Dark Market Crawler and Parser

MarketPlaces/SilkRoad4/crawler_selenium.py

@@ -0,0 +1,383 @@
+__author__ = 'Helium'
+
+'''
+Silk Road 4 Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, re, time
+from datetime import date
+import subprocess
+import configparser
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.SilkRoad4.parser import silkroad4_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.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():
+    mktName = getMKTName()
+    driver = getAccess()
+
+    if driver != 'down':
+        try:
+            login(driver)
+            crawlForum(driver)
+        except Exception as e:
+            print(driver.current_url, e)
+        closeDriver(driver)
+
+    new_parse(mktName, baseURL, True)
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'SilkRoad4'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closeDriver(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():
+    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)
+
+    driver.maximize_window()
+
+    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
+#If CAPTCHA is incorrect the first time, will automatically re-enter password and username after pressing 'Enter'
+#@param: current selenium web driver
+def login(driver):
+    
+    #login urls
+    login_page1 = driver.current_url
+    login_page2 = 'http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?login'
+
+    # Will automatically re-enter the user/pw if first time CAPTCHA is entered incorrectly.
+    while(driver.current_url == login_page1 or driver.current_url == login_page2):
+        # entering username and password into input boxes
+        usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/form/div/input[1]')
+        # Username here
+        usernameBox.send_keys('SamarIsland')
+
+        passwordBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/form/div/input[2]')
+        # Password here
+        passwordBox.send_keys('Underthe5e@')
+
+        input("Press ENTER if: \n- username and password needs to be re-entered again\n- when CAPTCHA is completed and home page is visible \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')))
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(driver, page, url):
+    cleanPage = cleanHTML(driver, page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import 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, 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 Spam Category
+    #Databases, Access, & Data
+    links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=12')
+    #Exploit Kits
+    links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=13')
+    #Exploits, Kits, & Vulnerabilities
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=11')
+    #Hacking Tools & Scripts
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=14')
+    #Other Hacking & Spam
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=21')
+    #Phishing Tools & Utilities
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=19')
+    #RDPs/VNCs
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=18')
+    #Social Media Boosting
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=20')
+    #Spam Tools & Scripts
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=15')
+    #Traffic
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=16')
+
+    #Fraud
+    #Accounts & Bank Drops
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=2')
+    #CVV & Cards
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=3')
+    #Carding/Fraud Software
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=8')
+    #Other Fraud
+    links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=9')
+    #Personal Info(SSN/DOB/Fullz?Scans)
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=5')
+    #Physical Fake IDs
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=7')
+    #Dumps
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=4')
+    #Skimmers
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=6')
+
+    #Guides & Tutorials
+    #Fraud Guides
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=137')
+    #Hacking Guides
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=136')
+    #Other Guides and tutorial
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=143')
+    #Security and Anonymity Guides
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=140')
+    #Social Engineering Guides
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=141')
+
+    #Malware
+    #Keyloggers
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=30')
+    #Botnets
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=23')
+    #RATs
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=24')
+
+    #Software
+    #Other Software
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=150')
+    #Security Software
+    #Security Software
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=145')
+    #Cracked Products
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=149')
+
+    #Services
+    #Hacking
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=112')
+    #Social Engineering
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=116')
+    #Security
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=113')
+    #Programming
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=115')
+    #Carding
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=114')
+
+    #Security and Hosting
+    #VPN
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=129')
+    #VPN Accounts
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=130')
+    #Proxies
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=132')
+    #Bulletproof Hosting
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=126')
+    #Hosting
+    #links.append('http://silkroadm5oqzuz3yq7pvwvinvyzeg2wnpnw3t4cyrsggrcgqfy2ptid.onion/?cat=125')
+
+    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 SilkRoad4 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(driver, html, linksToCrawl[i] + f"page{count+1}")
+
+                list = productPages(html)
+                countItem = 0
+                for item in list:
+                    countItem+=1
+
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver, driver.page_source, item)
+                    driver.back()
+
+                    if (countItem == 10):
+                        break
+                    #break
+
+
+
+                #     # comment out
+                #     break
+                #
+                #comment out
+                if count == 2:
+                   break
+
+                try:
+                    link = driver.find_element(by=By.XPATH, value='/html/body/div/div/table/tbody/tr/td[1]/center/form/input[3]').get_attribute('href')
+                    if link == "":
+                        raise NoSuchElementException
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    print("Crawling the SilkRoad4 market done.")
+
+
+# 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 '?listing=' 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 '?cat=' 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 silkroad4_links_parser(soup)
+
+
+def crawler():
+    startCrawling()

MarketPlaces/SilkRoad4/parser.py

@@ -0,0 +1,276 @@
+__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 silkroad4_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
+    LTC = "-1"                          # 19 Product_LTC_SellingPrice
+    XMR = "-1"                          # 20 Product_XMR_SellingPrice
+    image = "-1"                        # 19 Product_Image
+    vendor_image = "-1"                 # 20 Vendor_Image
+
+    bae = soup.find('div', {'id': 'cats'})
+
+    # Finding Vendor
+    vendor = bae.find('font', {'color':'blue'}).text
+    vendor = vendor.strip()
+
+    #Finding Product Name
+    name = bae.find('b', {'style': 'color:#333;'}).text
+    name = name.strip()
+
+    #Finding image
+    image = bae.find('img')
+    image = image.get('src')
+    image = image.split('base64,')[-1]
+
+    #Finding Price
+    temp = bae.find('span').next_sibling
+    price_list = temp.split("/")
+
+    USD = price_list[0].replace("$", "").strip()
+    BTC = price_list[1].replace("BTC","").strip()
+
+    #Not extracted into databse/PGAdmin yet!
+    LTC = price_list[2].replace("LTC", "").strip()
+    XMR = price_list[3].replace("XMR", "").strip()
+    #print(USD, "", BTC,"", LTC,"", XMR)
+
+    # Finding Ships From
+    a = bae.find_all('a',href=True, limit = 2)
+    shipFrom = a[0].text.strip()
+
+    #Finding Category
+    category = a[1].text.strip()
+
+    # Finding the Product description
+    describe = soup.find('div', {'style': 'color:#555;font-weight:normal;font-size:12px'}).text
+    describe = cleanString(describe.strip())
+
+    #Finding Rating
+    rate = soup.find('div', {'style': 'padding:0px; margin-bottom:10px; font-size:12px;'})
+    rate = rate.find('p')
+    if rate is not None:
+        rate = rate.text.strip()
+
+        #Some descriptions has 0 rating as 'No Rating yet', can convert to -1 for consistency in database
+        #if(rate is 'No rating yet'):
+           # rating_item = -1
+
+        #Only extract rating part
+        rating_item = rate[:rate.index('Note')]
+
+
+
+    #Finding Number of Reviews
+    table = soup.find('div', {'class': 'table-responsive'})
+    if table is not None:
+        num_rev = table.findAll('tr')
+        reviews = len(num_rev) - 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 = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate,
+           BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image)
+
+
+    # Sending the results
+    return row
+
+
+# This is the method to parse the Listing Pages
+def silkroad4_listing_parser(soup):
+
+    # Fields to be parsed
+    nm = 0                                    # *Total_Products (Should be Integer)
+    mktName = "SilkRoad4"                     # 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
+    LTC = []                                  # 21 Product_LTC_SellingPrice
+    XMR = []                                  # 22 Product_XMR_SellingPrice
+    image = []                                # 19 Product_Image
+    image_vendor = []                         # 20 Vendor_Image
+
+
+    listing = soup.findAll('div', {'style': "padding:10px; width:100%; margin-bottom:5px; margin-top:0px"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    # Finding category of listing page
+    cat = listing[0].find_all('a', href=True)
+    cat = cat[len(cat)-2].text
+    cat = cat.replace(",", "")
+    cat = cat.strip()
+
+    for a in listing:
+        bae = a.findAll('a', href=True)
+
+        # Adding the category
+        category.append(cat)
+
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        #Finding Price
+        temp = a.find('b', {'style': 'color:#333'})
+        temp = temp.text
+        price = temp.split("/")
+        USD.append(price[0].replace('$', '').strip())
+        BTC.append(price[1].replace('BTC', '').strip())
+
+        #LTC and XMR will not be stored in Pgadmin as of now
+        LTC.append(price[2].replace('LTC', '').strip())
+        XMR.append(price[3].replace('XMR', '').strip())
+        #print(USD, " ", BTC, ' ', LTC, '', XMR)
+
+        # Finding the Vendor
+        ven = a.findAll('b')
+        v = ven[2].find('font').text
+        v = v.strip()
+        vendor.append(v)
+
+        # Finding the Product
+        product = bae[0].text
+        product = product.replace(",", "")
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+
+        #Finding ShipFrom
+        shipf = bae[len(bae)-1].text.strip()
+        shipFrom.append(shipf)
+
+        #Finding image
+        product_image = a.find('img')
+        product_image = product_image.get('src')
+        product_image = product_image.split('base64,')[-1]
+        image.append(product_image)
+
+        # 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, vendor, rating_vendor, success, name, CVE, MS, category, describe, views,
+                            reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image,
+                            image_vendor)
+
+
+def silkroad4_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+    href = []
+
+    #finds all div with id, vp
+    divs = soup.findAll('div', {"id": "vp"})
+
+    listing = []
+
+    #for all div with id:vp, find first a with href
+    for div in divs:
+        a_s = div.find('a', href=True)
+
+        #if div has no href True, then move on. otherwise, store the a with href into listing
+        if a_s is not None:
+            listing.append(a_s)
+
+    #loop through listing with a with href and extract/return the href
+    for a in listing:
+        link = a['href']
+
+        #if '?listing' is in link, then it is a product, so append to the href list
+        if "?listing" in link:
+            href.append(link)
+
+    return href