First Commit. Added categories and started testing for 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:\Users\Helium\anaconda3" jdkType="Python SDK" />
+    <orderEntry type="inheritedJdk" />
     <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:\Users\Helium\anaconda3" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\John Wick\anaconda3" project-jdk-type="Python SDK" />
 </project>

MarketPlaces/HiddenMarket/crawler_selenium.py

@@ -0,0 +1,318 @@
+__author__ = 'DarkWeb'
+
+'''
+HiddenMarket Market Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+from PIL import Image
+
+import urllib.parse as urlparse
+import os, re, time
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.HiddenMarket.parser import hiddenmarket_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/'
+
+
+# Opens Tor Browser, crawls the website
+def startCrawling():
+    opentor()
+    marketName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closetor(driver)
+
+    # new_parse(marketName, baseURL, False)
+
+
+# Opens Tor Browser
+def opentor():
+    from MarketPlaces.Initialization.markets_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):
+    # wait for login page
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div[3]/div[3]")))
+
+    # entering username and password into input boxes
+    # usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
+    # Username here
+    # usernameBox.send_keys('ct1234')
+    # passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
+    # Password here
+    # passwordBox.send_keys('DementedBed1230')
+
+    '''
+    # wait for captcha page show up
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img")))
+
+    # save captcha to local
+    driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img').screenshot(
+        r'..\captcha.png')
+
+    # This method will show image in any image viewer
+    im = Image.open(r'..\captcha.png')
+
+    im.show()
+
+    # wait until input space show up
+    inputBox = driver.find_element(by=By.XPATH, value='//*[@id="captcha"]')
+
+    # ask user input captcha solution in terminal
+    userIn = input("Enter solution: ")
+
+    # send user solution into the input space
+    inputBox.send_keys(userIn)
+
+    # click the verify(submit) button
+    driver.find_element(by=By.XPATH, value="/html/body/main/div/div/div/div/div/form/div[4]/button").click()
+    '''
+    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/main/div/div/div[1]/div/div[1]/div/h5')))
+
+
+# Returns the name of the website
+def getMKTName():
+    name = 'HiddenMarket'
+    return name
+
+
+# Return the link of the website
+def getFixedURL():
+    url = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/'
+
+    return url
+
+
+# Closes Tor Browser
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.quit()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    from MarketPlaces.Initialization.markets_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", 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
+
+
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        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 MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE
+
+    mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getMKTName() + "/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 = []
+
+    # # Civil Software
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/civil_softwares')
+    # # Tutorials - Carding
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/carding')
+    # # Digital - Hacks
+    links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/hacks')
+    # Digital - Exploit Kit
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/exploit_kit')
+    # # 0Day
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/0day')
+    # Digital Forensics
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/digital_forensics')
+    # Tutorials - Mining
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/mining')
+    # Tutorials - Worms
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/worms')
+    # Tutorials - Viruses
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/viruses')
+    # Tutorials - Trojans
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/trojans')
+    # Tutorials - Botnets
+    # links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/botnets')
+
+    return links
+
+
+def crawlForum(driver):
+    print("Crawling the HiddenMarket market")
+
+    linksToCrawl = getInterestedLinks()
+
+    i = 0
+    while i < len(linksToCrawl):
+        link = linksToCrawl[i]
+        print('Crawling :', link)
+        try:
+            has_next_page = True
+            count = 0
+
+            while has_next_page:
+                try:
+                    driver.get(link)
+                except:
+                    driver.refresh()
+                html = driver.page_source
+                savePage(html, link)
+
+                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:
+                #     break
+
+                try:
+                    nav = driver.find_element(by=By.XPATH, value=
+                    '/html/body/main/div/div/div[2]/div[11]/div/nav')
+                    a = nav.find_element(by=By.LINK_TEXT, value="›")
+                    link = a.get_attribute('href')
+                    if link == "":
+                        raise NoSuchElementException
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    input("Crawling HiddenMarket market done sucessfully. Press ENTER to continue\n")
+
+
+# Returns 'True' if the link is Topic link
+def isDescriptionLink(url):
+    if 'product' in url:
+        return True
+    return False
+
+
+# Returns True if the link is a listingPage link
+def isListingLink(url):
+    if 'category' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return hiddenmarket_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/HiddenMarket/parser.py

@@ -0,0 +1,232 @@
+__author__ = 'DarkWeb'
+
+# Here, we are importing the auxiliary functions to clean or convert data
+from MarketPlaces.Utilities.utilities import *
+
+# Here, we are importing BeautifulSoup to search through the HTML tree
+from bs4 import BeautifulSoup
+
+
+# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
+def hiddenmarket_description_parser(soup):
+    # Fields to be parsed
+
+    vendor = "-1"  # 0 *Vendor_Name
+    success = "-1"  # 1 Vendor_Successful_Transactions
+    rating_vendor = "-1"  # 2 Vendor_Rating
+    name = "-1"  # 3 *Product_Name
+    describe = "-1"  # 4 Product_Description
+    CVE = "-1"  # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"  # 6 Product_MS_Classification (Microsoft Security)
+    category = "-1"  # 7 Product_Category
+    views = "-1"  # 8 Product_Number_Of_Views
+    reviews = "-1"  # 9 Product_Number_Of_Reviews
+    rating_item = "-1"  # 10 Product_Rating
+    addDate = "-1"  # 11 Product_AddedDate
+    BTC = "-1"  # 12 Product_BTC_SellingPrice
+    USD = "-1"  # 13 Product_USD_SellingPrice
+    EURO = "-1"  # 14 Product_EURO_SellingPrice
+    sold = "-1"  # 15 Product_QuantitySold
+    left = "-1"  # 16 Product_QuantityLeft
+    shipFrom = "-1"  # 17 Product_ShippedFrom
+    shipTo = "-1"  # 18 Product_ShippedTo
+
+    bae = soup.find('div', {'class': "col-9"})
+
+    # Finding Product Name
+    name = bae.find('h2').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    mb = bae.findAll('div', {"class": "mb-1"})
+
+    # Finding Vendor
+    vendor = mb[0].text
+    vendor = vendor.replace(",", "")
+    vendor = vendor.replace("Sold by:", "")
+    vendor = vendor.strip()
+
+    # # Finding Vendor Rating
+    # full_stars = bae[2].find_all('i', {'class': "fas fa-star"})
+    # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"})
+    # rating = len(full_stars) + (0.5 if half_star is not None else 0)
+
+    # Finding Quantity Sold and Left
+    temp = mb[4].text.split(',')
+
+    sold = temp[0].replace("sold", "")
+    sold = sold.strip()
+
+    left = temp[1].replace("in stock", "")
+    left = left.strip()
+
+    # Finding USD
+    USD = bae.find('div', {"class": "h3 text-secondary"}).text
+    USD = USD.replace("$", "")
+    USD = USD.strip()
+
+    # Finding BTC
+    temp = bae.find('div', {"class": "small"}).text.split("BTC")
+
+    BTC = temp[0].strip()
+
+    # shipping_info = bae[4].text
+    # if "Digital" not in shipping_info:
+    #     shipping_info = shipping_info.split("  ")
+    #
+    #     # Finding Shipment Information (Origin)
+    #     shipFrom = shipping_info[0].strip()
+    #
+    #     # Finding Shipment Information (Destination)
+    #     shipTo = shipping_info[1].strip()
+
+    # Finding the Product description
+    describe = bae.find('div', {"class": "card border-top-0"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.replace("\r", " ")
+    describe = describe.strip()
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # Populating the final variable (this should be a list with all fields scraped)
+    row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate,
+           BTC, USD, EURO, sold, left, shipFrom, shipTo)
+
+    # Sending the results
+    return row
+
+
+# This is the method to parse the Listing Pages
+def hiddenmarket_listing_parser(soup):
+    # Fields to be parsed
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "HiddenMarket"  # 0 *Marketplace_Name
+    vendor = []  # 1 *Vendor y
+    rating_vendor = []  # 2 Vendor_Rating
+    success = []  # 3 Vendor_Successful_Transactions
+    name = []  # 4 *Product_Name y
+    CVE = []  # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = []  # 6 Product_MS_Classification (Microsoft Security)
+    category = []  # 7 Product_Category y
+    describe = []  # 8 Product_Description
+    views = []  # 9 Product_Number_Of_Views
+    reviews = []  # 10 Product_Number_Of_Reviews
+    rating_item = []  # 11 Product_Rating
+    addDate = []  # 12 Product_AddDate
+    BTC = []  # 13 Product_BTC_SellingPrice
+    USD = []  # 14 Product_USD_SellingPrice y
+    EURO = []  # 15 Product_EURO_SellingPrice
+    sold = []  # 16 Product_QuantitySold
+    qLeft = []  # 17 Product_QuantityLeft
+    shipFrom = []  # 18 Product_ShippedFrom
+    shipTo = []  # 19 Product_ShippedTo
+    href = []  # 20 Product_Links
+
+    listing = soup.findAll('div', {"class": "card product-card mb-3"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    # Finding Category
+    cat = soup.find("div", {"class": "col-9"})
+    cat = cat.find("h2").text
+    cat = cat.replace("Category: ", "")
+    cat = cat.replace(",", "")
+    cat = cat.strip()
+
+    for card in listing:
+        category.append(cat)
+
+        bae = card.findAll('a')
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        href.append(link)
+
+        # Finding Product Name
+        product = bae[1].text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.strip()
+        name.append(product)
+
+        # Finding Vendor
+        vendor_name = bae[2].text
+        vendor_name = vendor_name.replace(",", "")
+        vendor_name = vendor_name.strip()
+        vendor.append(vendor_name)
+
+        # Finding USD
+        usd = card.find('div', {"class": "mb-1"}).text
+        usd = usd.replace("$", "")
+        usd = usd.strip()
+        USD.append(usd)
+
+        # Finding Reviews
+        num = card.find("span", {"class": "rate-count"}).text
+        num = num.replace("(", "")
+        num = num.replace("review)", "")
+        num = num.replace("reviews)", "")
+        num = num.strip()
+        reviews.append(num)
+
+        # Searching for CVE and MS categories
+        cve = card.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue = "-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue = cee
+        CVE.append(cveValue)
+
+        ms = card.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue = "-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue = me
+        MS.append(MSValue)
+
+    # Populate the final variable (this should be a list with all fields scraped)
+    return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views,
+                            reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href)
+
+
+def hiddenmarket_links_parser(soup):
+    # Returning all links that should be visited by the Crawler
+    href = []
+
+    listing = soup.findAll('div', {"class": "item"})
+
+    for div in listing:
+        link = div.find('a')['href']
+        href.append(link)
+
+    return href

MarketPlaces/Initialization/markets_mining.py

@@ -20,6 +20,7 @@ from MarketPlaces.Apocalypse.crawler_selenium import crawler as crawlerApocalyps
 from MarketPlaces.CityMarket.crawler_selenium import crawler as crawlerCityMarket
 from MarketPlaces.DarkMatter.crawler_selenium import crawler as crawlerDarkMatter
 from MarketPlaces.M00nkeyMarket.crawler_selenium import crawler as crawlerM00nkeyMarket
+from MarketPlaces.HiddenMarket.crawler_selenium import crawler as crawlerHiddenMarket
 
 import configparser
 import time
@@ -106,6 +107,8 @@ if __name__ == '__main__':
             crawlerDarkMatter()
         elif mkt == "M00nkeyMarket":
             crawlerM00nkeyMarket()
+        elif mkt == "HiddenMarket":
+            crawlerHiddenMarket()
 
 
 

MarketPlaces/Initialization/prepare_parser.py

@@ -12,6 +12,7 @@ from MarketPlaces.ThiefWorld.parser import *
 from MarketPlaces.AnonymousMarketplace.parser import *
 from MarketPlaces.TorBay.parser import *
 from MarketPlaces.M00nkeyMarket.parser import *
+from MarketPlaces.HiddenMarket.parser import *
 
 from MarketPlaces.Classifier.classify_product import predict
 
@@ -154,6 +155,8 @@ def new_parse(marketPlace, url, createLog):
                 rmm = torbay_description_parser(soup)
             elif marketPlace == "M00nkeyMarket":
                 rmm = m00nkey_description_parser(soup)
+            elif marketPlace == "HiddenMarket":
+                rmm = hiddenmarket_description_parser(soup)
 
             # key = u"Pr:" + rmm[0].upper()[:desc_lim1] + u" Vendor:" + rmm[13].upper()[:desc_lim2]
             key = u"Url:" + os.path.basename(line2).replace(".html", "")
@@ -211,6 +214,8 @@ def new_parse(marketPlace, url, createLog):
                     rw = torbay_listing_parser(soup)
                 elif marketPlace == "M00nkeyMarket":
                     rw = m00nkey_listing_parser(soup)
+                elif marketPlace == "HiddenMarket":
+                    rw =hiddenmarket_listing_parser(soup)
                 else:
                     parseError = True