3757')
+    # # Hacking Tutorials
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=12&sid=6f7add746810784861a7ec31703a3757')
+    # # Cracking Tutorials
+    # links.append('http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion/viewforum.php?f=13&sid=6f7add746810784861a7ec31703a3757')
 
     return links
 
 
 def crawlForum(driver):
-    print("Crawling the CrackingPro forum")
+    print("Crawling the AbyssForum forum")
 
     linksToCrawl = getInterestedLinks()
     visited = set(linksToCrawl)
@@ -236,12 +208,21 @@ def crawlForum(driver):
             savePage(html, link)
 
             has_next_page = True
+
             while has_next_page:
-                list = topicPages(html)  # for multiple pages
+                list = topicPages(html)
                 for item in list:
-                    # variable to check if there is a next page for the topic
+                    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
-                    back_counter = 1
+                    counter = 1
 
                     # check if there is a next page for the topics
                     while has_next_topic_page:
@@ -256,34 +237,31 @@ def crawlForum(driver):
                         # if there is a next page then go and save....
                         # next page in the topic?
                         try:
-                            temp = driver.find_element(by=By.ID, value='comments')  #
-                            temp2 = temp.find_elements(by=By.XPATH, value='/html/body/main/div/div/div/div[4]/div[1]')
-                            temp3 = temp2.find_elements(by=By.CLASS_NAME, value='ipsPagination')#/html/body/main/div/div/div/div[4]/div[1]
-                            item = temp3.find_element(by=By.CLASS_NAME, value='ipsPagination_next').get_attribute('href')  # /html/body/div/div[2]/div/div[2]/div
+                            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:
-                                back_counter += 1
+                                counter += 1
                         except NoSuchElementException:
                             has_next_topic_page = False
 
                     # end of loop
-                    for i in range(back_counter):
+                    for i in range(counter):
                         driver.back()
+                    '''
                     # comment out
                     break
 
                 # comment out
-                # if count == 1:
-                #     count = 0
-                #     break
+                if count == 1:
+                    count = 0
+                    break
 
-                try:  # change depending on web page, #next page
-                    temp = driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div[4]/div/div[1]/div')#/html/body/main/div/div/div/div[4]/div/div[1]/div
-                    temp2 = temp.find_element(by=By.CLASS_NAME, value='ipsPagination')
-                    link = temp2.find_element(by=By.CLASS_NAME, value='ipsPagination_next').get_attribute('href')
+                try:
+                    link = driver.find_element(by=By.XPATH, value = '/html/body/div[2]/div[2]/div[2]/div[2]/ul/li[9]/a').get_attribute('href')
 
                     if link == "":
                         raise NoSuchElementException
@@ -305,19 +283,20 @@ def crawlForum(driver):
     # finalTime = time.time()
     # print finalTime - initialTime
 
-    input("Crawling CrackingPro forum done sucessfully. Press ENTER to continue\n")
+
+    input("Crawling AbyssForum forum done sucessfully. Press ENTER to continue\n")
 
 
 # Returns 'True' if the link is Topic link
 def isDescriptionLink(url):
-    if 'topic' in url:
+    if 'viewtopic' in url:
         return True
     return False
 
 
 # Returns True if the link is a listingPage link
 def isListingLink(url):
-    if 'forum' in url:
+    if 'viewforum' in url:
         return True
     return False
 
@@ -326,9 +305,9 @@ def isListingLink(url):
 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 crackingPro_links_parser(soup)
+    return abyssForum_links_parser(soup)
 
 
 def crawler():
     startCrawling()
-    # print("Crawling and Parsing BestCardingWorld .... DONE!")
+    # print("Crawling and Parsing Abyss .... DONE!")

Forums/CrackingPro/parser.py → Forums/AbyssForum/parser.py

@@ -1,4 +1,4 @@
-__author__ = 'DarkWeb'
+__author__ = 'Helium'
 
 # Here, we are importing the auxiliary functions to clean or convert data
 from Forums.Utilities.utilities import *
@@ -334,22 +334,18 @@ def onniForums_listing_parser(soup):
 
     #return organizeTopics("TheMajesticGarden", nm, topic, board, view, post, user, addDate, href)
 
-def crackingPro_links_parser(soup):
+#need to change this method
+def abyssForum_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('ol', {"data-role": "tableRows"}).find_all('div', {"class": "ipsDataItem_main"})
+    listing = soup.find_all('dl', {"class": "row-item topic_read"})
 
     for a in listing:
-        #try:
-        link = a.find('span', {"class": "ipsType_break ipsContained"}).find('a').get('href')
-        #except:
-        #    link = a.find('span', {"class": "subject_new"}).find('a').get('href')
-
-
+        link = a.find('div', {"class": "list-inner"}).find('a').get('href')
 
         href.append(link)
 

Forums/Altenens/crawler_mechanize.py

@@ -1,257 +0,0 @@
-__author__ = '91Shadows'
-
-'''
-CryptBB Crawler (Mechanize)
-'''
-
-import codecs, os, re
-import socks, socket, time
-from datetime import date
-
-import urllib.parse as urlparse
-import http.client as httplib
-import mechanize
-import subprocess
-from bs4 import BeautifulSoup
-from Forums.Initialization.prepare_parser import new_parse
-from Forums.BestCardingWorld.parser import bestcardingworld_links_parser
-
-counter = 1
-httplib.HTTPConnection._http_vsn = 10
-httplib.HTTPConnection._http_vsn_str = 'HTTP/1.0'
-baseURL = 'http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=42&sid=ee2cbfd73c12923d979790b2bb4bdfd5'
-socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 9150)
-
-
-# Opens Tor Browser, crawls the website
-def startCrawling():
-    opentor()
-    getUrl()
-    forumName = getForumName()
-    br = getAccess()
-
-    if br != 'down':
-        crawlForum(br)
-        new_parse(forumName, False)
-
-    # new_parse(forumName, False)
-
-    closetor()
-
-
-# Opens Tor Browser
-def opentor():
-    global pid
-    print("Connecting Tor...")
-    path = open('../../path.txt').readline()
-    pro = subprocess.Popen(path)
-    pid = pro.pid
-    time.sleep(7.5)
-    input("Tor Connected. Press ENTER to continue\n")
-    return
-
-
-# Creates a connection through Tor Port
-def getUrl(timeout=None):
-    socket.socket = socks.socksocket
-    socket.create_connection = create_connection
-    return
-
-
-# Makes the onion address request
-def create_connection(address, timeout=None, source_address=None):
-    sock = socks.socksocket()
-    sock.connect(address)
-    return sock
-
-
-# Returns the name of website
-def getForumName():
-    name = 'CryptBB'
-    return name
-
-
-# Return the link of website
-def getFixedURL():
-    url = 'http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=42&sid=ee2cbfd73c12923d979790b2bb4bdfd5'
-
-    return url
-
-
-# Closes Tor Browser
-def closetor():
-    global pid
-    os.system("taskkill /pid " + str(pid))
-    print('Closing Tor...')
-    time.sleep(3)
-    return
-
-
-# Creates a Mechanize browser and initializes its options
-def createBrowser():
-    br = mechanize.Browser()
-    cj = mechanize.CookieJar()
-    br.set_cookiejar(cj)
-
-    # Browser options
-    br.set_handle_equiv(True)
-    br.set_handle_redirect(True)
-    br.set_handle_referer(True)
-    br.set_handle_robots(False)
-    br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
-    br.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'),
-                     ('Accept', '*/*')]
-
-    return br
-
-
-def getAccess():
-    url = getFixedURL()
-    br = createBrowser()
-
-    try:
-
-        br.open(url)
-        return br
-
-    except:
-
-        return 'down'
-
-
-# Saves the crawled html page
-def savePage(page, url):
-    filePath = getFullPathName(url)
-    os.makedirs(os.path.dirname(filePath), exist_ok=True)
-    a = page.read()
-    open(filePath, "wb").write(a)
-    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 = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/BestCardingWorld/HTML_Pages/' + str(
-            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-            "%04d" % date.today().year) + '/' + 'Description/' + fileName + '.html'
-    else:
-        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/BestCardingWorld/HTML_Pages/' + str(
-            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-            "%04d" % date.today().year) + '/' + 'Listing/' + fileName + '.html'
-    return fullPath
-
-
-# Creates the name of the file based on 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
-
-
-# Hacking and Markets related topics
-def getInterestedLinks():
-    links = []
-
-    links.append('http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=43&sid=e12864ffccc5df877b03b573534955be')
-
-    return links
-
-
-# Start crawling Forum pages
-def crawlForum(br):
-    print("Crawling CryptBB forum")
-
-    linksToCrawl = getInterestedLinks()
-    visited = set(linksToCrawl)
-    initialTime = time.time()
-
-
-    i = 0
-    while i < len(linksToCrawl):
-        link = linksToCrawl[i]
-        print('Crawling :', link)
-        try:
-            page = br.open(link)
-            savePage(page, link)
-
-            res = br.response().read()
-            soup = BeautifulSoup(res, 'html.parser')
-
-            next_link = soup.find("a", {"rel": "next"})
-            if next_link != None:
-                full_url = urlparse.urljoin(linksToCrawl[i], next_link['href'])
-                linksToCrawl.insert(i + 1, full_url)
-
-            listOfTopics = findDescriptionPages(link)
-            for topic in listOfTopics:
-                itemPage = br.open(str(topic))
-                savePage(itemPage, topic)
-
-        except Exception as e:
-            print('Error getting link: ', link, e)
-        i += 1
-
-    # finalTime = time.time()
-    # print finalTime - initialTime
-
-    input("CryptBB forum done sucessfully. Press ENTER to continue\n")
-
-    return
-
-
-# Returns True if the link is 'Topic' Links, may need to change for diff websites
-def isDescriptionLink(url):
-    if 'topic' in url:
-        return True
-    return False
-
-
-# Returns True if the link is a listingPage link, may need to change for diff websites
-def isListingLink(url):
-    '''
-    reg = 'board=[0-9]+.[0-9]+\Z'
-    if len(re.findall(reg, url)) == 0:
-        return False
-    return True
-    '''
-    if 'forum' in url:
-        return True
-    return False
-
-
-# calling the parser to define the links
-def findDescriptionPages(url):
-    soup = ""
-
-    error = False
-    try:
-        html = codecs.open(
-            "C:\\Users\\CALSysLab\\Documents\\threatIntelligence-main\\DarkWebMining_Working\\Forums\\BestCardingWorld\\HTML_Pages\\" + str(
-                "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-                "%04d" % date.today().year) + "\\Listing\\" + getNameFromURL(url) + ".html", encoding='utf8')
-        soup = BeautifulSoup(html, "html.parser")
-    except:
-        try:
-            html = open(
-                "C:\\Users\\CALSysLab\\Documents\\threatIntelligence-main\\DarkWebMining_Working\\Forums\\BestCardingWorld\\HTML_Pages\\" + str(
-                    "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-                    "%04d" % date.today().year) + "\\Listing\\" + getNameFromURL(url) + ".html")
-            soup = BeautifulSoup(html, "html.parser")
-        except:
-            error = True
-            print("There was a problem to read the file " + getNameFromURL(url) + " in the listing section.")
-
-    if not error:
-        return bestcardingworld_links_parser(soup)
-
-    else:
-        return []
-
-
-def crawler():
-    startCrawling()
-    print("Crawling and Parsing CryptBB .... DONE!")

Forums/Altenens/crawler_selenium.py

@@ -0,0 +1,317 @@
+__author__ = 'Helium'
+
+'''
+Altenens 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 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.Altenens.parser import altenens_links_parser
+from Forums.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'https://altenens.is/'
+
+
+# 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, False)
+
+
+# Opens Tor Browser
+def opentor():
+    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):
+    #click login button
+    login = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[1]/div/div/div/div[1]/a[1]').\
+            get_attribute('href')
+    driver.get(login)
+    # login.click()
+
+    # #entering username and password into input boxes
+    # usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[4]/div/div/div[3]/div/div/div/form/div[1]/div/dl[1]/dd')
+    # #Username here
+    # usernameBox.send_keys('mylittlepony45')#sends string to the username box
+    # passwordBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[4]/div/div/div[3]/div/div/div/form/div[1]/div/dl[2]/dd/div/div')
+    # #Password here
+    # passwordBox.send_keys('johnnyTest@18')# sends string to passwordBox
+
+    input("Press ENTER when CAPTCHA is completed\n")
+
+    # wait for listing page show up (This Xpath may need to change based on different seed url)
+    # wait for 50 sec until id = tab_content is found, then cont
+    WebDriverWait(driver, 50).until(EC.visibility_of_element_located(
+        (By.XPATH, '///html/body/div[1]/div[4]/div/div/div[3]/div/div/div[4]/div/div/div[1]/div/div[1]/div[2]/ol/li[1]')))
+
+
+# Returns the name of the website
+def getForumName():
+    name = 'Altenens'
+    return name
+
+
+# Return the link of the website
+def getFixedURL():
+    url = 'https://altenens.is/'
+    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() #close tab
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    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)# open url in browser
+        return driver
+    except:
+        driver.close()# close tab
+        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'..\\Altenens\\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'..\\Altenens\\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 = []
+
+    # # Hacking Tools
+    links.append('https://altenens.is/forums/hacking-tools.469165/')
+    # # hash cracking
+    # links.append('https://altenens.is/forums/hash-cracking.469167/')
+    # # phishing and spamming
+    # links.append('https://altenens.is/forums/phishing-and-spamming.469223/')
+    # # pentesting
+    #  links.append('https://altenens.is/forums/pentesting.469169/')
+    # # cracking tools
+    # links.append('https://altenens.is/forums/cracking-tools.469204/')
+    # # Cracking Tools
+    # links.append('https://altenens.is/forums/cracking-tutorials-other-methods.469205/')
+
+    return links
+
+
+def crawlForum(driver):
+    print("Crawling the Altenens 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)# open
+            except:
+                driver.refresh()
+            html = driver.page_source
+            savePage(html, link)
+
+            has_next_page = True
+
+            #loop through the topics
+            while has_next_page:
+                list = topicPages(html)# for multiple pages
+                for item in list:
+                    #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:
+                            item = driver.find_element(By.XPATH, '/html/body/div[1]/div[4]/div/div/div[3]/div/div/div[1]/div[1]/div[1]/nav/div[1]/a').get_attribute('href')
+
+                            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:# change depending on web page, #next page
+                    link = driver.find_element(by=By.XPATH, value = '/html/body/div[1]/div[4]/div/div/div[3]/div/div/div/div[1]/div[1]/nav/div[1]/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 Altenens forum done successfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is Topic link, may need to change for every website
+def isDescriptionLink(url):
+    if 'threads' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link, may need to change for every website
+def isListingLink(url):
+    if 'forums' 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 altenens_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

Forums/Altenens/geckodriver.log

@@ -0,0 +1,462 @@
+1655762162153	geckodriver	INFO	Listening on 127.0.0.1:50333
+1655762166434	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50334" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileqUeAAN"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655762166904	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50334/devtools/browser/fb880205-35da-44a4-83b8-a861ce7125f1
+1655762168590	Marionette	INFO	Listening on port 50341
+1655762169104	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655762207624	Marionette	INFO	Stopped listening on port 50341
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1655762207923	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655762990320	geckodriver	INFO	Listening on 127.0.0.1:50884
+1655762994595	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50885" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileurjxEe"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655762995244	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50885/devtools/browser/36503f58-7ab7-4188-81b0-fa1b81f32c0a
+1655762996997	Marionette	INFO	Listening on port 50890
+JavaScript error: resource://gre/modules/ExtensionContent.jsm, line 575: TypeError: PrecompiledScript.executeInGlobal: Argument 1 is not an object.
+1655762997277	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655763083091	Marionette	INFO	Stopped listening on port 50890
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655763083216	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655763089557	geckodriver	INFO	Listening on 127.0.0.1:50923
+1655763093759	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50924" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile5mY1qq"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655763094208	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50924/devtools/browser/68ce2df9-521f-4258-94f7-c2e2b199701a
+1655763095918	Marionette	INFO	Listening on port 50929
+1655763096408	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655763143935	Marionette	INFO	Stopped listening on port 50929
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655763144495	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655763166975	geckodriver	INFO	Listening on 127.0.0.1:50947
+1655763171175	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50948" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofilenAGZM5"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655763171719	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50948/devtools/browser/0b9966bd-0cec-45cc-9d11-02a2580233f0
+1655763173307	Marionette	INFO	Listening on port 50953
+1655763173368	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655763208922	Marionette	INFO	Stopped listening on port 50953
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655763209261	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655763387409	geckodriver	INFO	Listening on 127.0.0.1:49752
+1655763391806	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "49753" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofilevAHJSJ"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655763392827	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:49753/devtools/browser/7fe49a16-940f-4ee8-9a2f-48739a92db78
+1655763394700	Marionette	INFO	Listening on port 49759
+1655763395103	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655763430848	Marionette	INFO	Stopped listening on port 49759
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655763431145	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655765589286	geckodriver	INFO	Listening on 127.0.0.1:50102
+1655765621677	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50103" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile8ecUpb"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655765622149	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:50103/devtools/browser/e5a916fc-987c-43d4-9c12-9c9b88cca242
+1655765623776	Marionette	INFO	Listening on port 50109
+1655765623892	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655766125168	Marionette	INFO	Stopped listening on port 50109
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655766125303	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655766505099	geckodriver	INFO	Listening on 127.0.0.1:50156
+1655766509351	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50157" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileVqvmzh"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655766509876	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50157/devtools/browser/13084c14-64d3-48a5-8b99-4c514e961d4f
+1655766511328	Marionette	INFO	Listening on port 50162
+1655766511395	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655766552298	Marionette	INFO	Stopped listening on port 50162
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655766552578	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767657126	geckodriver	INFO	Listening on 127.0.0.1:50257
+1655767661375	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50258" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileB9Dzeh"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655767661843	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50258/devtools/browser/867cd318-6430-4b3f-9b63-8c6bdf17636a
+1655767663330	Marionette	INFO	Listening on port 50263
+1655767663431	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655767668263	Marionette	INFO	Stopped listening on port 50263
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1655767668591	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767689480	geckodriver	INFO	Listening on 127.0.0.1:50276
+1655767693635	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50277" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile8ZOQe7"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655767694215	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50277/devtools/browser/a70a3f5b-19af-4a68-99c8-c46086ba9599
+1655767695725	Marionette	INFO	Listening on port 50282
+1655767695830	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655767701272	Marionette	INFO	Stopped listening on port 50282
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655767701594	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767791360	geckodriver	INFO	Listening on 127.0.0.1:50296
+1655767795575	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50297" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile4GEqBr"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655767796001	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50297/devtools/browser/e2d4e57a-16ce-429d-9804-e9e391199ddf
+1655767797534	Marionette	INFO	Listening on port 50302
+1655767797661	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655767802833	Marionette	INFO	Stopped listening on port 50302
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655767803151	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767902908	geckodriver	INFO	Listening on 127.0.0.1:50320
+1655767907009	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50321" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileqlJ8ZA"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655767907484	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+DevTools listening on ws://localhost:50321/devtools/browser/49e77669-01dd-447e-a804-36d42b3400cf
+1655767908782	Marionette	INFO	Listening on port 50326
+1655767909069	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655767916218	Marionette	INFO	Stopped listening on port 50326
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655767916523	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767958348	geckodriver	INFO	Listening on 127.0.0.1:50340
+1655767962557	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50341" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofilekpCdfs"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655767963032	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50341/devtools/browser/b4d1728c-d26f-4537-adc2-5c954b171b13
+1655767964591	Marionette	INFO	Listening on port 50346
+1655767964633	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655767973210	Marionette	INFO	Stopped listening on port 50346
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655767973501	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655767998084	geckodriver	INFO	Listening on 127.0.0.1:50358
+1655768002314	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50359" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofileujYNBj"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655768002757	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50359/devtools/browser/04112c45-204d-43f1-9615-34782fd06632
+1655768004165	Marionette	INFO	Listening on port 50364
+1655768004375	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655768009787	Marionette	INFO	Stopped listening on port 50364
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+
+###!!! [Child][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+!!! error running onStopped callback: TypeError: callback is not a function
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+
+1655768010100	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655768083966	geckodriver	INFO	Listening on 127.0.0.1:50386
+1655768088234	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50387" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile39Pl1f"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655768088664	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50387/devtools/browser/3d6cda42-cb60-4c67-8d76-1d186a51887f
+1655768090263	Marionette	INFO	Listening on port 50392
+1655768090299	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655768091655	Marionette	INFO	Stopped listening on port 50392
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+
+###!!! [Parent][MessageChannel] Error: (msgtype=0x390076,name=PContent::Msg_DestroyBrowsingContextGroup) Closed channel: cannot send/recv
+
+
+###!!! [Parent][MessageChannel] Error: (msgtype=0x390076,name=PContent::Msg_DestroyBrowsingContextGroup) Closed channel: cannot send/recv
+
+
+###!!! [Parent][MessageChannel] Error: (msgtype=0x390076,name=PContent::Msg_DestroyBrowsingContextGroup) Closed channel: cannot send/recv
+
+1655768092659	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655768101201	geckodriver	INFO	Listening on 127.0.0.1:50404
+1655768105373	mozrunner::runner	INFO	Running command: "C:\\Users\\CALSysLab\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "50405" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\CALSYS~1\\AppData\\Local\\Temp\\rust_mozprofile2YRGSz"
+console.log: "TorSettings: loadFromPrefs()"
+console.log: "TorConnect: Init"
+console.log: "TorConnect: observed profile-after-change"
+console.log: "TorConnect: observing topic 'TorBootstrapStatus'"
+console.log: "TorConnect: observing topic 'TorBootstrapError'"
+console.log: "TorConnect: observing topic 'TorProcessExited'"
+console.log: "TorConnect: observing topic 'TorLogHasWarnOrErr'"
+console.log: "TorConnect: observing topic 'torsettings:ready'"
+console.log: "TorSettings: observed profile-after-change"
+1655768105853	Marionette	INFO	Marionette enabled
+console.log: "TorConnect: will load after bootstrap => [about:blank]"
+JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory.
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined
+console.error: "Could not load engine [email protected]: Error: Extension is invalid"
+DevTools listening on ws://localhost:50405/devtools/browser/9c4a4d71-25ff-4980-a54d-8545d6200790
+1655768107431	Marionette	INFO	Listening on port 50410
+1655768107530	RemoteAgent	WARN	TLS certificate errors will be ignored for this session
+1655768119155	Marionette	INFO	Stopped listening on port 50410
+JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver]
+!!! error running onStopped callback: TypeError: callback is not a function
+1655768119438	RemoteAgent	ERROR	unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]"  nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)"  location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64"  data: no] Stack trace: stop()@TargetObserver.jsm:64
+unwatchForTabs()@TargetList.jsm:70
+unwatchForTargets()@TargetList.jsm:37
+destructor()@TargetList.jsm:109
+stop()@CDP.jsm:104
+close()@RemoteAgent.jsm:138
+1655768229472	geckodriver	INFO	Listening on 127.0.0.1:50431
+1655768233458	webdriver::server	WARN	Rejected request with missing Host header

Forums/Altenens/parser.py

@@ -0,0 +1,264 @@
+__author__ = 'Helium'
+
+# 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 cryptBB_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 user'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())
+
+    # Finding the repeated tag that corresponds to the listing of posts
+
+    # try:
+    posts = soup.find('table', {"class": "tborder tfixed clear"}).find('td', {"id": "posts_container"}).find_all(
+        'div', {"class": "post"})
+
+    # 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('span', {"class": "largetext"})
+
+        # Finding the author (user) of the post
+
+        author = post_wrapper.text.strip()
+        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
+        '''
+
+        # CryptBB 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))
+
+        # 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))
+
+        # 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)
+
+        # Finding the post
+
+        inner = postarea.find('div', {"class": "post_body scaleimages"})
+        inner = inner.text.strip()
+        post.append(cleanString(inner))
+
+        # Finding the user'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 user'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, user, status, reputation, interest, sign, post, feedback, addDate)
+
+    # Sending the results
+
+    return row
+
+# This is the method to parse the Listing Pages (one page with many posts)
+
+def cryptBB_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
+    author = []        # all authors of each topic
+    views = []         # number of views of each topic
+    posts = []         # number of posts 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"})
+
+    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
+        user = ps.strip()
+        author.append(cleanString(user))
+
+        # Finding the number of replies
+        columns = itopic.findChildren('td',recursive=False)
+        replies = columns[3].text
+
+        posts.append(cleanString(replies))
+
+        # Finding the number of Views
+        tview = columns[4].text
+        views.append(cleanString(tview))
+
+        # If no information about when the topic was added, just assign "-1" to the variable
+
+        addDate.append("-1")
+
+    return organizeTopics("CryptBB", nm, topic, board, author, views, posts, href, addDate)
+
+
+def altenens_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+
+    listing = soup.find('div', {"class": "structItemContainer-group js-threadList"}).find_all('div', {"class": "structItem structItem--thread is-unread js-inlineModContainer js-threadListItem-1843963"})
+
+    for a in listing:
+        link = a.find('div', {"class": "structItem-title"}).find('a').get('href')
+
+        href.append(link)
+
+    return href

Forums/CrackingPro/crawler_mechanize.py

@@ -1,257 +0,0 @@
-__author__ = '91Shadows'
-
-'''
-OnniForums Crawler (Mechanize)
-'''
-
-import codecs, os, re
-import socks, socket, time
-from datetime import date
-
-import urllib.parse as urlparse
-import http.client as httplib
-import mechanize
-import subprocess
-from bs4 import BeautifulSoup
-from Forums.Initialization.prepare_parser import new_parse
-from Forums.OnniForums.parser import onniForums_listing_parser
-
-counter = 1
-httplib.HTTPConnection._http_vsn = 10
-httplib.HTTPConnection._http_vsn_str = 'HTTP/1.0'
-baseURL = 'http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=42&sid=ee2cbfd73c12923d979790b2bb4bdfd5'
-socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 9150)
-
-
-# Opens Tor Browser, crawls the website
-def startCrawling():
-    opentor()
-    getUrl()
-    forumName = getForumName()
-    br = getAccess()
-
-    if br != 'down':
-        crawlForum(br)
-        new_parse(forumName, False)
-
-    # new_parse(forumName, False)
-
-    closetor()
-
-
-# Opens Tor Browser
-def opentor():
-    global pid
-    print("Connecting Tor...")
-    path = open('../../path.txt').readline()
-    pro = subprocess.Popen(path)
-    pid = pro.pid
-    time.sleep(7.5)
-    input("Tor Connected. Press ENTER to continue\n")
-    return
-
-
-# Creates a connection through Tor Port
-def getUrl(timeout=None):
-    socket.socket = socks.socksocket
-    socket.create_connection = create_connection
-    return
-
-
-# Makes the onion address request
-def create_connection(address, timeout=None, source_address=None):
-    sock = socks.socksocket()
-    sock.connect(address)
-    return sock
-
-
-# Returns the name of website
-def getForumName():
-    name = 'CrackingPro'
-    return name
-
-
-# Return the link of website
-def getFixedURL():
-    url = 'http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=42&sid=ee2cbfd73c12923d979790b2bb4bdfd5'
-
-    return url
-
-
-# Closes Tor Browser
-def closetor():
-    global pid
-    os.system("taskkill /pid " + str(pid))
-    print('Closing Tor...')
-    time.sleep(3)
-    return
-
-
-# Creates a Mechanize browser and initializes its options
-def createBrowser():
-    br = mechanize.Browser()
-    cj = mechanize.CookieJar()
-    br.set_cookiejar(cj)
-
-    # Browser options
-    br.set_handle_equiv(True)
-    br.set_handle_redirect(True)
-    br.set_handle_referer(True)
-    br.set_handle_robots(False)
-    br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
-    br.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'),
-                     ('Accept', '*/*')]
-
-    return br
-
-
-def getAccess():
-    url = getFixedURL()
-    br = createBrowser()
-
-    try:
-
-        br.open(url)
-        return br
-
-    except:
-
-        return 'down'
-
-
-# Saves the crawled html page
-def savePage(page, url):
-    filePath = getFullPathName(url)
-    os.makedirs(os.path.dirname(filePath), exist_ok=True)
-    a = page.read()
-    open(filePath, "wb").write(a)
-    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 = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/CrackingPro/HTML_Pages/' + str(
-            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-            "%04d" % date.today().year) + '/' + 'Description/' + fileName + '.html'
-    else:
-        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/CrackingPro/HTML_Pages/' + str(
-            "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-            "%04d" % date.today().year) + '/' + 'Listing/' + fileName + '.html'
-    return fullPath
-
-
-# Creates the name of the file based on 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
-
-
-# Hacking and Markets related topics
-def getInterestedLinks():
-    links = []
-
-    links.append('http://bestteermb42clir6ux7xm76d4jjodh3fpahjqgbddbmfrgp4skg2wqd.onion/viewforum.php?f=43&sid=e12864ffccc5df877b03b573534955be')
-
-    return links
-
-
-# Start crawling Forum pages
-def crawlForum(br):
-    print("Crawling CrackingPro forum")
-
-    linksToCrawl = getInterestedLinks()
-    visited = set(linksToCrawl)
-    initialTime = time.time()
-
-
-    i = 0
-    while i < len(linksToCrawl):
-        link = linksToCrawl[i]
-        print('Crawling :', link)
-        try:
-            page = br.open(link)#open url
-            savePage(page, link)
-
-            res = br.response().read()
-            soup = BeautifulSoup(res, 'html.parser')
-
-            next_link = soup.find("a", {"rel": "next"})
-            if next_link != None:
-                full_url = urlparse.urljoin(linksToCrawl[i], next_link['href'])
-                linksToCrawl.insert(i + 1, full_url)
-
-            listOfTopics = findDescriptionPages(link)
-            for topic in listOfTopics:
-                itemPage = br.open(str(topic))
-                savePage(itemPage, topic)
-
-        except Exception as e:
-            print('Error getting link: ', link, e)
-        i += 1
-
-    # finalTime = time.time()
-    # print finalTime - initialTime
-
-    input("Crawling CrackingPro forum done sucessfully. Press ENTER to continue\n")
-
-    return
-
-
-# Returns True if the link is 'Topic' Links
-def isDescriptionLink(url):
-    if 'Topic' in url:
-        return True
-    return False
-
-
-# Returns True if the link is a listingPage link
-def isListingLink(url):
-    '''
-    reg = 'board=[0-9]+.[0-9]+\Z'
-    if len(re.findall(reg, url)) == 0:
-        return False
-    return True
-    '''
-    if 'Forum' in url:
-        return True
-    return False
-
-
-# calling the parser to define the links
-def findDescriptionPages(url):
-    soup = ""
-
-    error = False
-    try:
-        html = codecs.open(
-            "C:\\Users\\CALSysLab\\Documents\\threatIntelligence-main\\DarkWebMining_Working\\Forums\\CrackingPro\\HTML_Pages\\" + str(
-                "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-                "%04d" % date.today().year) + "\\Listing\\" + getNameFromURL(url) + ".html", encoding='utf8')
-        soup = BeautifulSoup(html, "html.parser")
-    except:
-        try:
-            html = open(
-                "C:\\Users\\CALSysLab\\Documents\\threatIntelligence-main\\DarkWebMining_Working\\Forums\\CrackingPro\\HTML_Pages\\" + str(
-                    "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
-                    "%04d" % date.today().year) + "\\Listing\\" + getNameFromURL(url) + ".html")
-            soup = BeautifulSoup(html, "html.parser")
-        except:
-            error = True
-            print("There was a problem to read the file " + getNameFromURL(url) + " in the listing section.")
-
-    if not error:
-        return onniForums_listing_parser(soup)
-
-    else:
-        return []
-
-
-def crawler():
-    startCrawling()
-    print("Crawling and Parsing CrackingPro .... DONE!")

Forums/CryptBB/crawler_mechanize.py

@@ -132,11 +132,11 @@ def savePage(page, url):
 def getFullPathName(url):
     fileName = getNameFromURL(url)
     if isDescriptionLink(url):
-        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/BestCardingWorld/HTML_Pages/' + str(
+        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/ThiefWorld/HTML_Pages/' + str(
             "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
             "%04d" % date.today().year) + '/' + 'Description/' + fileName + '.html'
     else:
-        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/BestCardingWorld/HTML_Pages/' + str(
+        fullPath = 'C:/Users/CALSysLab/Documents/threatIntelligence-main/DarkWebMining_Working/Forums/ThiefWorld/HTML_Pages/' + str(
             "%02d" % date.today().month) + str("%02d" % date.today().day) + str(
             "%04d" % date.today().year) + '/' + 'Listing/' + fileName + '.html'
     return fullPath

Forums/CryptBB/crawler_selenium.py

@@ -43,7 +43,7 @@ def startCrawling():
             print(driver.current_url, e)
         closetor(driver)
 
-    # new_parse(forumName, baseURL, False)
+    new_parse(forumName, baseURL, False)
 
 
 # Opens Tor Browser

Forums/CryptBB/parser.py

@@ -171,8 +171,8 @@ def cryptBB_listing_parser(soup):
     forum = "OnniForums"   # 0 *forum name
     board = "-1"        # 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)
-    topic = []          # 2 *all topics
-    author = []         # 3 *all authors of each topic
+    author = []         # 2 *all authors of each topic
+    topic = []          # 3 *all topics
     views = []          # 4 number of views of each topic
     posts = []          # 5 number of posts of each topic
     href = []           # 6 this variable should receive all cleaned urls (we will use this to do the marge between

Forums/Initialization/forumsList.txt

@@ -1 +1 @@
-OnniForums
+OnniForums

Forums/Initialization/forums_mining.py

@@ -9,7 +9,8 @@ from datetime import *
 from Forums.BestCardingWorld.crawler_selenium import crawler as crawlerBestCardingWorld
 from Forums.CryptBB.crawler_selenium import crawler as crawlerCryptBB
 from Forums.OnniForums.crawler_selenium import crawler as crawlerOnniForums
-# from Forums.CrackingPro.crawler_selenium import crawler as crawlerCrackingPro
+from Forums.AbyssForum.crawler_selenium import crawler as crawlerAbyssForum
+from Forums.Altenens.crawler_selenium import crawler as crawlerAltenensForum
 
 
 
@@ -106,6 +107,10 @@ if __name__ == '__main__':
             crawlerOnniForums()
         # elif forum == "CrackingPro":
         #     crawlerCrackingPro()
+        elif forum == "AbyssForum":
+            crawlerAbyssForum()
+        elif forum == "Altenens":
+            crawlerAltenensForum()
 
     print("Scraping process completed successfully!")
 

Forums/OnniForums/crawler_selenium.py

@@ -1,4 +1,4 @@
-__author__ = 'DarkWeb'
+__author__ = 'Helium'
 
 '''
 OnniForums Crawler (Selenium)
@@ -16,6 +16,7 @@ from PIL import Image
 
 import urllib.parse as urlparse
 import os, re, time
+import configparser
 from datetime import date
 import subprocess
 from bs4 import BeautifulSoup
@@ -23,6 +24,8 @@ from Forums.Initialization.prepare_parser import new_parse
 from Forums.OnniForums.parser import onniForums_links_parser
 from Forums.Utilities.utilities import cleanHTML
 
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
 counter = 1
 baseURL = 'http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/'
 
@@ -48,8 +51,7 @@ def startCrawling():
 def opentor():
     global pid
     print("Connecting Tor...")
-    path = open('../../path.txt').readline().strip()
-    pro = subprocess.Popen(path)
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
     pid = pro.pid
     time.sleep(7.5)
     input('Tor Connected. Press ENTER to continue\n')
@@ -72,7 +74,8 @@ def login(driver):
     #Password here
     passwordBox.send_keys('$ourP@tchK1ds')
 
-    input("Press ENTER when log in is completed\n")
+    clicker = driver.find_element(by=By.XPATH, value='/html/body/div/div[2]/div/form/div/input')
+    clicker.click()
 
     # 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(
@@ -105,12 +108,9 @@ def closetor(driver):
 # 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(config.get('TOR', 'firefox_binary_path'))
 
-    ff_binary = FirefoxBinary(lines[0].strip())
-
-    ff_prof = FirefoxProfile(lines[1].strip())
+    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)
@@ -118,7 +118,7 @@ def createFFDriver():
     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.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)
@@ -132,10 +132,11 @@ def createFFDriver():
     ff_prof.set_preference("javascript.enabled", True)
     ff_prof.update_preferences()
 
-    service = Service(lines[2].strip())
+    service = Service(config.get('TOR', 'geckodriver_path'))
 
     driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
 
+
     return driver
 
 
@@ -190,23 +191,23 @@ def getInterestedLinks():
     # Hacking & Cracking tutorials
     links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-tutorials')
     # Hacking & Cracking questions
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-questions')
-    # Exploit PoCs
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Exploit-PoCs')
-    # Cracked software
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Cracked-software')
-    # Malware-development
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Malware-development')
-    # Carding & Fraud
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Carding-Fraud')
-    # Darknet Discussions
-    links.append('http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion/forumdisplay.php?fid=88')
-    # OPSEC
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-OPSEC')
-    # Databases
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Databases')
-    # Proxies
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Proxies')
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-questions')
+    # # Exploit PoCs
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Exploit-PoCs')
+    # # Cracked software
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Cracked-software')
+    # # Malware-development
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Malware-development')
+    # # Carding & Fraud
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Carding-Fraud')
+    # # Darknet Discussions
+    # links.append('http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion/forumdisplay.php?fid=88')
+    # # OPSEC
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-OPSEC')
+    # # Databases
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Databases')
+    # # Proxies
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Proxies')
 
     return links
 
@@ -243,12 +244,12 @@ def crawlForum(driver):
                     savePage(driver.page_source, item)
                     driver.back()
                     # comment out, one topic per page
-                    # break
+                    break
 
                 # comment out, go through all pages
-                #if count == 1:
-                 #   count = 0
-                  #  break
+                if count == 1:
+                   count = 0
+                   break
 
                 try:
                     temp = driver.find_element(by=By.XPATH, value=

MarketPlaces/BlackPyramid/crawler_selenium.py

@@ -0,0 +1,314 @@
+__author__ = 'Helium'
+
+'''
+BlackPyramid 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.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.BlackPyramid.parser import blackpyramid_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/login/'
+
+
+# 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():
+    opentor()
+    # mktName = getMKTName()
+    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
+#prompts for ENTER input to continue
+def opentor():
+    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
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'BlackPyramid'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+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():
+    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", 2)
+    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)
+
+    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'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for login page
+    login_link = driver.find_element(by=By.XPATH, value='/html/body/div/div/div[3]/div/main/div/div/div/div[2]/div/div/div/section[1]/input[1]')
+    login_link.click() # open tab with url
+
+    # entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
+    # Username here
+    usernameBox.send_keys('ChipotleSteakBurrito')
+    passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
+    # Password here
+    passwordBox.send_keys('BlackBeans')
+
+    input("Press ENTER when CAPTCHA is completed\n")
+
+    # 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, '/html/body/div[2]/form/nav/nav/ul/li[2]/div/a/span[1]')))
+
+
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+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
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\BlackPyramid\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\BlackPyramid\HTML_Pages\\' + 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
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Hacking Guides
+    links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    # # Exploits
+    # links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    # # botnets/malware
+    # links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    # # fraud software
+    # links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    # # Other Tools
+    # links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    # # Services
+    # links.append('http://blackpyoc3gbnrlvxqvvytd3kxqj7pd226i2gvfyhysj24ne2snkmnyd.onion/search/results/')
+    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 BlackPyramid market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            try:
+                clicker = driver.find_element(by=By.XPATH, value='/html/body/div[2]/form/nav/nav/ul/li[2]/div/a')
+                clicker.click() # open tab with url
+                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()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    clicker = driver.find_element(by=By.XPATH, value=
+                        '/html/body/center/div[4]/div/div[3]/div[23]/div[2]/input[1]')
+                    if clicker == "":
+                        raise NoSuchElementException
+                    try:
+                        clicker.click()
+                    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 BlackPyramid forum done sucessfully. Press ENTER to continue\n")
+
+
+# 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 'products' 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 'search' 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 ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return blackpyramid_links_parser(soup)
+
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BlackPyramid .... DONE!")

MarketPlaces/BlackPyramid/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'Helium'
+
+# 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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    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
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.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 = a.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)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def blackpyramid_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+    href = []
+
+    listing = soup.findAll('article', {"class": "product"})
+
+    for div in listing:
+
+        link = div.find('a', {"class": "ah39063"})['href']
+        href.append(link)
+
+    return href

MarketPlaces/DarkFox/crawler_selenium.py

@@ -30,17 +30,17 @@ baseURL = 'http://57d5j6bbwlpxbxe5tsjjy3vziktv3fo2o5j3nheo4gpg6lzpsimzqzid.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():
-    # opentor()
+    opentor()
     mktName = getMKTName()
-    # driver = getAccess()
-
-    # if driver != 'down':
-    #     try:
-    #         captcha(driver)
-    #         crawlForum(driver)
-    #     except Exception as e:
-    #         print(driver.current_url, e)
-    #     closetor(driver)
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            captcha(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
 
     new_parse(mktName, False)
 

MarketPlaces/Initialization/marketsList.txt

@@ -1 +1 @@
-Tor2door
+MikesGrandStore

MarketPlaces/Initialization/markets_mining.py

@@ -9,6 +9,11 @@ from datetime import *
 from MarketPlaces.DarkFox.crawler_selenium import crawler as crawlerDarkFox
 from MarketPlaces.Tor2door.crawler_selenium import crawler as crawlerTor2door
 from MarketPlaces.ThiefWorld.crawler_selenium import crawler as crawlerThiefWorld
+from MarketPlaces.TorBay.crawler_selenium import crawler as crawlerTorBay
+from MarketPlaces.LionMarketplace.crawler_selenium import crawler as crawlerLionMarketplace
+from MarketPlaces.TorMarket.crawler_selenium import crawler as crawlerTorMarket
+from MarketPlaces.MikesGrandStore.crawler_selenium import crawler as crawlerMikesGrandStore
+
 
 import time
 
@@ -69,5 +74,15 @@ if __name__ == '__main__':
             crawlerTor2door()
         elif mkt == "ThiefWorld":
             crawlerThiefWorld()
+        elif mkt == "TorBay":
+            crawlerTorBay()
+        elif mkt == "LionMarketplace":
+            crawlerLionMarketplace()
+        elif mkt == "TorMarket":
+            crawlerTorMarket()
+        elif mkt == "MikesGrandStore":
+            crawlerMikesGrandStore()
+
+
 
     print("Scraping process completed successfully!")

MarketPlaces/LionMarketplace/crawler_selenium.py

@@ -0,0 +1,310 @@
+__author__ = 'Helium'
+
+'''
+LionMarketplace 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.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.LionMarketplace.parser import lionmarketplace_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.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():
+    opentor()
+    # mktName = getMKTName()
+    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
+#prompts for ENTER input to continue
+def opentor():
+    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
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'LionMarketplace'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+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():
+    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", 2)
+    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)
+
+    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'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[2]/div[2]/div[2]/div[1]/div/div[2]/div")))
+
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+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
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\LionMarketplace\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\LionMarketplace\HTML_Pages\\' + 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
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Software/Malware
+    links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/16')
+    # # Carding
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/20')
+    # # Hacker for hire
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/0b19f3a0-c7e8-11ec-997b-0dcb6b05ce1d')
+    # # Phishing
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/18098bb0-c7e8-11ec-95e9-45b5e8898cbd')
+    # # Ransomware
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/ce72cee0-c7e7-11ec-a86b-c1ff2d3b2020')
+    # # Exploits
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/e26387c0-c7e7-11ec-a708-ab6dc5117763')
+    # # Spamming and Anti-Captcha
+    # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/f08a9380-c7e7-11ec-918c-ffef7c670c97')
+    # hacked accounts
+    #links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/fd47b4a0-c7e7-11ec-937b-61246c4b12b3')
+
+    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 LionMarketplace market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 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()
+
+                    # 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[2]/nav/ul/li[5]/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 LionMarketplace forum done sucessfully. Press ENTER to continue\n")
+
+
+# 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 'product' 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 'category' 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 ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return lionmarketplace_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/LionMarketplace/parser.py

@@ -0,0 +1,291 @@
+__author__ = 'Helium'
+
+# 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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    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
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.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 = a.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)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def lionmarketplace_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "container d-flex justify-content-center"})
+
+    for a in listing:
+        bae = a.find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/MikesGrandStore/crawler_selenium.py

@@ -0,0 +1,297 @@
+__author__ = 'Helium'
+
+'''
+Mikes Grand Store 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.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.MikesGrandStore.parser import mikesgrandstore_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://4yx2akutmkhwfgzlpdxiah7cknurw6vlddlq24fxa3r3ebophwgpvhyd.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():
+    opentor()
+    # mktName = getMKTName()
+    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
+#prompts for ENTER input to continue
+def opentor():
+    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
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'MikesGrandStore'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://4yx2akutmkhwfgzlpdxiah7cknurw6vlddlq24fxa3r3ebophwgpvhyd.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+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():
+    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", 2)
+    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)
+
+    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'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[1]/header/div/div[3]/div/div/ul/li[6]/a")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+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
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\MikesGrandStore\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\MikesGrandStore\HTML_Pages\\' + 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
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Hacking and DDOS
+    links.append('http://4yx2akutmkhwfgzlpdxiah7cknurw6vlddlq24fxa3r3ebophwgpvhyd.onion/product-category/hacking/')
+    # # databases
+    # links.append('http://4yx2akutmkhwfgzlpdxiah7cknurw6vlddlq24fxa3r3ebophwgpvhyd.onion/product-category/databases/')
+
+    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 MikesGrandStore market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 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()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    count = 0
+                    break
+
+                try:
+                    link = driver.find_element(by=By.XPATH, value=
+                        '/html/body/div[1]/main/div/div[1]/div/div[3]/nav/ul/li[6]/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 MikesGrandStore forum done sucessfully. Press ENTER to continue\n")
+
+
+# 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 'product/' 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 'product-category' 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 ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return mikesgrandstore_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/MikesGrandStore/parser.py

@@ -0,0 +1,291 @@
+__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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    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
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.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 = a.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)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def mikesgrandstore_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "box-image"})
+
+    for a in listing:
+        bae = a.find('div', {"class": "image-fade_in_back"}).find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/ThiefWorld/crawler_selenium.py

@@ -45,7 +45,7 @@ def startCrawling():
             print(driver.current_url, e)
         closetor(driver)
 
-    # new_parse(mktName, False)
+    # new_parse(forumName, baseURL, False)
 
 
 # Opens Tor Browser

MarketPlaces/TorBay/crawler_selenium.py

@@ -0,0 +1,290 @@
+__author__ = 'Helium'
+
+'''
+TorBay Market 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.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, time
+from datetime import date
+import subprocess
+import configparser
+import subprocess
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.TorBay.parser import torbay_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://torbay3253zck4ym5cbowwvrbfjjzruzthrx3np5y6owvifrnhy5ybid.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():
+    opentor()
+    mktName = getMKTName()
+    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
+#prompts for ENTER input to continue
+def opentor():
+    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
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'TorBay Market'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://torbay3253zck4ym5cbowwvrbfjjzruzthrx3np5y6owvifrnhy5ybid.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+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():
+    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
+
+#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'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[2]/div/div/div/ul/li[6]/a")))
+
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+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
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\TorBay\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'..\TorBay\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, 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
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Hacking
+    links.append('http://torbay3253zck4ym5cbowwvrbfjjzruzthrx3np5y6owvifrnhy5ybid.onion/category/hacking')
+
+    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  TorBay Market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 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()
+
+                    #comment out
+                    break
+
+                # # comment out
+                if count == 1:
+                   count = 0
+                   break
+
+                try:
+                    link = driver.find_element(by=By.XPATH, value=
+                        '/html/body/section/div/div/div[2]/div/div[2]/ul/li[3]/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 TorBay forum done sucessfully. Press ENTER to continue\n")
+
+
+# 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 'product' 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 'category' 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 ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return torbay_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/TorBay/parser.py

@@ -0,0 +1,291 @@
+__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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    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
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.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 = a.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)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def torbay_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.find('section', {"id": "content"}).findAll('div', {"class": "product-card"})
+
+    for a in listing:
+        bae = a.find('div', {"class": "pc-footer"}).find('a', {"class": "btn btn-primary"}, href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/TorMarket/crawler_selenium.py

@@ -0,0 +1,299 @@
+__author__ = 'Helium'
+
+'''
+TorMarket 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.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.TorMarket.parser import tormarket_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.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():
+    opentor()
+    # mktName = getMKTName()
+    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
+#prompts for ENTER input to continue
+def opentor():
+    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
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'TorMarket'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+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():
+    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", 2)
+    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)
+
+    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'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[2]/div/div/div/main/article/div/section[4]/div/div[1]/div/div/div/div/ul/li[15]/ul/li[3]/a")))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+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
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import CURRENT_DATE
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = r'..\TorMarket\HTML_Pages\\' + CURRENT_DATE + r'\\Description\\' + fileName + '.html'
+    else:
+        fullPath = r'..\TorMarket\HTML_Pages\\' + 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
+# Guides and Tutorials, Digital Products, and Software and Malware
+#as you can see they are categories of products
+def getInterestedLinks():
+    links = []
+
+    # Hacking Tutorials
+    links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/guides-tutorials/hacking/')
+    # # Malware
+    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/malware/')
+    # # Hacking Services
+    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/services/hacking-services/')
+
+    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 TorMarket market")
+
+    linksToCrawl = getInterestedLinks()
+    visited = set(linksToCrawl)
+    initialTime = time.time()
+
+    count = 0
+    i = 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()
+
+                    # 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/div/div[1]/main/nav/ul/li[5]/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 TorMarket forum done sucessfully. Press ENTER to continue\n")
+
+
+# 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 'shop' 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 'product-category' 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 ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return tormarket_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/TorMarket/parser.py

@@ -0,0 +1,291 @@
+__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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def darkfox_description_parser(soup):
+
+    # Fields to be parsed
+
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    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
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+
+    # Finding Product Name
+    name = soup.find('h1').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('h3').find('a').text.strip()
+
+    # Finding Vendor Rating
+    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Successful Transactions
+    success = soup.find('h3').text
+    success = success.replace("Vendor: ", "")
+    success = success.replace(vendor, "")
+    success = success.replace("(", "")
+    success = success.replace(")", "")
+    success = success.strip()
+
+    bae = soup.find('div', {'class': "box"}).find_all('ul')
+
+    # Finding Prices
+    USD = bae[1].find('strong').text.strip()
+
+    li = bae[2].find_all('li')
+
+    # Finding Escrow
+    escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Category
+    category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding the Product Quantity Available
+    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+
+    # Finding Number Sold
+    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+
+    li = bae[3].find_all('li')
+
+    # Finding Shipment Information (Origin)
+    if "Ships from:" in li[-2].text:
+        shipFrom = li[-2].text
+        shipFrom = shipFrom.replace("Ships from: ", "")
+        # shipFrom = shipFrom.replace(",", "")
+        shipFrom = shipFrom.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text
+    shipTo = shipTo.replace("Ships to: ", "")
+    shipTo = shipTo.strip()
+    if "certain countries" in shipTo:
+        countries = ""
+        tags = li[-1].find_all('span', {'class': "tag"})
+        for tag in tags:
+            country = tag.text.strip()
+            countries += country + ", "
+        shipTo = countries.strip(", ")
+
+    # Finding the Product description
+    describe = soup.find('div', {'class': "pre-line"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    '''# Finding the Number of Product Reviews
+    tag = soup.findAll(text=re.compile('Reviews'))
+    for index in tag:
+        reviews = index
+        par = reviews.find('(')
+        if par >=0:
+            reviews = reviews.replace("Reviews (","")
+            reviews = reviews.replace(")","")
+            reviews = reviews.split(",")
+            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
+        else  :
+            review = "-1"'''
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def darkfox_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # Total_Products (Should be Integer)
+    mktName = "DarkFox"                       # 0 Marketplace_Name
+    name = []                                 # 1 Product_Name
+    CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
+    category = []                             # 4 Product_Category
+    describe = []                             # 5 Product_Description
+    escrow = []                               # 6 Vendor_Warranty
+    views = []                                # 7 Product_Number_Of_Views
+    reviews = []                              # 8 Product_Number_Of_Reviews
+    addDate = []                              # 9 Product_AddDate
+    lastSeen = []                             # 10 Product_LastViewDate
+    BTC = []                                  # 11 Product_BTC_SellingPrice
+    USD = []                                  # 12 Product_USD_SellingPrice
+    EURO = []                                 # 13 Product_EURO_SellingPrice
+    sold = []                                 # 14 Product_QuantitySold
+    qLeft =[]                                 # 15 Product_QuantityLeft
+    shipFrom = []                             # 16 Product_ShippedFrom
+    shipTo = []                               # 17 Product_ShippedTo
+    vendor = []                               # 18 Vendor
+    rating = []                               # 19 Vendor_Rating
+    success = []                              # 20 Vendor_Successful_Transactions
+    href = []                                 # 23 Product_Links (Urls)
+
+    listing = soup.findAll('div', {"class": "card"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product
+        product = bae[1].find('p').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        bae = a.find('div', {'class': "media-content"}).find('div').find_all('div')
+
+        if len(bae) >= 5:
+            # Finding Prices
+            price = bae[0].text
+            ud = price.replace(" USD", " ")
+            # u = ud.replace("$","")
+            u = ud.replace(",", "")
+            u = u.strip()
+            USD.append(u)
+            # bc = (prc[1]).strip(' BTC')
+            # BTC.append(bc)
+
+            # Finding the Vendor
+            vendor_name = bae[1].find('a').text
+            vendor_name = vendor_name.replace(",", "")
+            vendor_name = vendor_name.strip()
+            vendor.append(vendor_name)
+
+            # Finding the Category
+            cat = bae[2].find('small').text
+            cat = cat.replace("Category: ", "")
+            cat = cat.replace(",", "")
+            cat = cat.strip()
+            category.append(cat)
+
+            # Finding Number Sold and Quantity Left
+            num = bae[3].text
+            num = num.replace("Sold: ", "")
+            num = num.strip()
+            sold.append(num)
+
+            quant = bae[4].find('small').text
+            quant = quant.replace("In stock: ", "")
+            quant = quant.strip()
+            qLeft.append(quant)
+
+            # Finding Successful Transactions
+            freq = bae[1].text
+            freq = freq.replace(vendor_name, "")
+            freq = re.sub(r'Vendor Level \d+', "", freq)
+            freq = freq.replace("(", "")
+            freq = freq.replace(")", "")
+            freq = freq.strip()
+            success.append(freq)
+
+        # Searching for CVE and MS categories
+        cve = a.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 = a.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)
+
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def tormarket_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "product-loop-content text-center"})
+
+    for a in listing:
+        bae = a.find('h2', {"class": "woocommerce-loop-product__title"}).find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href

setup.ini

@@ -1,10 +1,10 @@
 [TOR]
-firefox_binary_path = C:\Users\calsyslab\Desktop\Tor Browser\Browser\firefox.exe
-firefox_profile_path = C:\Users\calsyslab\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default
-geckodriver_path = C:\Users\calsyslab\Projects\dw_pipeline_test\selenium\geckodriver.exe
+firefox_binary_path = C:\Users\\Helium\Desktop\Tor Browser\Browser\firefox.exe
+firefox_profile_path = C:\Users\\Helium\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default
+geckodriver_path = C:\Users\\Helium\\PycharmProjects\dw_pipeline_test\selenium\geckodriver.exe
 
 [Project]
-project_directory = C:\Users\calsyslab\Projects\dw_pipeline_test
+project_directory = C:\Users\Helium\\PycharmProjects\dw_pipeline_test
 shared_folder = \\VBoxSvr\VM_Files_(shared)
 
 [PostgreSQL]