debugged marketplaces

.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="inheritedJdk" />
+    <orderEntry type="jdk" jdkName="C:\Users\calsyslab\anaconda3" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyNamespacePackagesService">
@@ -10,10 +10,24 @@
       <list>
         <option value="$MODULE_DIR$/Forums/BestCardingWorld" />
         <option value="$MODULE_DIR$/Forums/CryptBB" />
-        <option value="$MODULE_DIR$/MarketPlaces/DarkFox" />
-        <option value="$MODULE_DIR$/MarketPlaces/Tor2door" />
         <option value="$MODULE_DIR$/Forums/OnniForums" />
         <option value="$MODULE_DIR$/MarketPlaces/ThiefWorld" />
+        <option value="$MODULE_DIR$/MarketPlaces/Apocalypse" />
+        <option value="$MODULE_DIR$/MarketPlaces/DarkMatter" />
+        <option value="$MODULE_DIR$/MarketPlaces/DigitalThriftShop" />
+        <option value="$MODULE_DIR$/MarketPlaces/HiddenMarket" />
+        <option value="$MODULE_DIR$/MarketPlaces/LionMarketplace" />
+        <option value="$MODULE_DIR$/MarketPlaces/Nexus" />
+        <option value="$MODULE_DIR$/MarketPlaces/RobinhoodMarket" />
+        <option value="$MODULE_DIR$/MarketPlaces/TorBay" />
+        <option value="$MODULE_DIR$/MarketPlaces/TorMarket" />
+        <option value="$MODULE_DIR$/MarketPlaces/ViceCity" />
+        <option value="$MODULE_DIR$/Forums/AbyssForum" />
+        <option value="$MODULE_DIR$/Forums/Altenens" />
+        <option value="$MODULE_DIR$/Forums/Cardingleaks" />
+        <option value="$MODULE_DIR$/Forums/HiddenAnswers" />
+        <option value="$MODULE_DIR$/Forums/Libre" />
+        <option value="$MODULE_DIR$/Forums/Procrax" />
       </list>
     </option>
   </component>

.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\John Wick\anaconda3" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\calsyslab\anaconda3" project-jdk-type="Python SDK" />
 </project>

Forums/DB_Connection/db_connection.py

@@ -2,7 +2,6 @@ __author__ = 'DarkWeb'
 
 import psycopg2
 import traceback
-import configparser
 
 
 def connectDataBase():

MarketPlaces/AnonymousMarketplace/crawler_selenium.py

@@ -187,12 +187,8 @@ def getNameFromURL(url):
 def getInterestedLinks():
     links = []
 
-    # # carding
-    # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/carding/')
-    # # hacked paypal
-    # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacked-paypal-accounts/')
-    # hacking services
-    links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacking-services/')
+    # home
+    links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/')
 
     return links
 
@@ -232,7 +228,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:
@@ -240,7 +236,7 @@ def crawlForum(driver):
 
                 #left in in case site changes
                 try:
-                    link = ""
+                    link = driver.find_element(by=By.LINK_TEXT, value="→").get_attribute('href')
                     if link == "":
                         raise NoSuchElementException
                     count += 1

MarketPlaces/AnonymousMarketplace/parser.py

@@ -41,12 +41,12 @@ def anonymousMarketplace_description_parser(soup: Tag):
         describe_output += div.text
     describe = cleanString(describe_output.strip())
     
-    product_ratings: Tag = soup.find("div", {"class": "star-rating"})
+    product_ratings: Tag = soup.find("div", {"class": "woocommerce-product-rating"})
     
-    product_reviews = product_ratings.find("div", {"class": "woocommerce-product-rating"}).find("strong", {"class": "rating"}).text
+    product_reviews = product_ratings.find("span", {"class": "rating"}).text
     reviews = cleanString(product_reviews.strip())
     
-    product_star_rating = product_ratings.find("span", {"class": "rating"}).text
+    product_star_rating = product_ratings.find("strong", {"class": "rating"}).text
     rating_item = cleanString(product_star_rating.strip())
     
     product_price = soup.find("span", {"class": "woocommerce-Price-amount amount"}).text
@@ -86,15 +86,16 @@ def anonymousMarketplace_listing_parser(soup: Tag):
     shipFrom = []                             # 18 Product_ShippedFrom
     shipTo = []                               # 19 Product_ShippedTo
     href = []                                 # 20 Product_Links
-    
-    
-    product_list: ResultSet[Tag] = soup.find("ul", {"class": "product_list_widget"}).find_all("li")
+
+    woo = soup.find('div', {"class": "woocommerce"})
+
+    product_list = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li')
     
     for item in product_list:
-        item_href = item.find("a").get("href")
+        item_href = item.find("a", recursive=False).get("href")
         href.append(item_href)
         
-        item_name = item.find("span", {"class": "product-title"}).text
+        item_name = item.find("h2").text
         name.append(cleanString(item_name.strip()))
         
         item_rating = item.find("div", {"class": "star-rating"}).find("strong", {"class": "rating"}).text
@@ -103,14 +104,11 @@ def anonymousMarketplace_listing_parser(soup: Tag):
         try:
             item_price = item.find("span", {"class": "woocommerce-Price-amount amount"}).text
             item_price = item_price.replace("$", "").strip()
-            USD.append(item_price)
+            USD.append(cleanNumbers(item_price))
         except AttributeError:
             USD.append("-1")
-        
-        
-            
-        
-        vendor.append("Anonymous")
+
+        vendor.append("AnonymousMarketplace")
         rating_vendor.append("-1")
         success.append("-1")
         CVE.append("-1")
@@ -153,10 +151,6 @@ def anonymousMarketplace_listing_parser(soup: Tag):
         shipTo=shipTo,
         href=href
     )
-    
-        
-        
-        
 
 
 #called by the crawler to get description links on a listing page
@@ -167,10 +161,13 @@ def anonymous_links_parser(soup):
     # Returning all links that should be visited by the Crawler
 
     href = []
-    listing = soup.find('ul', {"class": "product_list_widget"}).findAll('li')
+
+    woo = soup.find('div', {"class": "woocommerce"})
+
+    listing = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li')
 
     for a in listing:
-        bae = a.find('a', href=True)
+        bae = a.find('a', href=True, recursive=False)
 
         link = bae['href']
         href.append(link)

MarketPlaces/Apocalypse/crawler_selenium.py

@@ -203,8 +203,12 @@ def getNameFromURL(url):
 def getInterestedLinks():
     links = []
 
-    # # Hacking Services
-    # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/subcategory/19')
+    # # Digital Goods
+    # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/74')
+    # # Fraud
+    # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/75')
+    # # Services
+    # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/76')
     # software and malware
     links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/subcategory/30')
 
@@ -243,7 +247,11 @@ def crawlForum(driver):
                     except:
                         driver.refresh()
                     savePage(driver, driver.page_source, item)
-                    driver.back()
+                    # driver.back()
+                    try:
+                        driver.get(link)
+                    except:
+                        driver.refresh()
 
                     # comment out
                     # break
@@ -282,7 +290,7 @@ def isDescriptionLink(url):
 #@param: url of any url crawled
 #return: true if is a Listing page, false if not
 def isListingLink(url):
-    if 'subcategory' in url:
+    if 'category' in url:
         return True
     return False
 

MarketPlaces/DB_Connection/db_connection.py

@@ -2,7 +2,6 @@ __author__ = 'DarkWeb'
 
 import psycopg2
 import traceback
-import configparser
 
 
 def connectDataBase():

MarketPlaces/DarkBazar/crawler_selenium.py

@@ -1,4 +1,4 @@
-__author__ = 'Helium'
+__author__ = 'DarkWeb'
 
 '''
 DarkBazar Marketplace Crawler (Selenium)
@@ -10,6 +10,7 @@ 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.ui import Select
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.common.by import By
 
@@ -25,99 +26,11 @@ from MarketPlaces.DarkBazar.parser import darkbazar_links_parser
 from MarketPlaces.Utilities.utilities import cleanHTML
 
 counter = 1
-baseURL = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/log.php'
+baseURL = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/'
 
-def login(driver):
-    input("Press ENTER when CAPTCHA is complete and login page has loaded\n")
-
-    # entering username and password into input boxes
-    usernameBox = driver.find_element(by=By.XPATH, value='//input[@name="username"]')
-    # Username here
-    usernameBox.send_keys('aliciamykeys')
-    passwordBox = driver.find_element(by=By.XPATH, value='//input[@name="password"]')
-    # Password here
-    passwordBox.send_keys('aliciawherearemykey$')
-
-    input("Press ENTER when CAPTCHA is completed and you exit the newsletter\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, '//*[@id="submit"]')))
-
-def crawlForum(driver):
-
-    print("Crawling the DarkBazar 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:
-                    link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "Next")]').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 DarkBazar forum done sucessfully. Press ENTER to continue\n")
-
-
-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
-
-def getInterestedLinks():
-    links = []
-
-    links.append('http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/cat.php?category=5')
-
-    return links
 
-def crawler():
-    startCrawling()
 def startCrawling():
-    opentor()
+    # opentor()
     mktName = getMKTName()
     driver = getAccess()
 
@@ -129,7 +42,8 @@ def startCrawling():
             print(driver.current_url, e)
         closetor(driver)
 
-    # new_parse(mktName, baseURL, False)
+    new_parse(mktName, baseURL, True)
+
 
 # Opens Tor Browser
 def opentor():
@@ -143,14 +57,16 @@ def opentor():
     input('Tor Connected. Press ENTER to continue\n')
     return
 
+
 # Returns the name of the website
 def getMKTName():
     name = 'DarkBazar'
     return name
 
+
 # Return the base link of the website
 def getFixedURL():
-    url = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/log.php'
+    url = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/'
     return url
 
 
@@ -164,6 +80,7 @@ def closetor(driver):
     time.sleep(3)
     return
 
+
 # Creates FireFox 'driver' and configure its 'Profile'
 # to use Tor proxy and socket
 def createFFDriver():
@@ -179,9 +96,9 @@ def createFFDriver():
     ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True)
     ff_prof.set_preference("signon.rememberSignons", False)
     ff_prof.set_preference("network.cookie.lifetimePolicy", 2)
-    ff_prof.set_preference("network.dns.disablePrefetch", True)
-    ff_prof.set_preference("network.http.sendRefererHeader", 0)
-    ff_prof.set_preference("permissions.default.image", 2)
+    # ff_prof.set_preference("network.dns.disablePrefetch", True)
+    # ff_prof.set_preference("network.http.sendRefererHeader", 0)
+    ff_prof.set_preference("permissions.default.image", 1)
     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")
@@ -197,11 +114,10 @@ def createFFDriver():
 
     driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service)
 
+    driver.maximize_window()
+
     return driver
 
-def productPages(html):
-    soup = BeautifulSoup(html, "html.parser")
-    return darkbazar_links_parser(soup)
 
 #the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
 def getAccess():
@@ -214,10 +130,40 @@ def getAccess():
         driver.close()
         return 'down'
 
+
+def login(driver):
+    input("Press ENTER when CAPTCHA is complete and login page has loaded\n")
+
+    # entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='//input[@name="username"]')
+    # Username here
+    usernameBox.send_keys('aliciamykeys')
+    passwordBox = driver.find_element(by=By.XPATH, value='//input[@name="password"]')
+    # Password here
+    passwordBox.send_keys('aliciawherearemykey$')
+    # session time
+    session_select = Select(driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[4]/div/div[2]/select'))
+    session_select.select_by_visible_text('Session 60min')
+
+    input("Press ENTER when CAPTCHA is completed and you exit the newsletter\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, '//*[@id="submit"]')))
+
+
+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
+
+
 def getFullPathName(url):
-    from Forums.Initialization.forums_mining import config, CURRENT_DATE
+    from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE
 
-    mainDir = os.path.join(config.get('Project', 'shared_folder'), "Forums/" + getForumName() + "/HTML_Pages")
+    mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getForumName() + "/HTML_Pages")
     fileName = getNameFromURL(url)
     if isDescriptionLink(url):
         fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html')
@@ -225,6 +171,88 @@ def getFullPathName(url):
         fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html')
     return fullPath
 
+
+def getForumName() -> str:
+    name = 'DarkBazar'
+    return name
+
+
+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 = []
+
+    # # Digital Goods
+    # links.append('http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/cat.php?category=4')
+    # Services
+    links.append('http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/cat.php?category=5')
+
+    return links
+
+
+def crawlForum(driver):
+
+    print("Crawling the DarkBazar 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, link)
+
+                list = productPages(html)
+
+                for item in list:
+                    itemURL = urlparse.urljoin(baseURL, str(item))
+                    try:
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver, driver.page_source, item)
+                    driver.back()
+
+                    # comment out
+                    # break
+
+                # comment out
+                if count == 1:
+                    break
+
+                try:
+                    link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "Next")]').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 DarkBazar market done.")
+
+
 # Returns 'True' if the link is Topic link, may need to change for every website
 def isDescriptionLink(url):
     if 'item' in url:
@@ -238,15 +266,11 @@ def isListingLink(url):
         return True
     return False
 
-def getForumName() -> str:
-    name = 'DarkBazar'
-    return name
 
-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 productPages(html):
+    soup = BeautifulSoup(html, "html.parser")
+    return darkbazar_links_parser(soup)
 
+
+def crawler():
+    startCrawling()

MarketPlaces/DarkBazar/parser.py

@@ -1,3 +1,5 @@
+__author__ = 'DarkWeb'
+
 # Here, we are importing the auxiliary functions to clean or convert data
 from MarketPlaces.Utilities.utilities import *
 
@@ -44,21 +46,23 @@ def darkbazar_description_parser(soup):
     vendor = divmb[1].find('a').text.strip()
 
     # Finding Vendor Rating
-    rating = soup.find('div', {'class': ""}).text
-    rating = rating.replace("Vendor's Review : ", "")
-    rating = rating.strip()
+    temp = soup.find('div', {'class': ""}).text
+    temp = temp.split('(')
+    rating = temp[0].replace("Vendor's Review : ", "")
+    rating = rating.replace("%", "")
+    rating_vendor = rating.strip()
+
+    # Finding the Product Rating and Number of Product Reviews
+    reviews = temp[2].replace(" review)", "")
+    reviews = reviews.strip()
 
-    # Finding Successful Transactions
-    success = divmb[3].text
-    success = success.replace("Level:", "")
-    success = success.strip()
+    temp = temp[1].split(")")
+    rating = temp[1].replace("Product Review : ", "")
+    rating = rating.replace("%", "")
+    rating_item = rating.strip()
 
     # Finding Prices
-    USD = soup.find('div', {'class': "h3 text - primary"}).text.strip()
-
-
-    # Finding Escrow
-    escrow = divmb[5].find('span', {'class': "badge badge-danger"}).text.strip()
+    USD = soup.find('div', {'class': "h3 text-primary"}).text.strip()
 
     # Finding the Product Category
     pmb = soup.findAll('p', {'class': "mb-1"})
@@ -78,7 +82,6 @@ def darkbazar_description_parser(soup):
     sold = sold.replace("sold", "")
     sold = sold.strip()
 
-
     # Finding Shipment Information (Origin)
     pmb[0].text
     shipFrom = shipFrom.replace("Ships from: ", "").strip()
@@ -91,13 +94,6 @@ def darkbazar_description_parser(soup):
     cardbody = soup.findAll('div', {'class': "card-body"})
     describe = cardbody[1].text.strip()
 
-    # Finding the Number of Product Reviews
-    reviews = reviews.find('div', {'class': "product-rating"}).text
-    reviews = reviews.replace("(", "")
-    reviews = reviews.replace(" review)", "")
-    reviews = reviews.strip()
-
-
     # Searching for CVE and MS categories
     cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
     if cve:
@@ -117,8 +113,8 @@ def darkbazar_description_parser(soup):
             MS = MS.replace('\n', '')
 
     # Populating the final variable (this should be a list with all fields scraped)
-    row = (name, describe, CVE, MS, review, category, shipFrom, shipTo, left, escrow, vendor,
-           sold, addDate, BTC, USD, rating, success, EURO)
+    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
@@ -129,30 +125,30 @@ def darkbazar_description_parser(soup):
 # @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 darkbazar_listing_parser(soup):
+
     # Fields to be parsed
-    nm = 0  # Total_Products (Should be Integer)
-    mktName = "DarkBazar"  # 0 Marketplace_Name
-    name = []  # 1 Product_Name
-    CVE = []  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
-    MS = []  # 3 Product_MS_Classification (Microsoft Security)
-    category = []  # 4 Product_Category
-    describe = []  # 5 Product_Description
-    escrow = []  # 6 Vendor_Warranty
-    views = []  # 7 Product_Number_Of_Views
-    reviews = []  # 8 Product_Number_Of_Reviews
-    addDate = []  # 9 Product_AddDate
-    lastSeen = []  # 10 Product_LastViewDate
-    BTC = []  # 11 Product_BTC_SellingPrice
-    USD = []  # 12 Product_USD_SellingPrice
-    EURO = []  # 13 Product_EURO_SellingPrice
-    sold = []  # 14 Product_QuantitySold
-    qLeft = []  # 15 Product_QuantityLeft
-    shipFrom = []  # 16 Product_ShippedFrom
-    shipTo = []  # 17 Product_ShippedTo
-    vendor = []  # 18 Vendor
-    rating = []  # 19 Vendor_Rating
-    success = []  # 20 Vendor_Successful_Transactions
-    href = []  # 23 Product_Links (Urls)
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "DarkBazar"  # 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) dont worry about this
+    MS = []  # 6 Product_MS_Classification (Microsoft Security) dont worry about this
+    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', {"id": "itembox"})
 
@@ -194,13 +190,21 @@ def darkbazar_listing_parser(soup):
         cat = cat.strip()
         category.append(cat)
 
-        # Finding Number Sold and Quantity Left
-        span = lb[1].findAll("span")
-        num = span[-1].text
+        span = lb[0].findAll("span")
+
+        # Finding Number of Views
+        num = span[0].text
+        num = num.replace("views:", "")
+        num = num.strip()
+        sold.append(num)
+
+        # Finding Number Sold
+        num = span[2].text
         num = num.replace("Sold:", "")
         num = num.strip()
-        category.append(num)
+        sold.append(num)
 
+        # Finding Quantity Left
         quant = span[1].text
         quant = quant.replace("stock:", "")
         quant = quant.strip()
@@ -235,8 +239,8 @@ def darkbazar_listing_parser(soup):
         MS.append(MSValue)
 
     # Populate the final variable (this should be a list with all fields scraped)
-    return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
-                            BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)
+    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)
 
 
 # called by the crawler to get description links on a listing page
@@ -258,7 +262,6 @@ def darkbazar_links_parser(soup):
 
         # Adding the url to the list of urls
         link = bae[0].get('href')
-        link = cleanLink(link)
         href.append(link)
 
     return href

MarketPlaces/DarkMatter/crawler_selenium.py

@@ -229,17 +229,16 @@ def crawlForum(driver):
                 for item in list:
                     itemURL = urlparse.urljoin(baseURL, str(item))
                     try:
-                        time.sleep(1.5) # to keep from detecting click speed
+                        time.sleep(3) # to keep from detecting click speed
                         driver.get(itemURL)
                     except:
                         driver.refresh()
                     savePage(driver, driver.page_source, item)
-                    time.sleep(1.5)
+                    time.sleep(3) # to keep from detecting click speed
                     driver.back()
-                     # to keep from detecting click speed
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/DigitalThriftShop/crawler_selenium.py

@@ -235,7 +235,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/HiddenMarket/crawler_selenium.py

@@ -277,7 +277,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/Initialization/marketsList.txt

@@ -1,8 +1 @@
-Apocalypse
-DarkMatter
-DigitalThriftShop
-HiddenMarket
-Nexus
-Robinhood
-TorBay
-ViceCity
+DarkBazar

MarketPlaces/Initialization/markets_mining.py

@@ -24,6 +24,7 @@ from MarketPlaces.HiddenMarket.crawler_selenium import crawler as crawlerHiddenM
 from MarketPlaces.RobinhoodMarket.crawler_selenium import crawler as crawlerRobinhoodMarket
 from MarketPlaces.Nexus.crawler_selenium import crawler as crawlerNexus
 from MarketPlaces.CypherMarketplace.crawler_selenium import crawler as crawlerCypher
+from MarketPlaces.DarkBazar.crawler_selenium import crawler as crawlerDarkBazar
 
 import configparser
 import os
@@ -137,5 +138,7 @@ if __name__ == '__main__':
             crawlerNexus()
         elif mkt == "CypherMarketplace":
             crawlerCypher()
+        elif mkt == "DarkBazar":
+            crawlerDarkBazar()
 
     print("\nScraping process completed!")

MarketPlaces/Initialization/prepare_parser.py

@@ -1,4 +1,4 @@
-__author__ = 'Helium'
+__author__ = 'DarkWeb'
 
 import glob
 import os
@@ -21,6 +21,7 @@ from MarketPlaces.HiddenMarket.parser import *
 from MarketPlaces.RobinhoodMarket.parser import *
 from MarketPlaces.Nexus.parser import *
 from MarketPlaces.MikesGrandStore.parser import *
+from MarketPlaces.DarkBazar.parser import *
 
 from MarketPlaces.Classifier.classify_product import predict
 
@@ -148,6 +149,8 @@ def parse_listing(marketPlace, listingFile, soup, createLog, logFile):
             rw = nexus_listing_parser(soup)
         elif marketPlace == "MikesGrandStore":
             rw = mikesGrandStore_listing_parser(soup)
+        elif marketPlace == "DarkBazar":
+            rw = darkbazar_listing_parser(soup)
         else:
             print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!")
             raise Exception
@@ -199,6 +202,8 @@ def parse_description(marketPlace, descriptionFile, soup, createLog, logFile):
             rmm = nexus_description_parser(soup)
         elif marketPlace == "MikesGrandStore":
             rmm = mikesGrandStore_description_parser(soup)
+        elif marketPlace == "DarkBazar":
+            rmm = darkbazar_description_parser(soup)
         else:
             print("MISSING CALL TO DESCRIPTION PARSER IN PREPARE_PARSER.PY!")
             raise Exception

MarketPlaces/LionMarketplace/crawler_selenium.py

@@ -234,7 +234,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/LionMarketplace/parser.py

@@ -34,15 +34,11 @@ def lionmarketplace_description_parser(soup):
     shipTo = "-1"  # 18 Product_ShippedTo
 
     # vendor name
-    try:
-        temp = soup.find('div', {'class': 'btn-group'}).find('a').text
-        vendor = (cleanString(temp.strip()))
-    except:
-        print('vendor')
-        vendor = "-1"
+    temp = soup.find('div', {'class': 'btn-group'}).find('a').text
+    vendor = (cleanString(temp.strip()))
 
     # table with info
-    table = soup.find('table', {'class', 'table border-0 text-left table-borderless'})
+    table = soup.find('table')
     rows = table.findAll('tr')
 
     # successful transaction
@@ -51,37 +47,20 @@ def lionmarketplace_description_parser(soup):
     # vendor rating 5
     rating_vendor = '-1'
 
-
     # product name
-    try:
-        temp = soup.find('div', {'class', 'row'}).find('h2').text
-        name = (cleanString(temp.strip()))
-    except:
-        name = '-1'
-        print('product name')
+    temp = soup.find('div', {'class', 'row'}).find('h2').text
+    name = (cleanString(temp.strip()))
 
     # product description
-    try:
-        temp = soup.find('div', {'class': "mt-4"}).findAll('p')
-        temp = temp[1].text
-        if "\n" in temp:
-            temp = temp.replace("\n", " ")
-            temp = temp.replace("\r", " ")
-        describe = cleanString(temp.strip())
-    except:
-        describe="-1"
-        print('describe')
+    temp = soup.find('div', {'class': "mt-4"}).find(text=True, recursive=False)
+    describe = cleanString(temp.strip())
 
     CVE = "-1"  # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about that much
     MS = "-1"  # 6 Product_MS_Classification (Microsoft Security) dont worry about that much
 
     # product category
-    try:
-        temp = rows[1].find('strong').text
-        category = cleanString(temp.strip())
-    except:
-        category = "-1"
-        print('category')
+    temp = rows[1].find('strong').text
+    category = cleanString(temp.strip())
 
     # product number of views
     views = "-1"
@@ -92,54 +71,38 @@ def lionmarketplace_description_parser(soup):
     BTC = "-1"
 
     # USD selling price
-    try:
-        temp = rows[2].find('strong').text
-        if " $" in temp:
-            temp = temp.replace(" $", "")
-        elif "$" in temp:
-            temp = temp.replace("$", "")
-        USD = cleanString((temp.strip()))
-    except:
-        try:
-            temp = soup.find('li').find('strong').text
-            if " $" in temp:
-                temp = temp.replace(" $", "")
-            elif "$" in temp:
-                temp = temp.replace("$", "")
-            USD = cleanString((temp.strip()))
-        except:
-            print("USD")
+    temp = rows[2].find('strong').text
+    if " $" in temp:
+        temp = temp.replace(" $", "")
+    elif "$" in temp:
+        temp = temp.replace("$", "")
+    USD = cleanString((temp.strip()))
 
     EURO = "-1"  # 14 Product_EURO_SellingPrice
 
     # product sold
-    try:
-        if (len(rows) <= 5):
-            temp = rows[4].find('td').text
-            string = cleanString(temp)
-            if (string == 'Left/Sold'):
-                temp = rows[4].findAll('td')
-                temp = temp[1].findAll('span')
-
-                # left
-                temp2 = temp[1].text
-                temp3 = temp[1].text
-
-                if(" items" in temp2):
-                    temp2 = temp2.replace(" items", "")
-                if(" items" in temp3):
-                    temp3 = temp3.replace(" items", "")
-
-                sold = (cleanString(temp2.strip()))
-                left = cleanString(temp3.strip())
-            else:
-                sold = '-1'
-                left = "-1"
+    if (len(rows) <= 5):
+        temp = rows[4].find('td').text
+        string = cleanString(temp)
+        if (string == 'Left/Sold'):
+            temp = rows[4].findAll('td')
+            temp = temp[1].findAll('span')
+
+            # left
+            temp2 = temp[1].text
+            temp3 = temp[1].text
+
+            if(" items" in temp2):
+                temp2 = temp2.replace(" items", "")
+            if(" items" in temp3):
+                temp3 = temp3.replace(" items", "")
+
+            sold = (cleanString(temp2.strip()))
+            left = cleanString(temp3.strip())
         else:
             sold = '-1'
             left = "-1"
-    except:
-        print("success")
+    else:
         sold = '-1'
         left = "-1"
 
@@ -161,7 +124,7 @@ def lionmarketplace_description_parser(soup):
 def lionmarketplace_listing_parser(soup):
     # Fields to be parsed
     nm = 0  # *Total_Products (Should be Integer)
-    mktName = "M00nkeyMarket"  # 0 *Marketplace_Name
+    mktName = "LionMarketplace"  # 0 *Marketplace_Name
     vendor = []  # 1 *Vendor y
     rating_vendor = []  # 2 Vendor_Rating
     success = []  # 3 Vendor_Successful_Transactions
@@ -183,21 +146,20 @@ def lionmarketplace_listing_parser(soup):
     shipTo = []  # 19 Product_ShippedTo
     href = []  # 20 Product_Links
 
-    listing = soup.findAll('div', {"class": "card-body"})
+    listings = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"})
 
     # Populating the Number of Products
-    nm = len(listing)
+    nm = len(listings)
 
-    for a in listing:
+    for listing in listings:
 
+        a = listing.find('div', {"class": "card-body"})
         row = a.findAll('p')
+
         # vendor
-        try:
-            temp = row[3].text
-            vendor.append(cleanString(temp.strip()))
-        except:
-            vendor.append("-1")
-            print('vendor')
+        temp = row[3].text
+        temp = temp.replace("Vendor:", "")
+        vendor.append(cleanString(temp.strip()))
 
         # vendor rating
         rating_vendor.append("-1")
@@ -206,25 +168,16 @@ def lionmarketplace_listing_parser(soup):
         success.append("-1")
 
         # product name
-        try:
-            temp = a.find('a').text
-            name.append(cleanString(temp.strip()))
-        except:
-            name.append("-1")
-            print('product name')
+        temp = a.find('a').text
+        name.append(cleanString(temp.strip()))
 
         CVE.append('-1')
         MS.append('-1')
 
         # product category
-        try:
-            temp = row[2].text
-            if "Category: " in temp:
-                temp = temp.replace("Category: ", "")
-            category.append(cleanString(temp.strip()))
-
-        except:
-            print("Error in product category")
+        temp = row[2].text
+        temp = temp.replace("Category: ", "")
+        category.append(cleanString(temp.strip()))
 
         describe.append('-1')
 
@@ -238,14 +191,10 @@ def lionmarketplace_listing_parser(soup):
         BTC.append('-1')
 
         # USD
-        try:
-            temp = row[0].find('strong').text
-            if ' $' in temp:
-                temp = temp.replace(" $", "")
-            USD.append(cleanString(temp.strip()))  # 14 Product_USD_SellingPrice
-        except:
-            print("USD")
-            USD.append("-1")
+        temp = row[0].find('strong').text
+        if ' $' in temp:
+            temp = temp.replace(" $", "")
+        USD.append(cleanString(temp.strip()))  # 14 Product_USD_SellingPrice
 
         EURO.append("-1")  # 15 Product_EURO_SellingPrice
 
@@ -257,11 +206,8 @@ def lionmarketplace_listing_parser(soup):
         shipTo.append('-1')  # 19 Product_ShippedTo
 
         # href
-        try:
-            temp = a.find('a').get('href')
-            href.append(temp)
-        except:
-            print('product name')
+        temp = a.find('a').get('href')
+        href.append(temp)
 
     # 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,
@@ -276,9 +222,10 @@ def lionmarketplace_links_parser(soup):
     # Returning all links that should be visited by the Crawler
 
     href = []
-    listing = soup.findAll('div', {"class": "container d-flex justify-content-center"})
+    listings = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"})
 
-    for a in listing:
+    for listing in listings:
+        a = listing.find('div', {"class": "card-body"})
         bae = a.find('a', href=True)
         link = bae['href']
         href.append(link)

MarketPlaces/M00nkeyMarket/crawler_selenium.py

@@ -159,7 +159,7 @@ def login(driver):
 
     # 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")))
+        (By.XPATH, "/html/body/div/div[2]/div/div/div/div/div/div[1]/a/img")))
 
 # Saves the crawled html page, makes the directory path for html pages if not made
 def savePage(driver, page, url):

MarketPlaces/Nexus/crawler_selenium.py

@@ -173,16 +173,24 @@ def getNameFromURL(url):
 def getInterestedLinks():
     links = []
 
-    # Bot nets
-    links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/botnets/')
-    # # Rats
-    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/rats/')
-    # # Ransomware
-    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/ransomware/')
-    # # Other Malware
-    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/outros-malware/')
-    # # Hacking Tools & Scripting
-    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/hacking-spam/ferramentas-de-hacking-scripts/')
+    # malware
+    links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/')
+    # # hacking-spam
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/hacking-spam/')
+    # # hacking services
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/hacking/')
+    # # programming services
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/programacao/')
+    # # remote admin services
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/administracao-remota/')
+    # # hacking guides
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-hacking/')
+    # # malware guides
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-malware/')
+    # # fraud guides
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-fraudes/')
+    # # fraud software
+    # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/fraudes/software-de-fraude/')
 
     return links
 
@@ -222,7 +230,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                     # comment out
                 if count == 1:

MarketPlaces/RobinhoodMarket/crawler_selenium.py

@@ -218,7 +218,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:
@@ -266,5 +266,6 @@ def crawler():
     startCrawling()
     # print("Crawling and Parsing BestCardingWorld .... DONE!")
 
+
 if __name__ == '__main__':
-    startCrawling()
+    startCrawling()

MarketPlaces/ThiefWorld/crawler_selenium.py

@@ -144,7 +144,7 @@ def getAccess():
 def login(driver):
     # wait for  page to show up (This Xpath may need to change based on different seed url)
     WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
-        (By.XPATH, "/html/body/div/div[1]/div/div[1]/div[1]/ul")))
+        (By.XPATH, "/html/body/div/header/div[2]/div/nav/div[2]/a[1]")))
 
     temp = driver.find_element(By.XPATH, '/html/body/div/header/div[2]/div/nav/div[2]/a[1]').get_attribute(
         'href')  # /html/body/div/div[2]/div/div[2]/div
@@ -242,7 +242,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/TorBay/crawler_selenium.py

@@ -228,7 +228,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1:

MarketPlaces/TorMarket/crawler_selenium.py

@@ -37,7 +37,6 @@ def startCrawling():
 
     if driver != 'down':
         try:
-            # login(driver)
             crawlForum(driver)
         except Exception as e:
             print(driver.current_url, e)
@@ -101,8 +100,8 @@ def createFFDriver():
     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("network.dns.disablePrefetch", True)
+    # ff_prof.set_preference("network.http.sendRefererHeader", 0)
     ff_prof.set_preference("permissions.default.image", 1)
     ff_prof.set_preference("browser.download.folderList", 2)
     ff_prof.set_preference("browser.download.manager.showWhenStarting", False)
@@ -186,12 +185,12 @@ def getNameFromURL(url):
 def getInterestedLinks():
     links = []
 
-    # # Hacking Tutorials
-    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/guides-tutorials/hacking/')
+    # # Tutorials
+    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/guides-tutorials/')
     # Malware
     links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/malware/')
-    # # Hacking Services
-    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/services/hacking-services/')
+    # # Services
+    # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/services/')
 
     return links
 
@@ -238,8 +237,7 @@ def crawlForum(driver):
                     break
 
                 try:
-                    link = driver.find_element(by=By.XPATH, value=
-                        '/html/body/div[2]/div/div/div[1]/main/nav/ul/li[5]/a').get_attribute('href')
+                    link = driver.find_element(by=By.LINK_TEXT, value='Next').get_attribute('href')
                     if link == "":
                         raise NoSuchElementException
                     count += 1

MarketPlaces/TorMarket/parser.py

@@ -104,61 +104,58 @@ def tormarket_listing_parser(soup):
     shipFrom = []  # 18 Product_ShippedFrom
     shipTo = []  # 19 Product_ShippedTo
     href = []  # 20 Product_Links
-    products_list = soup.find_all('li')
-    nm = 0
+
+    products_list = soup.find('ul', {"class": "products columns-3 tablet-columns-2 mobile-columns-1"}).find_all('li')
+    nm = len(products_list)
+
     for product in products_list:
+        # Finding the name of the product
+        name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text
+        name_of_product_cleaned = cleanString(name_of_product.strip())
+        # print(name_of_product_cleaned)
+        name.append(name_of_product_cleaned)
+        #finding the URL
         try:
-            # Finding the name of the product
-            name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text
-            name_of_product_cleaned = cleanString(name_of_product.strip())
-            print(name_of_product_cleaned)
-            name.append(name_of_product_cleaned)
-            #finding the URL
-            try:
-                url = product.find("div", {"class": "product-loop-content text-center"}).find("a").get("href")
-                print(url)
-                href.append(url)
-            except AttributeError as e:
-                print("I can't find the link")
-                raise e
-
-            #finding the rating of the product
-            rating_score_of_product = product.find("div", {"class": "product-loop-content text-center"}).find("div").find("span").text
-            rating_item.append(cleanString(rating_score_of_product.strip()))
-            print("done")
-            #finding the rating of the vendors
-            rating_score_of_vendor = product.find("div", {"class": "wcfmmp-store-rating"}).find("strong").text
-            rating_vendor.append(cleanString(rating_score_of_vendor.strip()))
-            print("done")
-            #finding the cost in USD
-            cost = product.find("span", {"class": "woocommerce-Price-amount amount"}).text
-            USD.append(cost)
-            print("done")
-            #finding the name of the vendor
-            vendor_name = product.find("div", {"class": "wcfmmp_sold_by_wrapper"}).find("a").text
-            vendor.append(cleanString(vendor_name.strip()))
-            print("done")
-            #everything else appends a -1
-            success.append("-1")
-            CVE.append("-1")
-            MS.append("-1")
-            category.append("-1")
-            describe.append("-1")
-            views.append("-1")
-            reviews.append("-1")
-            addDate.append("-1")
-            BTC.append("-1")
-            EURO.append("-1")
-            sold.append("-1")
-            qLeft.append("-1")
-            shipFrom.append("-1")
-            shipTo.append("-1")
-            print("Done! moving onto the next product!")
-            print(len(shipTo))
-            nm += 1
+            url = product.find("div", {"class": "product-loop-content text-center"}).find("a").get("href")
+            # print(url)
+            href.append(url)
         except AttributeError as e:
-            print("I'm somewhere I don't belong. I'm going to leave")
-            continue
+            print("I can't find the link")
+            raise e
+
+        #finding the rating of the product
+        rating_score_of_product = product.find("div", {"class": "product-loop-content text-center"}).find("div").find("span").text
+        rating_item.append(cleanString(rating_score_of_product.strip()))
+        # print("done")
+        #finding the rating of the vendors
+        rating_score_of_vendor = product.find("div", {"class": "wcfmmp-store-rating"}).find("strong").text
+        rating_vendor.append(cleanString(rating_score_of_vendor.strip()))
+        # print("done")
+        #finding the cost in USD
+        cost = product.find("span", {"class": "woocommerce-Price-amount amount"}).text
+        USD.append(cost)
+        # print("done")
+        #finding the name of the vendor
+        vendor_name = product.find("div", {"class": "wcfmmp_sold_by_wrapper"}).find("a").text
+        vendor.append(cleanString(vendor_name.strip()))
+        # print("done")
+        #everything else appends a -1
+        success.append("-1")
+        CVE.append("-1")
+        MS.append("-1")
+        category.append("-1")
+        describe.append("-1")
+        views.append("-1")
+        reviews.append("-1")
+        addDate.append("-1")
+        BTC.append("-1")
+        EURO.append("-1")
+        sold.append("-1")
+        qLeft.append("-1")
+        shipFrom.append("-1")
+        shipTo.append("-1")
+        # print("Done! moving onto the next product!")
+        # print(len(shipTo))
 
 
     # Populate the final variable (this should be a list with all fields scraped)

MarketPlaces/ViceCity/crawler_selenium.py

@@ -271,7 +271,7 @@ def crawlForum(driver):
                     driver.back()
 
                     # comment out
-                    break
+                    # break
 
                 # comment out
                 if count == 1: