Merge branch 'van-deliverable' into 'main'

pull request from Van

See merge request dw9372422/dw_pipeline_test!7

MarketPlaces/GoFish/crawler_selenium.py

@@ -0,0 +1,300 @@
+__author__ = 'DarkWeb'
+
+'''
+Go Fish market Crawler (Selenium)
+- this is a new marketplace and was up for only a few days, crawler has not been finished
+'''
+
+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.GoFish.parser import gofish_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.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, True)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    from MarketPlaces.Initialization.markets_mining import config
+
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'GoFish'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.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():
+    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", 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")
+    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
+#@param: current selenium web driver
+def login(driver):
+    input("Press ENTER when CAPTCHA is completed\n")
+
+    # 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, '//*[@id="username"]')))
+
+    # entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
+    # Username here
+    usernameBox.send_keys('itsmedio')
+    passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
+    # Password here
+    passwordBox.send_keys('DementedBed123-')
+
+    input("Press ENTER when CAPTCHA and exit pressed is completed\n")
+
+    # wait for listing page show up (This Xpath may need to change based on different seed url)
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, "/html/body/div/div[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):
+    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
+    links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=129')
+    # Malware
+    links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=97')
+    # Exploits
+    links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=107')
+
+    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 GoFish 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)
+                    time.sleep(3)
+                    driver.back()
+
+                    # comment out
+                    break
+
+                # comment out
+                if count == 1:
+                    break
+
+                try:
+                    link = driver.find_element(by=By.LINK_TEXT, value='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 GoFishMarket 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 'c' 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 'a' 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 gofish_links_parser(soup)
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/GoFish/parser.py

@@ -0,0 +1,327 @@
+__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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def gofish_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) dont worry about that much
+    MS = "-1"  # 6 Product_MS_Classification (Microsoft Security) dont worry about that much
+    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
+
+    #vendor name
+    try:
+        temp = soup.find('div', {'class': 'box rounded mb-0'}).find('a').text
+        vendor = (cleanString(temp.strip()))
+    except:
+        vendor = "-1"
+
+    #successful transaction
+    try:
+        temp = soup.findAll('div', {'class','text-center text-truncate column-flex ml-1 mr-1'}) #card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
+        temp = temp2[1].text
+        success = (temp.strip())
+    except:
+        print("success")
+
+
+    #vendor rating 5
+    try:
+        temp = soup.findAll('div', {'class', 'text-center text-truncate column-flex ml-1 mr-1'})  # card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
+        temp = temp2[5].text
+        rating_vendor = (cleanString(temp.strip()))
+    except:
+        print("product")
+
+    # product name
+    try:
+        temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').text
+        name = (cleanString(temp.strip()))
+    except:
+        temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').find("div").text
+        name = (cleanString(temp.strip()))
+
+    # product description
+    describe = soup.find('div', {'class': "box rounded flex-fill"}).find('pre').text
+    if "\n" in describe:
+        describe = describe.replace("\n", " ")
+        describe = describe.replace("\r", " ")
+    describe = cleanString(describe.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 = soup.findAll('table', {'class', 'table table-hover'})
+        temp2 = temp[1].find('tr').findAll('td')
+        temp = temp2[1].text
+        category = cleanString(temp.strip())
+    except:
+        temp = soup.find('table', {'class', 'table table-hover'})
+        temp2 = temp.find('tbody').find('tr').findAll('td')
+        temp = temp2[1].text
+        category = cleanString(temp.strip())
+
+    # product number of view
+    try:
+        temp = soup.find('div', {'class', 'box rounded mb-0'})
+        temp2 = temp.findAll('i')
+        temp = temp2[2].text
+        views = cleanString((temp.strip()))
+    except:
+        print('Product number of view')
+
+    reviews = "-1"  # 9 Product_Number_Of_Reviews
+    rating_item = "-1"  # 10 Product_Rating
+    addDate = "-1"  # 11 Product_AddedDate
+
+    #BTC selling price box box-rounded mt-2
+    try:
+        temp = soup.find('div', {'class', 'box box-rounded mt-2'})
+        temp2 = temp.findAll('i', {'class', 'float-right color-prices'})
+        temp = temp2[1].text
+        BTC = cleanString((temp.strip()))
+    except:
+        try:
+            temp = soup.find('div', {'class', 'box box-rounded'})
+            temp2 = temp.findAll('span', {'class', 'float-right color-prices'})
+            temp = temp2[1].text
+            BTC = cleanString((temp.strip()))
+        except:
+            print("BTC")
+
+
+    # USD selling price
+    try:
+        temp = soup.find('div', {'class', 'box box-rounded mt-2'})
+        temp2 = temp.findAll('center')
+        temp = temp2[1].find('i').text
+        if "$" in temp:
+            temp = temp.replace("$", "")
+        USD = cleanString((temp.strip()))
+    except:
+        try:
+            temp = soup.find('div', {'class', 'box box-rounded'})
+            temp2 = temp.findAll('center')
+            temp = temp2[1].find('span').text
+            if "$" in temp:
+                temp = temp.replace("$", "")
+            USD = cleanString((temp.strip()))
+        except:
+            print("USD")
+
+    EURO = "-1"  # 14 Product_EURO_SellingPrice
+
+
+   # product sold
+    try:
+        temp = soup.find('div', {'class', 'box rounded mb-0'})  # card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp.find('i')
+        temp = temp2.text
+        sold = (cleanString(temp.strip()))
+        # sold = "-1"
+    except:
+        print("product sold")
+
+    # product quantatiy left  ###ERRROR
+    try:
+        temp = soup.findAll('table', {'class', 'table table-hover'})
+        temp2 = temp[1].findAll('tr')
+        temp3 = temp2[1].findAll('td')
+        temp = temp3[1].text
+        left = cleanString(temp.strip())
+    except:
+        temp = soup.find('table', {'class', 'table table-hover'})
+        temp2 = temp.findAll('tr')
+        temp3 = temp2[1].findAll('td')
+        temp = temp3[1].text
+        left = cleanString(temp.strip())
+
+
+    shipFrom = "-1"  # 17 Product_ShippedFrom
+    shipTo = "-1"  # 18 Product_ShippedTo
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def gofish_listing_parser(soup):
+    # Fields to be parsed
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "GoFish"  # 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', {"class": "card mt-1"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+
+        # vendor
+        try:
+            temp = a.find('div', {'class','col-5 justify-content-between mx-auto'}).find('a').text
+            vendor.append(cleanString(temp.strip()))
+        except:
+            print('vendor')
+
+        #vendor rating
+
+
+        #successful transactions CHECK AGAIN HERE
+        try:
+            success.append("-1")
+        except:
+            print('successful transactions')
+
+        # product name
+        try:
+            temp = a.find('h5', {'class','card-title rounded text-truncate'}).find('a').text
+            name.append(cleanString(temp.strip()))
+        except:
+            print('product name')
+
+
+        CVE.append('-1')
+        MS.append('-1')
+        rating_vendor.append('-1')
+
+        # product category
+        try:
+            temp = soup.find('div', {'class', 'card-sidebar-menu box mb-2 flex-column'}).find('h3').find('span').text
+            if "Search Results for: " in temp:
+                temp = temp.replace("Search Results for: ", "")
+            category.append(cleanString(temp.strip()))
+
+        except:
+            print("Error in product category")
+
+        describe.append('-1')
+
+        # product views
+        try:
+            temp = a.find('h6',{'class', 'card-subtitle mb-1 text-muted text-truncate'})
+            temp2 = temp.find('i').text
+            views.append(cleanString(temp2.strip()))
+        except:
+            print("Error in views")
+
+        reviews.append('-1')  # 10 Product_Number_Of_Reviews
+        rating_item.append('-1')  # 11 Product_Rating
+        addDate.append('-1')  # 12 Product_AddDate
+
+        # BTC
+        try:
+            temp = a.find('div', {'class', 'col-3 justify-content-between mx-auto'})
+            temp2 = temp.findAll('p')
+            temp = temp2[1].text
+            BTC.append(cleanString(temp.strip()))
+        except:
+            print("BTC")
+
+        #USD ERROR get rid of $
+        try:
+            temp = a.find('div', {'class', 'col-12 justify-content-between mx-auto'}).find('i').text
+            if '$' in temp:
+                temp = temp.replace("$", "")
+            USD.append(cleanString(temp.strip()))  # 14 Product_USD_SellingPrice
+        except:
+            print("USD")
+
+        EURO.append("-1")  # 15 Product_EURO_SellingPrice
+
+        #product sold
+        try:
+            temp = a.find('div', {'class', 'col-12 mx-auto text-truncate text-center flex-fill'}).findAll('p', {'class', 'card-text mb-0'})
+            temp2 = temp[1].find('i').text
+            sold.append(cleanString(temp2.strip()))
+        except:
+            print("product sold")
+
+        qLeft.append('-1')  # 17 Product_QuantityLeft
+        shipFrom.append('-1')  # 18 Product_ShippedFrom
+        shipTo.append('-1')  # 19 Product_ShippedTo
+
+        #href
+        try:
+            temp = a.find('h5', {'class', 'card-title rounded text-truncate'}).find('a').get('href')
+            href.append(temp)  # 20 Product_Links
+        except:
+            print("href")
+
+
+    # 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)
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def gofish_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    listing = soup.findAll('div', {"class": "card mt-1"})
+
+    for a in listing:
+        bae = a.find('a',  href=True)#card-title rounded text-truncate
+        link = bae['href']
+        href.append(link)
+
+    return href

MarketPlaces/Torzon/crawler_selenium.py

@@ -0,0 +1,308 @@
+__author__ = 'DarkWeb'
+
+'''
+Torzon Market Crawler (Selenium)
+- problem extracting description links from HTML structure, continue work with this crawler
+by fixing torzon_links_parser()
+'''
+
+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.Torzon.parser import torzon_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+
+counter = 1
+BASE_URL = 'http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.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, BASE_URL, False)
+
+
+# Opens Tor Browser
+#prompts for ENTER input to continue
+def opentor():
+    from MarketPlaces.Initialization.markets_mining import config
+
+    global pid
+    print("Connecting Tor...")
+    pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path'))
+    pid = pro.pid
+    time.sleep(7.5)
+    input('Tor Connected. Press ENTER to continue\n')
+    return
+
+
+# Returns the name of the website
+#return: name of site in string type
+def getMKTName():
+    name = 'Torzon'
+    return name
+
+
+# Return the base link of the website
+#return: url of base site in string type
+def getFixedURL():
+    url = 'http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.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():
+    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)#connection issue
+    # ff_prof.set_preference("network.http.sendRefererHeader", 0)#connection issue
+    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")
+    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() ###### may want to use BASE_URL instead #######
+    try:
+        driver.get(BASE_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):
+    input("Press ENTER when CAPTCHA is completed and page is loaded\n")
+    # wait for  page to show up (This Xpath may need to change based on different seed url)
+
+# 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)
+    # filePath = getFullPathName("Hello")
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    with open(filePath, 'wb') as file:
+        file.write(cleanPage.encode('utf-8'))
+    # 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 = []
+
+    # # services
+    links.append('http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.onion/products.php?sta=1&shipsto=All&shipsfrom=All&category=Services&small=0&big=5000000&id=1995441210213618738586452129269668912607120977870')
+
+    # # software & malware
+    links.append('http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.onion/products.php?sta=1&shipsto=All&shipsfrom=All&category=Services&small=0&big=5000000&id=1995441210213618738586452129269668912607120977870')
+
+    # # fraud
+    links.append('http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.onion/products.php?sta=1&shipsto=All&shipsfrom=All&category=Services&small=0&big=5000000&id=1995441210213618738586452129269668912607120977870')
+
+    # # guides
+    links.append('http://torzon4kv5swfazrziqvel2imhxcckc4otcvopiv5lnxzpqu4v4m5iyd.onion/products.php?sta=1&shipsto=All&shipsfrom=All&category=Guides and Tutorials&small=0&big=5000000&id=75026212163304997524932260388151806190538071909089')
+
+    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 Torzon 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(BASE_URL, str(item))
+                    try:
+                        time.sleep(1.5) # to keep from detecting click speed
+                        driver.get(itemURL)
+                    except:
+                        driver.refresh()
+                    savePage(driver.page_source, item)
+                    time.sleep(1.5)
+                    driver.back()
+                     # to keep from detecting click speed
+
+                #     # comment out
+                #     break
+                #
+                # # comment out
+                # if count == 1:
+                #     break
+
+                try:
+                    # nav = driver.find_element(by=By.XPATH, value='/html/body/table[1]/tbody/tr/td/form/div/div[2]/table[2]')
+                    # a = nav.find_element(by=By.LINK_TEXT, value=">")
+                    link = driver.find_element(by=By.LINK_TEXT, value=">").get_attribute('href')
+                    if link == "":
+                        raise NoSuchElementException
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+            # raise e
+        i += 1
+
+    input("Crawling Torzon market 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 'products/' in url and '/products/?category' not 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 torzon_links_parser(soup)
+
+
+# Drop links that "signout"
+# def isSignOut(url):
+#     #absURL = urlparse.urljoin(url.base_url, url.url)
+#     if 'signout' in url.lower() or 'logout' in url.lower():
+#         return True
+#
+#     return False
+
+
+def crawler():
+    startCrawling()
+    # print("Crawling and Parsing BestCardingWorld .... DONE!")

MarketPlaces/Torzon/parser.py

@@ -0,0 +1,328 @@
+__author__ = 'Helium'
+
+# 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
+
+
+#parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of description page
+#return: 'row' that contains a variety of lists that each hold info on the description page
+def torzon_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) dont worry about that much
+    MS = "-1"  # 6 Product_MS_Classification (Microsoft Security) dont worry about that much
+    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
+
+    #vendor name
+    try:
+        temp = soup.find('div', {'class': 'box rounded mb-0'}).find('a').text
+        vendor = (cleanString(temp.strip()))
+    except:
+        vendor = "-1"
+
+    #successful transaction
+    try:
+        temp = soup.findAll('div', {'class','text-center text-truncate column-flex ml-1 mr-1'}) #card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
+        temp = temp2[1].text
+        success = (temp.strip())
+    except:
+        print("success")
+
+
+    #vendor rating 5
+    try:
+        temp = soup.findAll('div', {'class', 'text-center text-truncate column-flex ml-1 mr-1'})  # card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
+        temp = temp2[5].text
+        rating_vendor = (cleanString(temp.strip()))
+    except:
+        print("product")
+
+    # product name
+    try:
+        temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').text
+        name = (cleanString(temp.strip()))
+    except:
+        temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').find("div").text
+        name = (cleanString(temp.strip()))
+
+    # product description
+    describe = soup.find('div', {'class': "box rounded flex-fill"}).find('pre').text
+    if "\n" in describe:
+        describe = describe.replace("\n", " ")
+        describe = describe.replace("\r", " ")
+    describe = cleanString(describe.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 = soup.findAll('table', {'class', 'table table-hover'})
+        temp2 = temp[1].find('tr').findAll('td')
+        temp = temp2[1].text
+        category = cleanString(temp.strip())
+    except:
+        temp = soup.find('table', {'class', 'table table-hover'})
+        temp2 = temp.find('tbody').find('tr').findAll('td')
+        temp = temp2[1].text
+        category = cleanString(temp.strip())
+
+    # product number of view
+    try:
+        temp = soup.find('div', {'class', 'box rounded mb-0'})
+        temp2 = temp.findAll('i')
+        temp = temp2[2].text
+        views = cleanString((temp.strip()))
+    except:
+        print('Product number of view')
+
+    reviews = "-1"  # 9 Product_Number_Of_Reviews
+    rating_item = "-1"  # 10 Product_Rating
+    addDate = "-1"  # 11 Product_AddedDate
+
+    #BTC selling price box box-rounded mt-2
+    try:
+        temp = soup.find('div', {'class', 'box box-rounded mt-2'})
+        temp2 = temp.findAll('i', {'class', 'float-right color-prices'})
+        temp = temp2[1].text
+        BTC = cleanString((temp.strip()))
+    except:
+        try:
+            temp = soup.find('div', {'class', 'box box-rounded'})
+            temp2 = temp.findAll('span', {'class', 'float-right color-prices'})
+            temp = temp2[1].text
+            BTC = cleanString((temp.strip()))
+        except:
+            print("BTC")
+
+
+    # USD selling price
+    try:
+        temp = soup.find('div', {'class', 'box box-rounded mt-2'})
+        temp2 = temp.findAll('center')
+        temp = temp2[1].find('i').text
+        if "$" in temp:
+            temp = temp.replace("$", "")
+        USD = cleanString((temp.strip()))
+    except:
+        try:
+            temp = soup.find('div', {'class', 'box box-rounded'})
+            temp2 = temp.findAll('center')
+            temp = temp2[1].find('span').text
+            if "$" in temp:
+                temp = temp.replace("$", "")
+            USD = cleanString((temp.strip()))
+        except:
+            print("USD")
+
+    EURO = "-1"  # 14 Product_EURO_SellingPrice
+
+
+   # product sold
+    try:
+        temp = soup.find('div', {'class', 'box rounded mb-0'})  # card sidebar-menu mb-4 card sidebar-menu mb-4
+        temp2 = temp.find('i')
+        temp = temp2.text
+        sold = (cleanString(temp.strip()))
+        # sold = "-1"
+    except:
+        print("product sold")
+
+    # product quantatiy left  ###ERRROR
+    try:
+        temp = soup.findAll('table', {'class', 'table table-hover'})
+        temp2 = temp[1].findAll('tr')
+        temp3 = temp2[1].findAll('td')
+        temp = temp3[1].text
+        left = cleanString(temp.strip())
+    except:
+        temp = soup.find('table', {'class', 'table table-hover'})
+        temp2 = temp.findAll('tr')
+        temp3 = temp2[1].findAll('td')
+        temp = temp3[1].text
+        left = cleanString(temp.strip())
+
+
+    shipFrom = "-1"  # 17 Product_ShippedFrom
+    shipTo = "-1"  # 18 Product_ShippedTo
+
+    # 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
+
+
+#parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs
+#stores info it needs in different lists, these lists are returned after being organized
+#@param: soup object looking at html page of listing page
+#return: 'row' that contains a variety of lists that each hold info on the listing page
+def torzon_listing_parser(soup):
+    # Fields to be parsed
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "Torzon"  # 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', {"class": "card mt-1"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    for a in listing:
+
+        # vendor
+        try:
+            temp = a.find('div', {'class','col-5 justify-content-between mx-auto'}).find('a').text
+            vendor.append(cleanString(temp.strip()))
+        except:
+            print('vendor')
+
+        #vendor rating
+
+
+        #successful transactions CHECK AGAIN HERE
+        try:
+            success.append("-1")
+        except:
+            print('successful transactions')
+
+        # product name
+        try:
+            temp = a.find('h5', {'class','card-title rounded text-truncate'}).find('a').text
+            name.append(cleanString(temp.strip()))
+        except:
+            print('product name')
+
+
+        CVE.append('-1')
+        MS.append('-1')
+        rating_vendor.append('-1')
+
+        # product category
+        try:
+            temp = soup.find('div', {'class', 'card-sidebar-menu box mb-2 flex-column'}).find('h3').find('span').text
+            if "Search Results for: " in temp:
+                temp = temp.replace("Search Results for: ", "")
+            category.append(cleanString(temp.strip()))
+
+        except:
+            print("Error in product category")
+
+        describe.append('-1')
+
+        # product views
+        try:
+            temp = a.find('h6',{'class', 'card-subtitle mb-1 text-muted text-truncate'})
+            temp2 = temp.find('i').text
+            views.append(cleanString(temp2.strip()))
+        except:
+            print("Error in views")
+
+        reviews.append('-1')  # 10 Product_Number_Of_Reviews
+        rating_item.append('-1')  # 11 Product_Rating
+        addDate.append('-1')  # 12 Product_AddDate
+
+        # BTC
+        try:
+            temp = a.find('div', {'class', 'col-3 justify-content-between mx-auto'})
+            temp2 = temp.findAll('p')
+            temp = temp2[1].text
+            BTC.append(cleanString(temp.strip()))
+        except:
+            print("BTC")
+
+        #USD ERROR get rid of $
+        try:
+            temp = a.find('div', {'class', 'col-12 justify-content-between mx-auto'}).find('i').text
+            if '$' in temp:
+                temp = temp.replace("$", "")
+            USD.append(cleanString(temp.strip()))  # 14 Product_USD_SellingPrice
+        except:
+            print("USD")
+
+        EURO.append("-1")  # 15 Product_EURO_SellingPrice
+
+        #product sold
+        try:
+            temp = a.find('div', {'class', 'col-12 mx-auto text-truncate text-center flex-fill'}).findAll('p', {'class', 'card-text mb-0'})
+            temp2 = temp[1].find('i').text
+            sold.append(cleanString(temp2.strip()))
+        except:
+            print("product sold")
+
+        qLeft.append('-1')  # 17 Product_QuantityLeft
+        shipFrom.append('-1')  # 18 Product_ShippedFrom
+        shipTo.append('-1')  # 19 Product_ShippedTo
+
+        #href
+        try:
+            temp = a.find('h5', {'class', 'card-title rounded text-truncate'}).find('a').get('href')
+            href.append(temp)  # 20 Product_Links
+        except:
+            print("href")
+
+
+    # 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)
+
+#called by the crawler to get description links on a listing page
+#@param: beautifulsoup object that is using the correct html page (listing page)
+#return: list of description links from a listing page
+def torzon_links_parser(soup):
+
+    # Returning all links that should be visited by the Crawler
+
+    href = []
+    # listing = soup.findAll('div', {"class": "card mt-1"})
+    listing = soup.find('td', {"valign": "top"}).find("table", {"border": "0"}).findAll('td', {'width': '50%'})
+
+    for a in listing:
+        bae = a.find('a',  href=True)#card-title rounded text-truncate
+        link = bae['href']
+        href.append(link)
+
+    return href