completed ThifWorld Crawler

.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="C:\ProgramData\Anaconda3" 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="C:\ProgramData\Anaconda3" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\Helium\anaconda3" project-jdk-type="Python SDK" />
 </project>

Forums/Altenens/crawler_mechanize.py

@@ -0,0 +1,257 @@
+__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/CrackingPro/crawler_selenium.py

@@ -20,7 +20,7 @@ from datetime import date
 import subprocess
 from bs4 import BeautifulSoup
 from Forums.Initialization.prepare_parser import new_parse
-from Forums.OnniForums.parser import cryptBB_links_parser
+from Forums.CrackingPro.parser import crackingPro_links_parser
 from Forums.Utilities.utilities import cleanHTML
 
 counter = 1
@@ -58,7 +58,7 @@ 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').\
@@ -73,7 +73,7 @@ def login(driver):
     #Password here
     passwordBox.send_keys('Gr33nSp@m&3ggs')
 
-
+    '''
 
     input("Press ENTER when log in is completed\n")
 
@@ -237,27 +237,53 @@ def crawlForum(driver):
 
             has_next_page = True
             while has_next_page:
-                list = topicPages(html)#parses?
+                list = topicPages(html)  # for multiple pages
                 for item in list:
-                    itemURL = urlparse.urljoin(baseURL, str(item))
-                    try:
-                        driver.get(itemURL)
-                    except:
-                        driver.refresh()
-                    savePage(driver.page_source, item)
-                    driver.back()
+                    # variable to check if there is a next page for the topic
+                    has_next_topic_page = True
+                    back_counter = 1
+
+                    # check if there is a next page for the topics
+                    while has_next_topic_page:
+                        # try to access next page of th topic
+                        itemURL = urlparse.urljoin(baseURL, str(item))
+                        try:
+                            driver.get(itemURL)
+                        except:
+                            driver.refresh()
+                        savePage(driver.page_source, item)
+
+                        # if there is a next page then go and save....
+                        # next page in the topic?
+                        try:
+                            temp = driver.find_element(by=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
+
+                            if item == "":
+                                raise NoSuchElementException
+                                has_next_topic_page = False
+                            else:
+                                back_counter += 1
+                        except NoSuchElementException:
+                            has_next_topic_page = False
+
+                    # end of loop
+                    for i in range(back_counter):
+                        driver.back()
                     # comment out
                     break
 
                 # comment out
-                #if count == 1:
-                #    count = 0
-                #    break
+                # if count == 1:
+                #     count = 0
+                #     break
 
-                try:
-                    temp = driver.find_element(by=By.XPATH, value=
-                        '/html/body/main/div/div/div/div[4]/div/div[1]/div/ul/')
-                    link = temp.find_element(by=By.CLASS_NAME, value='ipsPagination_next').get_attribute('href')
+                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')
 
                     if link == "":
                         raise NoSuchElementException
@@ -300,7 +326,7 @@ 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 cryptBB_links_parser(soup)
+    return crackingPro_links_parser(soup)
 
 
 def crawler():

Forums/CrackingPro/parser.py

@@ -334,20 +334,22 @@ def onniForums_listing_parser(soup):
 
     #return organizeTopics("TheMajesticGarden", nm, topic, board, view, post, user, addDate, href)
 
-def cryptBB_links_parser(soup):
+def crackingPro_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('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"})
 
     for a in listing:
-        try:
-            link = a.find('span', {"class": "subject_old"}).find('a').get('href')
-        except:
-            link = a.find('span', {"class": "subject_new"}).find('a').get('href')
+        #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')
+
+
 
         href.append(link)
 

MarketPlaces/Initialization/marketsList.txt

@@ -1 +1 @@
-Tor2door
+ThiefWorld

MarketPlaces/Initialization/markets_mining.py

@@ -8,6 +8,7 @@ import os
 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
 
 import time
 
@@ -66,5 +67,7 @@ if __name__ == '__main__':
             crawlerDarkFox()
         elif mkt == 'Tor2door':
             crawlerTor2door()
+        elif mkt == "ThiefWorld":
+            crawlerThiefWorld()
 
     print("Scraping process completed successfully!")

MarketPlaces/Initialization/prepare_parser.py

@@ -1,4 +1,4 @@
-__author__ = 'DarkWeb'
+__author__ = 'Helium'
 
 import glob
 import os

MarketPlaces/ThiefWorld/crawler_selenium.py

@@ -0,0 +1,312 @@
+__author__ = 'Helium'
+
+'''
+ThiefWorld 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
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.ThiefWorld.parser import thiefworld_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.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(mktName, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    path = open('../../path.txt').readline().strip()
+    pro = subprocess.Popen(path)
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'TheifWorld'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.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():
+    file = open('../../path.txt', 'r')
+    lines = file.readlines()
+
+    ff_binary = FirefoxBinary(lines[0].strip())
+
+    ff_prof = FirefoxProfile(lines[1].strip())
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 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(lines[2].strip())
+
+    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/div[1]/div/div[1]/div[1]/ul")))
+
+    temp = driver.find_element(By.XPATH, '/html/body/div/header/div[2]/div/nav/div[2]/a[1]').get_attribute(
+        'href')  # /html/body/div/div[2]/div/div[2]/div
+    link = urlparse.urljoin(baseURL, str(temp))
+    driver.get(link)  # open
+    # 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.ID, "side-bar")))
+
+# 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'..\ThiefWorld\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'..\ThiefWorld\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 and DDOS
+    links.append('http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.onion/catalog/35')
+    # # Carding Manuals
+    links.append('http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.onion/catalog/20')
+    # # Software
+    links.append('http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.onion/catalog/37')
+    # #Database
+    links.append('http://qsw7iurcrdwyml5kg4oxbmtqrcnpxiag3iumdarefzeunnyc2dnyljad.onion/catalog/38')
+
+    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 ThiefWorld 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/div[1]/div/div/div[2]/div[3]/div/ul/li[13]/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 ThiefWorld 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 'catalog' 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 thiefworld_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/ThiefWorld/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 thiefworld_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.find('div', {"class": "row tile__list tileitems_filter pad15 tileproduct__list"}).findAll('div', {"class": "desc"})
+
+    for a in listing:
+        bae = a.find('div', {"class": "title"}).find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href