procrax, cardingleaks - craweler completed

altenens - debugging crawler

torbay - in progress parser

Forums/Altenens/crawler_selenium.py

@@ -60,24 +60,24 @@ def opentor():
 
 # Login using premade account credentials and do login captcha manually
 def login(driver):
-    #click login button
-    login = driver.find_element(by=By.XPATH, value='//*[@id="top"]/div[1]/div/div/div/div[1]/a[1]')
-    login.click()
-
-    #entering username and password into input boxes
-    usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="_xfUid-1-1688066635"]')
-    #Username here
-    usernameBox.send_keys('mylittlepony45')#sends string to the username box
-    passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="_xfUid-2-1688066635"]')
-    #Password here
-    passwordBox.send_keys('johnnyTest@18')# sends string to passwordBox
+    # #click login button
+    # login_link = 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_link)  # open tab with url
+    #
+    # #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/input')
+    # #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/input')
+    # #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]span>')))
+    # 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]/a')))
 
 
 # Returns the name of the website
@@ -241,9 +241,9 @@ def crawlForum(driver):
                         savePage(driver.page_source, item)
 
                         # if there is a next page then go and save....
-                        # next page in the topic?
+                        # specific
                         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')
+                            item = driver.find_element(By.LINK_TEXT, value='Next').get_attribute('href')
 
                             if item == "":
                                 raise NoSuchElementException
@@ -256,8 +256,8 @@ def crawlForum(driver):
                     #end of loop
                     for i in range(counter):
                         driver.back()
-                    # comment out
-                    break
+                    # # comment out
+                    # break
 
                 # comment out
                 if count == 1:
@@ -265,8 +265,7 @@ def crawlForum(driver):
                    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')
-
+                    link = driver.find_element(by=By.LINK_TEXT, value='Next').get_attribute('href')
                     if link == "":
                         raise NoSuchElementException
                     try:

Forums/Initialization/forums_mining.py

@@ -1,7 +1,7 @@
 __author__ = 'DarkWeb'
 
 '''
-Starting point of the Darkweb Mining Platform
+
 '''
 
 import os
@@ -10,8 +10,10 @@ from Forums.BestCardingWorld.crawler_selenium import crawler as crawlerBestCardi
 from Forums.CryptBB.crawler_selenium import crawler as crawlerCryptBB
 from Forums.OnniForums.crawler_selenium import crawler as crawlerOnniForums
 from Forums.AbyssForum.crawler_selenium import crawler as crawlerAbyssForum
-from Forums.Altenens.crawler_selenium import crawler as crawlerAltenensForum
+from Forums.Procrax.crawler_selenium import crawler as crawlerProcraxForum
 from Forums.HiddenAnswers.crawler_selenium import crawler as crawlerHiddenAnswers
+from Forums.Cardingleaks.crawler_selenium import crawler as crawlerCardingleaks
+from Forums.Altenens.crawler_selenium import crawler as crawlerAltenens
 
 import configparser
 import time
@@ -113,9 +115,12 @@ if __name__ == '__main__':
             crawlerHiddenAnswers()
         elif forum == "Altenens":
             crawlerAltenensForum()
-
-    
-    
+        elif forum == 'Procrax':
+            crawlerProcraxForum()
+        elif forum == 'Cardingleaks':
+            crawlerCardingleaks()
+        elif forum == 'Altenens':
+            crawlerAltenens()
 
 
 

Forums/OnniForums/crawler_selenium.py

@@ -31,19 +31,19 @@ baseURL = 'http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion
 
 # Opens Tor Browser, crawls the website
 def startCrawling():
-    # opentor()
+    opentor()
     forumName = getForumName()
-    # driver = getAccess()
+    driver = getAccess()
 
-    # if driver != 'down':
-    #     try:
-    #         login(driver)
-    #         crawlForum(driver)
-    #     except Exception as e:
-    #         print(driver.current_url, e)
-    #     closetor(driver)
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
 
-    new_parse(forum=forumName, url=baseURL, createLog=False)
+    # new_parse(forum=forumName, url=baseURL, createLog=False)
 
 
 # Opens Tor Browser
@@ -190,9 +190,9 @@ def getInterestedLinks():
     links = []
 
     # # Hacking & Cracking tutorials
-    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-tutorials')
+    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-tutorials')
     # Hacking & Cracking questions
-    links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-questions')
+    # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Hacking-Cracking-questions')
     # # Exploit PoCs
     # links.append('http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion/Forum-Exploit-PoCs')
     # # Cracked software
@@ -280,12 +280,12 @@ def crawlForum(driver):
                         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=

Forums/Procrax/crawler_selenium.py

@@ -0,0 +1,319 @@
+__author__ = 'Helium'
+
+'''
+Procrax 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.Procrax.parser import procrax_links_parser
+from Forums.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'https://procrax.cx/'
+
+
+# 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():
+    from Forums.Initialization.forums_mining import config
+
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Login using premade account credentials and do login captcha manually
+def login(driver):
+    WebDriverWait(driver, 50).until(EC.visibility_of_element_located(
+        (By.XPATH, '/html/body/div[1]/div[3]/div[2]/div[3]/div[2]/div[1]/form/div/div/div/dl[4]/dd/div/div[2]/button/span')))
+    # #entering username and password into input boxes
+    # usernameBox = driver.find_element(by=By.NAME, value='login')
+    # #Username here
+    # usernameBox.send_keys('cheese_pizza_man')#sends string to the username box
+    # passwordBox = driver.find_element(by=By.NAME, value='password')
+    # #Password here
+    # passwordBox.send_keys('Gr33nSp@m&3ggs')# sends string to passwordBox
+    #
+    # clicker = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[3]/div[2]/div[3]/div[2]/div[1]/form/div/div/div/dl[4]/dd/div/div[2]/button/span')
+    # clicker.click()
+    #
+    # # # 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[3]/div[2]/div[3]/div[1]/div/div[1]/div')))
+
+
+# Returns the name of the website
+def getForumName():
+    name = 'Procrax'
+    return name
+
+
+# Return the link of the website
+def getFixedURL():
+    url = 'https://procrax.cx/'
+    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():
+    from Forums.Initialization.forums_mining import config
+
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    ff_prof.set_preference("places.history.enabled", False)
+    ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    ff_prof.set_preference("signon.rememberSignons", False)
+    ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    ff_prof.set_preference("network.dns.disablePrefetch", True)
+    ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 3)
+    ff_prof.set_preference("browser.download.folderList", 2)
+    ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", True)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)# 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):
+    from Forums.Initialization.forums_mining import config, CURRENT_DATE
+
+    mainDir = os.path.join(config.get('Project', 'shared_folder'), "Forums/" + getForumName() + "/HTML_Pages")
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html')
+    else:
+        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html')
+    return fullPath
+
+
+# Creates the file name from passed URL
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if (name == ''):
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+def getInterestedLinks():
+    links = []
+
+    # # general hacking
+    # links.append('https://procrax.cx/forums/general-hacking.24/')
+    # # hacking security tools
+    # links.append('https://procrax.cx/forums/hacking-security-tools.20/')
+    # # hacktube
+    # links.append('https://procrax.cx/forums/hacktube.22/')
+    # # cardable
+    #  links.append('https://procrax.cx/forums/cardable-websites.28/')
+    # #  tools
+    # links.append('https://procrax.cx/forums/tools-bots-validators.73/')
+    # general forum
+    links.append('https://procrax.cx/forums/forum-discussions-updates.7/')
+
+
+    return links
+
+
+def crawlForum(driver):
+    print("Crawling the Procrax 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....
+                        # specific
+                        try:
+                            # temp = driver.find_element(By.XPATH, value='/html/body/div[1]/div[3]/div[2]/div[3]/div/div')
+                            item = driver.find_element(By.LINK_TEXT, value='Next').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, #general
+                    # /html/body/div[1]/div[3]/div[2]/div[3]/div/div/div/div[1]/div/nav/div[1]
+                    # temp = driver.find_element(By.XPATH, value='/html/body/div[1]/div[3]/div[2]/div[3]/div/div/div/div[1]/div/nav/div[1]')
+                    link = driver.find_element(by=By.LINK_TEXT, value='Next').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 Procrax 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 procrax_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

Forums/Procrax/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 procrax_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+
+    listing = soup.find_all('div', {"class": "structItem-title"})
+
+    for a in listing:
+        link = a.find('a', {'class': ''}).get('href')
+
+        href.append(link)
+
+    return href

MarketPlaces/M00nkeyMarket/crawler_selenium.py

@@ -2,7 +2,8 @@ __author__ = 'Helium'
 
 '''
 M00nkeyMarket Forum Crawler (Selenium) incomplete
-having trouble checking it due to the captcha
+
+might be impossible to crawl
 '''
 
 from selenium import webdriver
@@ -154,11 +155,11 @@ def login(driver):
     # Password here
     passwordBox.send_keys('genie_show_metheWorld')
 
-    input("Press ENTER when CAPTCHA and anti-phishing is completed\n")
+    input("Press ENTER when CAPTCHA and exit pressed 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/div[1]/div/div/div[2]/div[3]/div/ul/li[2]/ul/li[5]/a")))
+        (By.XPATH, "/html/body/div/div[1]/div/div/div[2]/div[3]/div")))
 
 # Saves the crawled html page, makes the directory path for html pages if not made
 def savePage(page, url):
@@ -248,13 +249,15 @@ def crawlForum(driver):
                     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/div/div[1]/div/div/div[3]/div/div[3]/nav')
-                    link = temp.find_element(by=By.CLASS_NAME, value='next ml-1 mt-1').get_attribute('href')
+                    temp = driver.find_element(by=By.CLASS_NAME, value='col-lg-12 flex-fill ml-auto text-right mb-1')
+                    temp2 = temp.find_element(by=By.CLASS_NAME, value="next ml-1 mt-1")
+                    link = temp2.find_element(By.TAG_NAME, value='a').get_attribute('href')
+
                     if link == "":
                         raise NoSuchElementException
                     try:

MarketPlaces/M00nkeyMarket/parser.py

@@ -284,7 +284,7 @@ def m00nkey_links_parser(soup):
     listing = soup.findAll('h5', {"class": "card-title rounded text-truncate"})
 
     for a in listing:
-        bae = a.find('a', href=True)
+        bae = a.find('a', href=True)#card-title rounded text-truncate
         link = bae['href']
         href.append(link)
 

MarketPlaces/ThiefWorld/crawler_selenium.py

@@ -31,19 +31,19 @@ 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()
+    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, baseURL, False)
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(mktName, baseURL, False)
 
 
 # Opens Tor Browser

MarketPlaces/TorBay/crawler_selenium.py

@@ -64,7 +64,7 @@ def opentor():
 # Returns the name of the website
 #return: name of site in string type
 def getMKTName():
-    name = 'TorBay Market'
+    name = 'TorBay'
     return name
 
 
@@ -226,13 +226,13 @@ def crawlForum(driver):
                     savePage(driver.page_source, item)
                     driver.back()
 
-                    #comment out
-                    break
-
-                # # comment out
-                if count == 1:
-                   count = 0
-                   break
+                #     #comment out
+                #     break
+                #
+                # # # comment out
+                # if count == 1:
+                #    count = 0
+                #    break
 
                 try:
                     link = driver.find_element(by=By.XPATH, value=

MarketPlaces/TorBay/parser.py

@@ -11,7 +11,7 @@ from bs4 import BeautifulSoup
 #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):
+def torbay_description_parser(soup):
 
     # Fields to be parsed
 
@@ -40,43 +40,34 @@ def darkfox_description_parser(soup):
     EURO = "-1"                         # 22 Product_EURO_SellingPrice
 
     # Finding Product Name
-    name = soup.find('h1').text
-    name = name.replace('\n', ' ')
-    name = name.replace(",", "")
-    name = name.strip()
+    name = soup.find('div', {'class': 'product-information'}).find('h1').text.strip()
 
     # Finding Vendor
-    vendor = soup.find('h3').find('a').text.strip()
+    vendor = soup.find('div', {"class": "profile-info"}).find('a').text.strip()
 
     # Finding Vendor Rating
-    rating = soup.find('span', {'class': "tag is-dark"}).text.strip()
+    rating.append(-1)
 
     # 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()
+    success.append(-1)
 
     bae = soup.find('div', {'class': "box"}).find_all('ul')
 
     # Finding Prices
-    USD = bae[1].find('strong').text.strip()
+    USD = soup.find('div', {'class': "total-price"}).find('span').text.strip()
 
-    li = bae[2].find_all('li')
 
-    # Finding Escrow
+    # Finding Escrow NEED WORK
     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()
+    category = soup.find('div', {'class': "profile-info"}).find('p').find('a').text.strip()
 
     # Finding the Product Quantity Available
-    left = li[3].find('span', {'class': "tag is-dark"}).text.strip()
+    left.append(-1)
 
     # Finding Number Sold
-    sold = li[4].find('span', {'class': "tag is-dark"}).text.strip()
+    sold.append(-1)
 
     li = bae[3].find_all('li')
 
@@ -147,11 +138,11 @@ def darkfox_description_parser(soup):
 #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):
+def torbay_listing_parser(soup):
 
     # Fields to be parsed
     nm = 0                                    # Total_Products (Should be Integer)
-    mktName = "DarkFox"                       # 0 Marketplace_Name
+    mktName = "TorBay"                       # 0 Marketplace_Name
     name = []                                 # 1 Product_Name
     CVE = []                                  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
     MS = []                                   # 3 Product_MS_Classification (Microsoft Security)
@@ -174,7 +165,7 @@ def darkfox_listing_parser(soup):
     success = []                              # 20 Vendor_Successful_Transactions
     href = []                                 # 23 Product_Links (Urls)
 
-    listing = soup.findAll('div', {"class": "card"})
+    listing = soup.findAll('div', {"class": "product-card"})
 
     # Populating the Number of Products
     nm = len(listing)

setup.ini

@@ -1,12 +1,12 @@
 
 [TOR]
-firefox_binary_path = C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe
-firefox_profile_path = C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\TorBrowser\\Data\\Browser\\profile.default
-geckodriver_path = C:\\NSF-REU\\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:\\NSF-REU\\dw_pipeline_test
-shared_folder = \\VBoxSvr\\VM_Files_(shared)
+project_directory = C:\\Users\\Helium\\PycharmProjects\\dw_pipeline_test
+shared_folder = \\VBoxSvr\\Shared
 
 [PostgreSQL]
 ip = localhost