Merge branch 'josh-development' into 'main'

Finished Crawler and Parser for ViceCIty

See merge request dw9372422/dw_pipeline_test!3

.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>

Forums/Utilities/utilities.py

@@ -292,7 +292,7 @@ def cleanHTML(html):
     clean_html = re.sub(r"<embed.*scriptable?>", "", clean_html)
 
     # image and JavaScript
-    clean_html = re.sub(r"<div.*background-image.*?>", "", clean_html)
+    clean_html = re.sub(r"<div[^>]*style=\"[^\"]*background-image.*?>", "", clean_html)
 
     return clean_html
 

MarketPlaces/Initialization/marketsList.txt

@@ -1 +1 @@
-M00nkeyMarket
+ViceCity

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.ViceCity.crawler_selenium import crawler as crawlerViceCity
 
 import configparser
 import time
@@ -106,6 +107,8 @@ if __name__ == '__main__':
             crawlerDarkMatter()
         elif mkt == "M00nkeyMarket":
             crawlerM00nkeyMarket()
+        elif mkt == "ViceCity":
+            crawlerViceCity()
 
 
 

MarketPlaces/Initialization/prepare_parser.py

@@ -10,6 +10,7 @@ from MarketPlaces.Tor2door.parser import *
 from MarketPlaces.Apocalypse.parser import *
 from MarketPlaces.ThiefWorld.parser import *
 from MarketPlaces.AnonymousMarketplace.parser import *
+from MarketPlaces.ViceCity.parser import *
 from MarketPlaces.TorBay.parser import *
 from MarketPlaces.M00nkeyMarket.parser import *
 
@@ -150,6 +151,8 @@ def new_parse(marketPlace, url, createLog):
                 rmm = thiefWorld_description_parser(soup)
             elif marketPlace =="AnonymousMarketplace":
                 rmm = anonymousMarketplace_description_parser(soup)
+            elif marketPlace == "ViceCity":
+                rmm = vicecity_description_parser(soup)
             elif marketPlace == "TorBay":
                 rmm = torbay_description_parser(soup)
             elif marketPlace == "M00nkeyMarket":
@@ -161,7 +164,7 @@ def new_parse(marketPlace, url, createLog):
             # save file address with description record in memory
             detPage[key] = {'rmm': rmm, 'filename': os.path.basename(line2)}
 
-        except:  
+        except :  
 
             nError += 1
             print("There was a problem to parse the file " + line2 + " in the Description section!")
@@ -207,6 +210,8 @@ def new_parse(marketPlace, url, createLog):
                     rw = thiefWorld_listing_parser(soup)
                 elif marketPlace == "AnonymousMarketplace":
                     rw = anonymousMarketplace_listing_parser(soup)
+                elif marketPlace == "ViceCity":
+                    rw = vicecity_listing_parser(soup)
                 elif marketPlace == "TorBay":
                     rw = torbay_listing_parser(soup)
                 elif marketPlace == "M00nkeyMarket":

MarketPlaces/Utilities/utilities.py

@@ -315,7 +315,7 @@ def cleanHTML(html):
     clean_html = re.sub(r"<embed.*scriptable?>", "", clean_html)
 
     # image and JavaScript
-    clean_html = re.sub(r"<div.*background-image.*?>", "", clean_html)
+    clean_html = re.sub(r"<div[^>]*style=\"[^\"]*background-image.*?>", "", clean_html)
 
     return clean_html
 

MarketPlaces/ViceCity/crawler_selenium.py

@@ -0,0 +1,333 @@
+__author__ = 'DarkWeb'
+
+'''
+ViceCity Market Forum Crawler (Selenium)
+'''
+
+from selenium import webdriver
+from selenium.common.exceptions import NoSuchElementException
+from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
+from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.by import By
+
+from PIL import Image
+import urllib.parse as urlparse
+import os, time
+from datetime import date
+import subprocess
+import configparser
+import subprocess
+from bs4 import BeautifulSoup
+from MarketPlaces.Initialization.prepare_parser import new_parse
+from MarketPlaces.ViceCity.parser import vicecity_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+config = configparser.ConfigParser()
+config.read('../../setup.ini')
+counter = 1
+baseURL = 'http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.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, baseURL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'ViceCity'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/'
+    return url
+
+
+# Closes Tor Browser
+#@param: current selenium driver
+def closetor(driver):
+    # global pid
+    # os.system("taskkill /pid " + str(pro.pid))
+    # os.system("taskkill /t /f /im tor.exe")
+    print('Closing Tor...')
+    driver.close()
+    time.sleep(3)
+    return
+
+
+# Creates FireFox 'driver' and configure its 'Profile'
+# to use Tor proxy and socket
+def createFFDriver():
+    ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path'))
+
+    ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path'))
+    # ff_prof.set_preference("places.history.enabled", False)
+    # ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True)
+    # ff_prof.set_preference("privacy.clearOnShutdown.passwords", True)
+    # ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True)
+    # ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
+    # ff_prof.set_preference("signon.rememberSignons", False)
+    # ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
+    # ff_prof.set_preference("network.dns.disablePrefetch", True)
+    # ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    # ff_prof.set_preference("permissions.default.image", 3)
+    # ff_prof.set_preference("browser.download.folderList", 2)
+    # ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
+    # ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
+    ff_prof.set_preference('network.proxy.type', 1)
+    ff_prof.set_preference("network.proxy.socks_version", 5)
+    ff_prof.set_preference('network.proxy.socks', '127.0.0.1')
+    ff_prof.set_preference('network.proxy.socks_port', 9150)
+    ff_prof.set_preference('network.proxy.socks_remote_dns', True)
+    ff_prof.set_preference("javascript.enabled", False)
+    ff_prof.update_preferences()
+
+    service = Service(config.get('TOR', 'geckodriver_path'))
+
+    driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
+
+    return driver
+
+#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
+#return: return the selenium driver or string 'down'
+def getAccess():
+    url = getFixedURL()
+    driver = createFFDriver()
+    try:
+        driver.get(url)
+        return driver
+    except:
+        driver.close()
+        return 'down'
+
+
+# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
+# then allows for manual solving of captcha in the terminal
+#@param: current selenium web driver
+def login(driver):
+    # wait for first captcha 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/form/div/div[1]")))
+    input("Press Enter once captcha done (dont press done)")
+    #clicks button after captcha is inputted
+    driver.find_element(by=By.XPATH, value='/html/body/div/div/form/button').click()
+
+    #wait for login page to show up
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '/html/body/div/div/div/form')))
+    #puts username into box
+    userBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
+    userBox.send_keys('ct1234')
+
+    #waits for second catpcha to be inputted by user
+    input("Press Enter once captcha done (dont press continue)")
+    #clicks on continue
+    driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/input[2]').click()
+
+    #waits for password to show
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '/html/body/div/div/div/form/div[3]/input')))
+    time.sleep(10) # give time for site to catch up
+    # puts password into box
+    passBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/div[2]/input')
+    passBox.send_keys('DementedBed123-')
+    driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/div[3]/input').click()
+
+    # wait for pin input to show
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '/html/body/div[1]/div/form/span')))
+    pinBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div/form/input[1]')
+    pinBox.send_keys('12345')
+    driver.find_element(by=By.XPATH, value='/html/body/div[1]/div/form/input[2]').click()
+
+    # waits for main listing page before crawling to ensure everything goes well
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '/html/body/div[1]/div/div[2]')))
+
+
+# Saves the crawled html page, makes the directory path for html pages if not made
+def savePage(page, url):
+    cleanPage = cleanHTML(page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+# Gets the full path of the page to be saved along with its appropriate file name
+#@param: raw url as crawler crawls through every site
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import 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 = []
+
+    # Digital - Fraud Software, Has Hacking and Guides
+    links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=150')
+    # Digital - Guides and Tutorials
+    links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=94')
+    # Carding Services
+    links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=155')
+    # Digital - Other (half junk half random stuff like: bots, rats, viruses, and guides)
+    links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=153')
+
+    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 ViceCity 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)
+                j = 0
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    time.sleep(2.5) # to let page catchup
+                    savePage(driver.page_source, item)
+                    time.sleep(2.5) # so site doesnt crash
+                    driver.back()
+
+                    #comment out
+                    # break
+
+                # # comment out
+                # if count == 1:
+                #    count = 0
+                #    break
+
+                try:
+                    temp = driver.find_element(by=By.CLASS_NAME, value='pagination')
+                    link = temp.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 ViceCity  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 '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 'category' in url:
+        return True
+    return False
+
+
+# calling the parser to define the links, the html is the url of a link from the list of interested link list
+#@param: link from interested link list ie. getInterestingLinks()
+#return: list of description links that should be crawled through
+def productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return vicecity_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/ViceCity/parser.py

@@ -0,0 +1,282 @@
+__author__ = 'DarkWeb'
+
+import re
+
+# 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 vicecity_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
+
+    # Finding Product Name
+    name = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"})
+    name = name.find('span', {'style': "font-size:18px;font-weight: bold;color: #fff"}).text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    # Finding Vendor
+    vendor = soup.find('div', {'class': "listing_info"})
+    vendor = vendor.find('div', {'class': "listing_right"})
+    numbers = vendor.find('a').find('span').text
+    vendor = vendor.find('a').text
+    vendor = vendor.replace(numbers, "").strip() # removes numbers at the end of vendor name
+
+    # Finding Vendor Rating
+    rating = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title')
+    rating = re.search(r"\d+%", rating)
+    rating_vendor = rating.group(0).strip()
+
+    # 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 Successful Transactions
+    success = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title')
+    success = re.search(r"\d+(?= sales)", success)
+    success = success.group(0).strip()
+
+
+    bae = soup.find('pre')
+
+    # Finding USD
+    USD = bae.find('span').text
+    USD = re.search(r"\$\d+(?:\.\d+)?", USD).group(0)
+    USD = USD.replace("$", "").strip()
+
+    # Finding BTC
+    BTC = bae.find_all('span')
+    BTC = re.search(r"\d+(?:\.\d+)?", BTC[1].text).group(0)
+    BTC = BTC.strip()
+
+    # Finding the Product Category
+    category = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"})
+    category = category.find('span', {'style': "font-size:15px;color: #a1a1a1"}).text
+    category = category.replace("Category:", "").strip()
+
+    li = bae.find_all('span')
+
+    # Finding Shipment Information (Origin)
+    shipFrom = li[-4].text.strip()
+
+    # Finding Shipment Information (Destination)
+    shipTo = li[-2].text.strip()
+
+    # Finding the Product description
+    describe = soup.find('p', {
+        'style': "width:705px;margin-left:-305px;background-color: #242424;border-radius: 3px;border: 1px solid #373737;padding: 5px;"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.strip()
+
+    # Finding the Number of Product Reviews
+    li = soup.find_all('label', {'class': "tc_label threetabs"})
+    review = li[1].text
+    review = re.search(r"\d+", review)
+    if review:
+        reviews = review.group(0).strip()
+    else:
+        reviews = '0'
+
+    # 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 vicecity_listing_parser(soup):
+    # Fields to be parsed
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "ViceCity"  # 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": "wLf"}) # should be 30
+
+    # 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 a in listing:
+        # category.append(cat)
+
+        # bae = card.findAll('a')
+
+        # Adding the url to the list of urls
+        link = a.find('div', {"class": "wLfLeft"}).find('a', href=True).get('href')
+        link = cleanLink(link)
+        href.append(link)
+
+        # Finding the Product Name
+        product = a.find('div', {"class": "wLfName"}).find('a').text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.replace("...", "")
+        product = product.strip()
+        name.append(product)
+
+        # Finding the Vendor
+        vendor_name = a.find('div', {"class": "wLfVendor"}).find('a').text
+        addedNums = a.find('div', {"class": "wLfVendor"}).find('a').find('span').text # finds numbers added at end
+        vendor_name = vendor_name.replace(",", "")
+        vendor_name = vendor_name.replace(addedNums, "") # removes numbers added at end
+        vendor_name = vendor_name.strip()
+        vendor.append(vendor_name)
+
+        # Finding Prices
+        price = a.find('div', {"class": "wLfPrice"}).find_all('span')
+        ud = price[0].text.replace(" USD", " ")
+        # u = ud.replace("$","")
+        ud = ud.replace(",", "")
+        u = ud.replace(price[1].text, "")
+        u = u.strip()
+        USD.append(u)
+        bc = price[1].text
+        bc = re.search(r"\d+(?:\.\d+)?", bc).group(0).strip()
+        BTC.append(bc)
+
+        # # 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)
+
+        # Finding Successful Transactions
+        freq = a.find('div', {"class": "wLfVendor"}).find('a').get('title')
+        freq = re.search(r'\d+(?= sales)', freq).group(0)
+        freq = freq.strip()
+        success.append(freq)
+
+        # Finding Ship from and ship to
+        place = a.find('div', {"class": "wLfPrice"})
+        place = place.find('span', {'style': "font-size: 12px;"}).text
+        place = place.split('⟶')
+        varFrom = place[0].strip()
+        varTo = place[1].strip()
+        if varFrom == "WW":
+            varFrom = "Worldwide"
+        if varTo == "WW":
+            varTo = "Worldwide"
+        shipFrom.append(varFrom)
+        shipTo.append(varTo)
+
+        # 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)
+
+
+def vicecity_links_parser(soup):
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "wLf"})
+
+    for a in listing:
+        bae = a.find('div', {"class": "wLfLeft"}).find('a', href=True)
+        link = bae['href']
+        href.append(link)
+
+    return href