From ab8044130613dd34a060635c538ddef584f928a1 Mon Sep 17 00:00:00 2001 From: Helium Date: Wed, 14 Feb 2024 21:46:19 -0800 Subject: [PATCH] completed darkbay marketplace scraper --- MarketPlaces/DarkBay/crawler_selenium.py | 256 +++++++++++++++++++++++ MarketPlaces/DarkBay/parser.py | 209 ++++++++++++++++++ 2 files changed, 465 insertions(+) create mode 100644 MarketPlaces/DarkBay/crawler_selenium.py create mode 100644 MarketPlaces/DarkBay/parser.py diff --git a/MarketPlaces/DarkBay/crawler_selenium.py b/MarketPlaces/DarkBay/crawler_selenium.py new file mode 100644 index 0000000..46def19 --- /dev/null +++ b/MarketPlaces/DarkBay/crawler_selenium.py @@ -0,0 +1,256 @@ +__author__ = 'DarkWeb' + +''' +DarkBay 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.DarkBay.parser import darkbay_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.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 = 'DarkBay' + return name + + +# Return the base link of the website +def getFixedURL(): + url = 'http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.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/nav/ul'))) + + +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 = 'DarkBay' + 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 = [] + + # # database + # links.append('http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.onion/hacking/databases') + # scripts + links.append('http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.onion/hacking/scripts') + # malware + links.append('http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.onion/hacking/malware') + # # services + # links.append('http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.onion/hacking/services') + # ebooks + # links.append('http://darkbayx7a4sosoo4hqvoljqelgkusjlrqmt237ls6hndbplmel55oad.onion/hacking/books') + + return links + + +def crawlForum(driver): + + print("Crawling the DarkBay 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.CLASS_NAME, value='pagination') + link = link.find_element(by=By.TAG_NAME, value='span') + link = link.find_element(by=By.XPATH, value='./following-sibling::a') + link = link.get_attribute('href') + if link == "": + print('no next page') + raise NoSuchElementException + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + print("Crawling the DarkBay market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'offer' 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 'offer' not in url: + return True + return False + + +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return darkbay_links_parser(soup) + + +def crawler(): + startCrawling() diff --git a/MarketPlaces/DarkBay/parser.py b/MarketPlaces/DarkBay/parser.py new file mode 100644 index 0000000..6cc79ef --- /dev/null +++ b/MarketPlaces/DarkBay/parser.py @@ -0,0 +1,209 @@ +__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 darkbay_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 + + + + # vendor name + vendor = soup.find('div', {'class', 'vendor'}).find('a').text + + # product name + name = soup.find('h3').text + + # description + describe = soup.find('div', {'class', 'description'}).text.replace('\n', ' ') + + # category + category = soup.find('i', {'class', 'fas fa-folder'}).text + + # finding price + money = soup.find('div', {'class', 'price'}) + BTC = money.find('span', {'class', 'btc'}).text.replace('$','') + USD = money.find('span', {'class', 'usd'}).text.replace('₿','') + + if soup.find('div', {'class': 'instock many'}): + left = soup.find('div', {'class': 'instock many'}).text + if 'in stock' in left: + left.replace('in stock', '').strip() + if left == '': + left = '-1' + + # ship to and ship from + location = soup.find('dl', {'class': 'compact ships mb1'}).findAll('dd') + shipFrom = location[0].text + shipFrom = ''.join(c for c in shipFrom if c.isalnum()) + shipFrom = shipFrom.strip() + shipFrom = cleanString(shipFrom) + shipTo = location[1].text + shipTo = ''.join(c for c in shipTo if c.isalnum()) + shipTo = shipTo.strip() + + # Finding Product Image + if soup.find('div', {"class": 'product-photos'}): + image = soup.find('div', {"class": 'product-photos'}).find('img') + image = image.get('src') + image = image.split('base64,')[-1] + else: + image = "-1" + + + + # 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 darkbay_listing_parser(soup): + + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "DarkBay" # 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('div', {'class': 'path'}).findAll('a') + listing = soup.find('div', {"class": 'items'}).findAll('form', {"action": '/cart'}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + + category.append(cat[1].text) + + # Adding the url to the list of urls + link = a.find('a').get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product name + product = a.find('a').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') + if product_image is not None: + product_image = product_image.get('src') + product_image = product_image.split('base64,')[-1] + image.append(product_image) + else: + image.append('-1') + + + # vendor name + ven = a.find('div', {'class', 'vendor'}).find('a').text + ven = cleanString(ven) + vendor.append(ven) + + # find price in usd + usd = a.find('div', {'class': 'price'}).text + usd = usd.replace('$','') + USD.append(usd) + + rating_vendor.append('-1') + success.append('-1') + CVE.append('-1') + MS.append('-1') + describe.append('-1') + views.append('-1') + reviews.append('-1') + rating_item.append('-1') + addDate.append('-1') + BTC.append('-1') + EURO.append('-1') + sold.append('-1') + qLeft.append('-1') + shipFrom.append('-1') + shipTo.append('-1') + image_vendor.append('-1') + + + + + # 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 darkbay_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.find('div', {"class": "items"}).findAll('form', {'class':'item'}) + + 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