diff --git a/MarketPlaces/Abacus/.gitkeep b/MarketPlaces/Abacus/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/MarketPlaces/Abacus/crawler_selenium.py b/MarketPlaces/Abacus/crawler_selenium.py new file mode 100644 index 0000000..c929877 --- /dev/null +++ b/MarketPlaces/Abacus/crawler_selenium.py @@ -0,0 +1,312 @@ +__author__ = 'DarkWeb' + +''' +Abacus Marketplace Crawler (Selenium) +''' + +from selenium import webdriver +from selenium.common.exceptions import NoSuchElementException +from selenium.webdriver.firefox.firefox_profile import FirefoxProfile +from selenium.webdriver.firefox.firefox_binary import FirefoxBinary +from selenium.webdriver.firefox.service import Service +from selenium.webdriver.support.ui import WebDriverWait +from selenium.webdriver.support.ui import Select +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.Abacus.parser import abacus_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion' + + +def startCrawling(): + mktName = getMKTName() + driver = getAccess() + + if driver != 'down': + try: + login(driver) + crawlForum(driver) + except Exception as e: + print(driver.current_url, e) + closeDriver(driver) + + # new_parse(mktName, baseURL, True) + + +# Returns the name of the website +def getMKTName(): + name = 'Abacus' + return name + + +# Return the base link of the website +def getFixedURL(): + url = 'http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion' + return url + + +# Closes Tor Browser +def closeDriver(driver): + # global pid + # os.system("taskkill /pid " + str(pro.pid)) + # os.system("taskkill /t /f /im tor.exe") + print('Closing Tor...') + driver.close() + time.sleep(3) + return + + +# Creates FireFox 'driver' and configure its 'Profile' +# to use Tor proxy and socket +def createFFDriver(): + from MarketPlaces.Initialization.markets_mining import config + + ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path')) + + ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path')) + ff_prof.set_preference("places.history.enabled", False) + ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True) + ff_prof.set_preference("privacy.clearOnShutdown.passwords", True) + ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True) + ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True) + ff_prof.set_preference("signon.rememberSignons", False) + ff_prof.set_preference("network.cookie.lifetimePolicy", 2) + # ff_prof.set_preference("network.dns.disablePrefetch", True) + # ff_prof.set_preference("network.http.sendRefererHeader", 0) + ff_prof.set_preference("permissions.default.image", 3) + ff_prof.set_preference("browser.download.folderList", 2) + ff_prof.set_preference("browser.download.manager.showWhenStarting", False) + ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain") + ff_prof.set_preference('network.proxy.type', 1) + ff_prof.set_preference("network.proxy.socks_version", 5) + ff_prof.set_preference('network.proxy.socks', '127.0.0.1') + ff_prof.set_preference('network.proxy.socks_port', 9150) + ff_prof.set_preference('network.proxy.socks_remote_dns', True) + ff_prof.set_preference("javascript.enabled", False) + ff_prof.update_preferences() + + service = Service(config.get('TOR', 'geckodriver_path')) + + driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + + driver.maximize_window() + + return driver + + +#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down' +def getAccess(): + url = getFixedURL() + driver = createFFDriver() + try: + driver.get(url) + return driver + except: + driver.close() + return 'down' + + +def login(driver): + input("Press ENTER when CAPTCHA is complete and login page has loaded\n") + + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, '/html/body/div/div/div[1]/div/form/div[3]/input[1]'))) + + # entering username and password into input boxes + try: + usernameBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/div[1]/div/form/div[3]/input[1]') + # Username here + usernameBox.send_keys('ct1234') + passwordBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/div[1]/div/form/div[3]/input[2]') + # Password here + passwordBox.send_keys('DementedBed123-') + except: + usernameBox = driver.find_element(by=By.CSS_SELECTOR, value='input.border-solid:nth-child(2)') + # Username here + usernameBox.send_keys('ct1234') + passwordBox = driver.find_element(by=By.CSS_SELECTOR, value='input.border-solid:nth-child(4)') + # Password here + passwordBox.send_keys('DementedBed123-') + + input("Press ENTER AFTER phishing is completed (there is a captcha first and then an antiphishing check)\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/div[2]/div/div[2]'))) + + +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 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 + + +def getMKTName() -> str: + name = 'Abacus' + 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 = [] + + # botnets and malware + links.append('http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion/search?fcats[]=475756f633d0cc71f0c868bd&cats=2&s_quick=1') + # # social engineering + # links.append( + # 'http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion/search?fcats[]=1c29a89f7a4022133cab877d&cats=2&s_quick=1') + # digital + links.append( + 'http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion/search?fcats[]=475756f633d0cc71f0c868bd&cats=2&s_quick=1') + # # hacking + # links.append( + # 'http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion/search?fcats[]=a0773b3de70bdaca38acda2f&cats=2&s_quick=1') + # # carding + # links.append('http://abacuseeettcn3n2zxo7tqy5vsxhqpha2jtjqs7cgdjzl2jascr4liad.onion/search?fcats[]=1b17857dc74c11953df85c55&cats=2&s_quick=1 + + return links + + +def crawlForum(driver): + + print("Crawling the Abacus 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: + print('waiting ten seconds to avoid ddos check') + time.sleep(10) + 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: + print(itemURL) + print('waiting 5 sec to avoid ddos check') + time.sleep(5) + driver.get(itemURL) + except: + driver.refresh() + savePage(driver, driver.page_source, item) + print('waiting 20 seconds to avoid ddos check') + time.sleep(20) + driver.back() + + # comment out + break + + # # comment out + # if count == 3: + # break + + try: + chev = driver.find_element(by=By.XPATH, value='/html/body/div/div/div[2]/div/div[3]/div[4]') + a_tags = chev.find_elements(by=By.TAG_NAME, value='a') + try: + for a_tag in a_tags: + try: + temp = a_tag.find_element(by=By.CLASS_NAME, value='gg-chevron-right') + except: + temp = '' + if temp: + link = a_tag.get_attribute('href') + print(link) + if link == '#': + link = '' + break + else: + link = '' + except: + try: + a_tag = a_tags[-2].find_element(by=By.CLASS_NAME, value='gg-chevron-right').get_attribute('href') + if a_tag: + link = a_tag.get_attribute('href') + if link == '#': + link = '' + break + else: + link = '' + except: + link='' + if link == "": + raise NoSuchElementException + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + print("Crawling the Abacus market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'listing' in url: + return True + return False + + +# Returns True if the link is a listingPage link, may need to change for every website +def isListingLink(url): + if 'search' in url: + return True + return False + + +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return abacus_links_parser(soup) + + +def crawler(): + startCrawling() diff --git a/MarketPlaces/Abacus/parser.py b/MarketPlaces/Abacus/parser.py new file mode 100644 index 0000000..fe3c561 --- /dev/null +++ b/MarketPlaces/Abacus/parser.py @@ -0,0 +1,228 @@ +__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 abacus_description_parser(soup): + # Fields to be parsed + + vendor = "-1" # 0 *Vendor_Name + success = "-1" # 1 Vendor_Successful_Transactions + rating_vendor = "-1" # 2 Vendor_Rating + name = "-1" # 3 *Product_Name + describe = "-1" # 4 Product_Description + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) + category = "-1" # 7 Product_Category + views = "-1" # 8 Product_Number_Of_Views + reviews = "-1" # 9 Product_Number_Of_Reviews + rating_item = "-1" # 10 Product_Rating + addDate = "-1" # 11 Product_AddedDate + BTC = "-1" # 12 Product_BTC_SellingPrice + USD = "-1" # 13 Product_USD_SellingPrice + EURO = "-1" # 14 Product_EURO_SellingPrice + sold = "-1" # 15 Product_QuantitySold + left = "-1" # 16 Product_QuantityLeft + shipFrom = "-1" # 17 Product_ShippedFrom + shipTo = "-1" # 18 Product_ShippedTo + image = "-1" # 19 Product_Image + vendor_image = "-1" # 20 Vendor_Image + + product_info = soup.find('div', {'class': '2xl:self-start w-full h-full'}) + about_vendor = soup.find('div', {'class': 'px-0.5 py-1 flex flex-col items-center gap-2 text-[13px]'}) + + try: + ven_temp = about_vendor.find('div', {'class': 'flex items-center gap-0.5'}).find('a').text + ven_temp_list = ven_temp.split(' ') + if len(ven_temp_list) > 1: + ven_temp_list = ven_temp_list[:-1] + ven_temp = ' '.join(ven_temp_list) + vendor = cleanString(ven_temp.strip()) + except: + vendor = '-1' + print(vendor) + + success = "-1" + + try: + rating = about_vendor.find('div', {'class':'font-bold rounded px-2'}).text + rating_list = rating.split(' ') + rating = rating_list[0] + rating = rating.replace('%', '') + except: + rating = '-1' + rating_vendor = rating + print(rating_vendor) + + name = product_info.find('div', {'class': 'w-full flex gap-0.5 items-center border-solid border-0 border-border border-b group-hover:border-abacus2 text-sm font-bold justify-center 2xl:justify-start py-1 leading-tight'}) + name = cleanString(name.strip()) + try: + description = soup.find('div', {'class': 'hidden gap-2 flex-col w-0 p-3 anim anim-FadeIn'}).find('div', {'class':'text-xs w-full text-left text-black'}).text + description = cleanString(description.strip()) + except: + description = '-1' + describe = description + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) + category = "-1" # 7 Product_Category + views = "-1" # 8 Product_Number_Of_Views + reviews = "-1" # 9 Product_Number_Of_Reviews + rating_item = "-1" # 10 Product_Rating + addDate = "-1" # 11 Product_AddedDate + BTC = "-1" # 12 Product_BTC_SellingPrice + USD = "-1" # 13 Product_USD_SellingPrice + EURO = "-1" # 14 Product_EURO_SellingPrice + sold = "-1" # 15 Product_QuantitySold + left = "-1" # 16 Product_QuantityLeft + shipFrom = "-1" # 17 Product_ShippedFrom + shipTo = "-1" # 18 Product_ShippedTo + image = "-1" # 19 Product_Image + vendor_image = "-1" # 20 Vendor_Image + + + # Populating the final variable (this should be a list with all fields scraped) + row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, + BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image) + + # Sending the results + return row + + +# 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 abacus_listing_parser(soup): + + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "Abacus" # 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 + image = [] # 20 Product_Image + image_vendor = [] # 21 Vendor_Image + href = [] # 22 Product_Links + + cat = soup.find('span', {"class": "btn btn-sm btn-outline-dark w-100 active"}).text + cat = cleanString(cat).strip() + + listing = soup.find('div', {"class": 'card-body text-black text-left bg-dark'}).findAll('div', {"class": 'card mb-4 border-danger rounded-0'}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + + category.append(cat) + + # Adding the url to the list of urls + link = a.find('a', {'class': "badge badge-danger w-100 text-white"}).get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product name + product = a.find('div', {"class": 'marquee-parent'}).find('div', {"class": "marquee-child"}).text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.replace("...", "") + product = product.strip() + name.append(product) + + # Finding Product Image + product_image = a.find('img') + product_image = product_image.get('src') + product_image = product_image.split('base64,')[-1] + image.append(product_image) + + # Finding Prices + price = a.findAll('a', {"class": "text-white"})[-1].text + price = price.replace("$","") + price = price.strip() + USD.append(price) + + # Finding Item Rating + temp = a.find('small', {"class": "text-white"}) + rating = len(temp.findAll('i', {"class": "fas fa-star"})) + half_stars = len(temp.findAll('i', {'class': "fas fa-star-half-alt"})) + if half_stars > 0: + rating += 0.5 + rating_item.append(str(rating)) + + # Finding the Vendor + vendor_name = a.find('a', {"class": 'badge badge-dark w-100 text-white my-1'}).text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + image_vendor.append("-1") + + # Searching for CVE and MS categories + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if not cve: + cveValue = "-1" + else: + cee = " " + for idx in cve: + cee += (idx) + cee += " " + cee = cee.replace(',', ' ') + cee = cee.replace('\n', '') + cveValue = cee + CVE.append(cveValue) + + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + if not ms: + MSValue = "-1" + else: + me = " " + for im in ms: + me += (im) + me += " " + me = me.replace(',', ' ') + me = me.replace('\n', '') + MSValue = me + MS.append(MSValue) + + # Populate the final variable (this should be a list with all fields scraped) + return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, + reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image, image_vendor) + + +# 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 abacus_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.findAll('div', {"class": "src-listing p-1 pb-0 flex flex-col justify-between w-full rounded-md border-solid border-[1px] !border-border !bg-white hover:!bg-hover hover:!border-abacus2 !mt-0"}) + + for a in listing: + link = a.find('a', href=True).get('href') + href.append(link) + + return href \ No newline at end of file diff --git a/MarketPlaces/MGMGrand/.gitkeep b/MarketPlaces/MGMGrand/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/MarketPlaces/MGMGrand/crawler_selenium.py b/MarketPlaces/MGMGrand/crawler_selenium.py new file mode 100644 index 0000000..73d47d4 --- /dev/null +++ b/MarketPlaces/MGMGrand/crawler_selenium.py @@ -0,0 +1,277 @@ +__author__ = 'DarkWeb' + +''' +MGMGrand marketplace Crawler (Selenium) +''' + +from selenium import webdriver +from selenium.common.exceptions import NoSuchElementException +from selenium.webdriver.firefox.firefox_profile import FirefoxProfile +from selenium.webdriver.firefox.firefox_binary import FirefoxBinary +from selenium.webdriver.firefox.service import Service +from selenium.webdriver.support.ui import WebDriverWait +from selenium.webdriver.support.ui import Select +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.MGMGrand.parser import mgm_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion' + + +def startCrawling(): + mktName = getMKTName() + driver = getAccess() + + if driver != 'down': + try: + login(driver) + crawlForum(driver) + except Exception as e: + print(driver.current_url, e) + closeDriver(driver) + + new_parse(mktName, baseURL, True) + + +# Returns the name of the website +def getMKTName(): + name = 'MGMGrand' + return name + + +# Return the base link of the website +def getFixedURL(): + url = 'http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion' + return url + + +# Closes Tor Browser +def closeDriver(driver): + # global pid + # os.system("taskkill /pid " + str(pro.pid)) + # os.system("taskkill /t /f /im tor.exe") + print('Closing Tor...') + driver.close() + time.sleep(3) + return + + +# Creates FireFox 'driver' and configure its 'Profile' +# to use Tor proxy and socket +def createFFDriver(): + from MarketPlaces.Initialization.markets_mining import config + + ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path')) + + ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path')) + ff_prof.set_preference("places.history.enabled", False) + ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True) + ff_prof.set_preference("privacy.clearOnShutdown.passwords", True) + ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True) + ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True) + ff_prof.set_preference("signon.rememberSignons", False) + ff_prof.set_preference("network.cookie.lifetimePolicy", 2) + ff_prof.set_preference("network.dns.disablePrefetch", True) + ff_prof.set_preference("network.http.sendRefererHeader", 0) + ff_prof.set_preference("permissions.default.image", 3) + ff_prof.set_preference("browser.download.folderList", 2) + ff_prof.set_preference("browser.download.manager.showWhenStarting", False) + ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain") + ff_prof.set_preference('network.proxy.type', 1) + ff_prof.set_preference("network.proxy.socks_version", 5) + ff_prof.set_preference('network.proxy.socks', '127.0.0.1') + ff_prof.set_preference('network.proxy.socks_port', 9150) + ff_prof.set_preference('network.proxy.socks_remote_dns', True) + ff_prof.set_preference("javascript.enabled", False) + ff_prof.update_preferences() + + service = Service(config.get('TOR', 'geckodriver_path')) + + driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + + driver.maximize_window() + + return driver + + +#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down' +def getAccess(): + url = getFixedURL() + driver = createFFDriver() + try: + driver.get(url) + return driver + except: + driver.close() + return 'down' + + +def login(driver): + 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('blabri') + passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]') + # Password here + passwordBox.send_keys('fishowal') + + input("Press ENTER when captcha is solved and you're logged in") + + # Wait for the element to be visible + WebDriverWait(driver, 100).until( + EC.visibility_of_element_located((By.XPATH, '/html/body/div[2]/div[2]/a/span')) + ) + + # Find the element and click it + temp = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/a/span') + temp.click() + + +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 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 + + +def getMKTName() -> str: + name = 'MGMGrand' + 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 = [] + + + # Carding + links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/c54f4d30-9060-11eb-be9c-630550815967') + # # softwares and malwares + # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/6a211fa0-9062-11eb-b3bd-d7d946c69ce2') + # # social engineering tutorial + # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/5596f690-9063-11eb-9ebb-6b44dbdbc454') + # # misc services + # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/b212fe30-9063-11eb-a479-35581612f6c2') + # # hacking tutorials + # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/2ed713f0-9063-11eb-bf9c-232fd3b49a98') + return links + + +def crawlForum(driver): + + print("Crawling the MGM 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 == 4: + # break + + try: + li_tags = driver.find_element(by=By.CLASS_NAME, value='pagination mb-0').find_elements(by=By.TAG_NAME, value='li') + a_tag = li_tags[-1].find_element(by=By.TAG_NAME, value='a') + if a_tag: + try: + link = a_tag.get_attribute('href') + print(link) + except: + link = '' + if link == "": + raise NoSuchElementException + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + print("Crawling the MGMGrand market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'product' in url: + return True + return False + + +# Returns True if the link is a listingPage link, may need to change for every website +def isListingLink(url): + if 'category' in url: + return True + return False + + +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return mgm_links_parser(soup) + + +def crawler(): + startCrawling() diff --git a/MarketPlaces/MGMGrand/parser.py b/MarketPlaces/MGMGrand/parser.py new file mode 100644 index 0000000..df01556 --- /dev/null +++ b/MarketPlaces/MGMGrand/parser.py @@ -0,0 +1,250 @@ +__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 mgm_description_parser(soup): + # Fields to be parsed + + vendor = "-1" # 0 *Vendor_Name + success = "-1" # 1 Vendor_Successful_Transactions + rating_vendor = "-1" # 2 Vendor_Rating + name = "-1" # 3 *Product_Name + describe = "-1" # 4 Product_Description + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) + category = "-1" # 7 Product_Category + views = "-1" # 8 Product_Number_Of_Views + reviews = "-1" # 9 Product_Number_Of_Reviews + rating_item = "-1" # 10 Product_Rating + addDate = "-1" # 11 Product_AddedDate + BTC = "-1" # 12 Product_BTC_SellingPrice + USD = "-1" # 13 Product_USD_SellingPrice + EURO = "-1" # 14 Product_EURO_SellingPrice + sold = "-1" # 15 Product_QuantitySold + left = "-1" # 16 Product_QuantityLeft + shipFrom = "-1" # 17 Product_ShippedFrom + shipTo = "-1" # 18 Product_ShippedTo + image = "-1" # 19 Product_Image + vendor_image = "-1" # 20 Vendor_Image + + # Finding Product Name + divmb = soup.find('div', {'class': "col-md-12 my-2"}) + + name = divmb.find('span', {'class': "btn btn-sm btn-outline-dark w-100 active rounded-0"}).text + name = name.replace('\n', ' ') + name = name.replace(",", "") + name = name.strip() + + box = soup.find('div', {'class': "col-md-7"}).find('span') + box = box.findAll('span', {'class': "btn btn-mgray btn-sm w-100 active border-danger"}) + + # Finding Vendor + vendor = soup.find('a', {'class': "btn btn-sm btn-mgray my-1 w-100 text-white"}).get('href') + vendor = vendor.split('otherParty=')[-1] + vendor = cleanString(vendor).strip() + + # Finding Vendor Rating + temp = box[1] + rating_vendor = len(temp.findAll('i', {"class": "fas fa-star"})) + half_stars = len(temp.findAll('i', {'class': "fas fa-star-half-alt"})) + if half_stars > 0: + rating_vendor += 0.5 + + # Finding Successful Transactions + success = box[2].text + success = cleanNumbers(success).strip() + + box2 = soup.find('div', {"class": "col-md-4 text-center"}).find('span', {"class": "text-left"}).findAll('span') + + # Finding USD + USD = box2[0].text + USD = USD.replace('\n', '') + USD = USD.replace('$', '') + USD = USD.strip() + + # Finding Vendor Image + vendor_image = soup.find('img', {"class": 'img-fluid'}).get('src') + vendor_image = vendor_image.split('base64,')[-1] + + # Finding the Product description + temp = soup.find('div', {"class": 'row-md-12'}).find('div', {"class": 'col-md-4'}) + cardbody = temp.find('textarea', {"class": 'disabled form-control form-control-sm w-100 bg-mgray text-white rounded-0 border-danger'}) + describe = cleanString(cardbody.text).strip() + + # Finding Product Image + image = soup.find('div', {"class": 'row-md-12'}).find('div', {"class": 'col-md-4 text-center'}).find('img') + if image is not None: + image = image.get('src') + image = image.split('base64,')[-1] + else: + image = "-1" + + # Searching for CVE and MS categories + cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if cve: + CVE = " " + for idx in cve: + CVE += (idx) + CVE += " " + CVE = CVE.replace(',', ' ') + CVE = CVE.replace('\n', '') + ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}')) + if ms: + MS = " " + for im in ms: + MS += (im) + MS += " " + MS = MS.replace(',', ' ') + MS = MS.replace('\n', '') + + # Populating the final variable (this should be a list with all fields scraped) + row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, + BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image) + + # Sending the results + return row + + +# 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 mgm_listing_parser(soup): + + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "Ares" # 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 + image = [] # 20 Product_Image + image_vendor = [] # 21 Vendor_Image + href = [] # 22 Product_Links + + cat = soup.find('span', {"class": "btn btn-sm btn-outline-dark w-100 active"}).text + cat = cleanString(cat).strip() + + listing = soup.find('div', {"class": 'card-body text-black text-left bg-dark'}).findAll('div', {"class": 'card mb-4 border-danger rounded-0'}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + + category.append(cat) + + # Adding the url to the list of urls + link = a.find('a', {'class': "badge badge-danger w-100 text-white"}).get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product name + product = a.find('div', {"class": 'marquee-parent'}).find('div', {"class": "marquee-child"}).text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.replace("...", "") + product = product.strip() + name.append(product) + + # Finding Product Image + product_image = a.find('img') + product_image = product_image.get('src') + product_image = product_image.split('base64,')[-1] + image.append(product_image) + + # Finding Prices + price = a.findAll('a', {"class": "text-white"})[-1].text + price = price.replace("$","") + price = price.strip() + USD.append(price) + + # Finding Item Rating + temp = a.find('small', {"class": "text-white"}) + rating = len(temp.findAll('i', {"class": "fas fa-star"})) + half_stars = len(temp.findAll('i', {'class': "fas fa-star-half-alt"})) + if half_stars > 0: + rating += 0.5 + rating_item.append(str(rating)) + + # Finding the Vendor + vendor_name = a.find('a', {"class": 'badge badge-dark w-100 text-white my-1'}).text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + + image_vendor.append("-1") + + # Searching for CVE and MS categories + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if not cve: + cveValue = "-1" + else: + cee = " " + for idx in cve: + cee += (idx) + cee += " " + cee = cee.replace(',', ' ') + cee = cee.replace('\n', '') + cveValue = cee + CVE.append(cveValue) + + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + if not ms: + MSValue = "-1" + else: + me = " " + for im in ms: + me += (im) + me += " " + me = me.replace(',', ' ') + me = me.replace('\n', '') + MSValue = me + MS.append(MSValue) + + # Populate the final variable (this should be a list with all fields scraped) + return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, + reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image, image_vendor) + + +# 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 mgm_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.find('div', {"class": "list-products columns-3"}).find_all('div', {'class':'product-item hover-shadow'}) + + for a in listing: + bae = a.findAll('a', href=True) + + # Adding the url to the list of urls + link = bae[0].get('href') + href.append(link) + + return href \ No newline at end of file