From e39dd180901a36519e680c54b4896478b314f00b Mon Sep 17 00:00:00 2001 From: Kimtaiyo Mech Date: Sun, 25 Feb 2024 16:39:52 -0800 Subject: [PATCH 1/5] initial crawler for ZeroDay --- MarketPlaces/Initialization/marketsList.txt | 2 +- MarketPlaces/Initialization/markets_mining.py | 3 + MarketPlaces/ZeroDay/crawler_selenium.py | 284 ++++++++++++++++++ MarketPlaces/ZeroDay/parser.py | 250 +++++++++++++++ 4 files changed, 538 insertions(+), 1 deletion(-) create mode 100644 MarketPlaces/ZeroDay/crawler_selenium.py create mode 100644 MarketPlaces/ZeroDay/parser.py diff --git a/MarketPlaces/Initialization/marketsList.txt b/MarketPlaces/Initialization/marketsList.txt index f81b343..ef58f0d 100644 --- a/MarketPlaces/Initialization/marketsList.txt +++ b/MarketPlaces/Initialization/marketsList.txt @@ -1 +1 @@ -GoFish \ No newline at end of file +ZeroDay \ No newline at end of file diff --git a/MarketPlaces/Initialization/markets_mining.py b/MarketPlaces/Initialization/markets_mining.py index 15ce3ae..29f17b5 100644 --- a/MarketPlaces/Initialization/markets_mining.py +++ b/MarketPlaces/Initialization/markets_mining.py @@ -23,6 +23,7 @@ from MarketPlaces.Ares.crawler_selenium import crawler as crawlerAres from MarketPlaces.Bohemia.crawler_selenium import crawler as crawlerBohemia from MarketPlaces.TheDarkMarket.crawler_selenium import crawler as crawlerTheDarkMarket from MarketPlaces.GoFish.crawler_selenium import crawler as crawlerGoFish +from MarketPlaces.ZeroDay.crawler_selenium import crawler as crawlerZeroDay import configparser import os @@ -132,5 +133,7 @@ if __name__ == '__main__': crawlerGoFish() elif mkt == "TheDarkMarket": crawlerTheDarkMarket() + elif mkt == "ZeroDay": + crawlerZeroDay() print("\nScraping process completed!") diff --git a/MarketPlaces/ZeroDay/crawler_selenium.py b/MarketPlaces/ZeroDay/crawler_selenium.py new file mode 100644 index 0000000..5b16314 --- /dev/null +++ b/MarketPlaces/ZeroDay/crawler_selenium.py @@ -0,0 +1,284 @@ +__author__ = 'DarkWeb' + +''' +ZeroDay 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.ZeroDay.parser import zeroday_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/' + + +def startCrawling(): + mktName = getMKTName() + driver = getAccess() + + if driver != 'down': + try: + # login(driver) + agreeToTerms(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 = 'ZeroDay' + return name + + +# Return the base link of the website +def getFixedURL(): + url = 'http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.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 agreeToTerms(driver): + try: + agree_button = driver.find_element(by=By.XPATH, value='//input[@type="submit" and @name="agree" and @value="Yes, I agree"]') + agree_button.click() + except Exception as e: + print('Problem with clicking agree button', e) + +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, '//*[@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 BROKEN CIRCLE is pressed\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[6]/div[3]/div[2]/div[1]/div[1]'))) + + +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 = 'ZeroDay' + 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 = [] + + # Private category sells private exploits and vulnerabilities + + # Remote exploits + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/private/remote') + # Local exploits + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/private/local') + # Web App exploits + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/private/webapps') + # doc/poc - denial of service / proof of concept + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/private/dos') + + # Remote + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/remote') + # Local + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/local') + # Web app + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/webapps') + # dos/poc + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/dos') + # Shellcode + links.append('http://sq542reyqwagfkghieehykb6hh6ohku5irarrrbeeo5iyozdbhe5n3id.onion/shellcode') + + return links + + +def crawlForum(driver): + + print("Crawling the ZeroDay market") + + linksToCrawl = getInterestedLinks() + + i = 0 + while i < len(linksToCrawl): + link = linksToCrawl[i] + print('Crawling :', link) + try: + has_next_page = True + count = 0 + + while has_next_page: + try: + driver.get(link) + except: + driver.refresh() + html = driver.page_source + savePage(driver, html, link) + list = productPages(html) + + for item in list: + itemURL = urlparse.urljoin(baseURL, str(item)) + try: + driver.get(itemURL) + except: + driver.refresh() + savePage(driver, driver.page_source, item) + driver.back() + + # # comment out + # break + # + # comment out + # if count == 1: + # break + + try: + link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "next")]').get_attribute('href') + if link == "": + raise NoSuchElementException + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + print("Crawling the Ares market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'description' 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 zeroday_links_parser(soup) + + +def crawler(): + startCrawling() diff --git a/MarketPlaces/ZeroDay/parser.py b/MarketPlaces/ZeroDay/parser.py new file mode 100644 index 0000000..f450628 --- /dev/null +++ b/MarketPlaces/ZeroDay/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 zeroday_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 zeroday_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 zeroday_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"}) + + 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 From 13eb2aac9dd18b9dffaeabf8d3a16a5c0dcf87af Mon Sep 17 00:00:00 2001 From: loki1001 Date: Mon, 26 Feb 2024 03:10:46 -0800 Subject: [PATCH 2/5] initial 0days parser --- MarketPlaces/ZeroDay/parser.py | 282 ++++++++++++++++----------------- 1 file changed, 136 insertions(+), 146 deletions(-) diff --git a/MarketPlaces/ZeroDay/parser.py b/MarketPlaces/ZeroDay/parser.py index f450628..0ecab51 100644 --- a/MarketPlaces/ZeroDay/parser.py +++ b/MarketPlaces/ZeroDay/parser.py @@ -5,88 +5,53 @@ from MarketPlaces.Utilities.utilities import * # Here, we are importing BeautifulSoup to search through the HTML tree from bs4 import BeautifulSoup +import re # 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 zeroday_description_parser(soup): +def zerodays_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 = "-1" # 0 *Vendor_Name y + success = "-1" # 1 Vendor_Successful_Transactions n + rating_vendor = "-1" # 2 Vendor_Rating y + name = "-1" # 3 *Product_Name y + describe = "-1" # 4 Product_Description y + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) + category = "-1" # 7 Product_Category y + views = "-1" # 8 Product_Number_Of_Views y + reviews = "-1" # 9 Product_Number_Of_Reviews n + rating_item = "-1" # 10 Product_Rating n + addDate = "-1" # 11 Product_AddedDate y + BTC = "-1" # 12 Product_BTC_SellingPrice y + USD = "-1" # 13 Product_USD_SellingPrice y + EURO = "-1" # 14 Product_EURO_SellingPrice n + sold = "-1" # 15 Product_QuantitySold n + left = "-1" # 16 Product_QuantityLeft n + shipFrom = "-1" # 17 Product_ShippedFrom n + shipTo = "-1" # 18 Product_ShippedTo n + image = "-1" # 19 Product_Image n + vendor_image = "-1" # 20 Vendor_Image n - # Finding Product Name - divmb = soup.find('div', {'class': "col-md-12 my-2"}) + # Finding Vendor + div_vendor = soup.find('div', {'class': "exploit_view_table_user_content"}) + vendor = div_vendor.find('a').text.strip() - 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() + # Finding Vendor Rating (bug in their system shows standard rating) + div_rating = div_vendor.find_next_sibling('div') + rating_vendor = div_rating.find_all('div', {'class': "td"})[1].text - 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 Product Name + div_name = soup.find('div', {'class': "exploit_title"}) + name = div_name.find('h1', {'class': "YellowText"}).text + name = name.strip() - # 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" + # Finding Product description + describe = soup.find('meta', attrs={'name': "description"}).get("content") # Searching for CVE and MS categories cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) @@ -106,6 +71,31 @@ def zeroday_description_parser(soup): MS = MS.replace(',', ' ') MS = MS.replace('\n', '') + # Finding category + div_category = soup.find('div', {'class': "td"}, text="Category").find_next_sibling('div', {'class': "td"}) + category = div_category.text.strip() + + # Finding views + div_views = soup.find('div', {'class': "td"}, text="Views").find_next_sibling('div', {'class': "td"}) + views = div_views.text.replace(' ', '').strip() + + # Finding added date + div_date = soup.find('div', {'class': 'td'}, text='Date add').find_next_sibling('div', {'class': "td"}) + addDate = div_date.text.strip() + + # Finding BTC and USD/GOLD + div_price = soup.find('div', {'class': "td"}, text="Price") + price = div_price.find_next_sibling('div', {'class': "td"}).text.strip() + + if "free" in price.lower(): + BTC = 0 + USD = 0 + else: + price = ''.join(price.split()) + index = price.index('BTC') + BTC = price[:index] + USD = price[index + 3:].replace('USD', '') + # 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) @@ -113,94 +103,59 @@ def zeroday_description_parser(soup): # 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 zeroday_listing_parser(soup): +def zerodays_listing_parser(soup): # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) - mktName = "Ares" # 0 *Marketplace_Name + mktName = "0Days" # 0 *Marketplace_Name y vendor = [] # 1 *Vendor y - rating_vendor = [] # 2 Vendor_Rating - success = [] # 3 Vendor_Successful_Transactions + rating_vendor = [] # 2 Vendor_Rating y + success = [] # 3 Vendor_Successful_Transactions n 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 + describe = [] # 8 Product_Description n + views = [] # 9 Product_Number_Of_Views y + reviews = [] # 10 Product_Number_Of_Reviews n + rating_item = [] # 11 Product_Rating n + addDate = [] # 12 Product_AddDate y + BTC = [] # 13 Product_BTC_SellingPrice y 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() + EURO = [] # 15 Product_EURO_SellingPrice n + sold = [] # 16 Product_QuantitySold n + qLeft = [] # 17 Product_QuantityLeft n + shipFrom = [] # 18 Product_ShippedFrom n + shipTo = [] # 19 Product_ShippedTo n + image = [] # 20 Product_Image n + image_vendor = [] # 21 Vendor_Image n + href = [] # 22 Product_Links y - listing = soup.find('div', {"class": 'card-body text-black text-left bg-dark'}).findAll('div', {"class": 'card mb-4 border-danger rounded-0'}) + listings = soup.findAll('div', {"class": "ExploitTableContent"}) # Populating the Number of Products - nm = len(listing) + nm = len(listings) - 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() + for listing in listings: + # Finding the vendor name + vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text.strip() vendor.append(vendor_name) - image_vendor.append("-1") + # Finding the vendor rating + vendor_level_div = listing.find('div', {'class': "tips_bl"}) + vendor_level = vendor_level_div.find('div', {'class': "tips_value_big"}).text + rating_vendor.append(vendor_level) + + # Finding the product name + product_name = listing.find('h3').text.strip() + name.append(product_name) # Searching for CVE and MS categories - cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + cve = listing.findAll(text=re.compile('CVE-\d{4}-\d{4}')) if not cve: cveValue = "-1" else: @@ -213,7 +168,7 @@ def zeroday_listing_parser(soup): cveValue = cee CVE.append(cveValue) - ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + ms = listing.findAll(text=re.compile('MS\d{2}-\d{3}')) if not ms: MSValue = "-1" else: @@ -226,25 +181,60 @@ def zeroday_listing_parser(soup): MSValue = me MS.append(MSValue) + # Finding the category + category_text = listing.find_all('div', {'class': "td"})[2].text.strip() + category.append(category_text) + + # Finding the hrefs + description_link = listing.find('h3').find('a')['href'] + href.append(description_link) + + # Finding the views + views_text = listing.find_all('div', {'class': "td"})[3].text.strip() + views.append(views_text) + + # Finding the date added + date = listing.find('div', {'class': "td"}).find('a').text.strip() + addDate.append(date) + + # Finding the BTC and USD/GOLD + btc_listing = listing.find('div', {"class": 'tips_price_btc'}) + if btc_listing: + btc_price = btc_listing.text.strip().replace('Open this exploit for ', '').replace(' BTC', '') + crossed = btc_listing.find('span', {'class': "crossed"}) + if crossed: + btc_price = crossed.next_sibling.strip().replace(' BTC', '') + else: + btc_price = 0 + BTC.append(btc_price) + + usd_listing = listing.find('div', {"class": 'tips_price_1'}) + if usd_listing: + usd_price = usd_listing.text.strip().replace('Open this exploit for ', '').replace(' GOLD', '') + crossed = usd_listing.find('span', {'class': "crossed"}) + if crossed: + usd_price = crossed.next_sibling.strip().replace(' GOLD', '') + usd_price = ''.join(usd_price.replace(' ', '')) + else: + usd_price = 0 + USD.append(usd_price) + # 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 zeroday_links_parser(soup): +def zerodays_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] - listing = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"}) - - for a in listing: - bae = a.findAll('a', href=True) + listings = soup.findAll('div', {"class": "ExploitTableContent"}) + for listing in listings: # Adding the url to the list of urls - link = bae[0].get('href') - href.append(link) + description_link = listing.find('h3').find('a')['href'] + href.append(description_link) return href \ No newline at end of file From c42d89662f90a987cbadd3dd086c11994d816059 Mon Sep 17 00:00:00 2001 From: loki1001 Date: Mon, 26 Feb 2024 03:10:46 -0800 Subject: [PATCH 3/5] fixed naming of initial 0days parser --- MarketPlaces/ZeroDay/parser.py | 294 ++++++++++++++++----------------- 1 file changed, 143 insertions(+), 151 deletions(-) diff --git a/MarketPlaces/ZeroDay/parser.py b/MarketPlaces/ZeroDay/parser.py index f450628..e3a50f5 100644 --- a/MarketPlaces/ZeroDay/parser.py +++ b/MarketPlaces/ZeroDay/parser.py @@ -5,6 +5,7 @@ from MarketPlaces.Utilities.utilities import * # Here, we are importing BeautifulSoup to search through the HTML tree from bs4 import BeautifulSoup +import re # parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs @@ -14,79 +15,43 @@ from bs4 import BeautifulSoup def zeroday_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 = "-1" # 0 *Vendor_Name y + success = "-1" # 1 Vendor_Successful_Transactions n + rating_vendor = "-1" # 2 Vendor_Rating y + name = "-1" # 3 *Product_Name y + describe = "-1" # 4 Product_Description y + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) + category = "-1" # 7 Product_Category y + views = "-1" # 8 Product_Number_Of_Views y + reviews = "-1" # 9 Product_Number_Of_Reviews n + rating_item = "-1" # 10 Product_Rating n + addDate = "-1" # 11 Product_AddedDate y + BTC = "-1" # 12 Product_BTC_SellingPrice y + USD = "-1" # 13 Product_USD_SellingPrice y + EURO = "-1" # 14 Product_EURO_SellingPrice n + sold = "-1" # 15 Product_QuantitySold n + left = "-1" # 16 Product_QuantityLeft n + shipFrom = "-1" # 17 Product_ShippedFrom n + shipTo = "-1" # 18 Product_ShippedTo n + image = "-1" # 19 Product_Image n + vendor_image = "-1" # 20 Vendor_Image n - # Finding Product Name - divmb = soup.find('div', {'class': "col-md-12 my-2"}) + # Finding Vendor + div_vendor = soup.find('div', {'class': "exploit_view_table_user_content"}) + vendor = div_vendor.find('a').text.strip() + + # Finding Vendor Rating (bug in their system shows standard rating) + div_rating = div_vendor.find_next_sibling('div') + rating_vendor = div_rating.find_all('div', {'class': "td"})[1].text - name = divmb.find('span', {'class': "btn btn-sm btn-outline-dark w-100 active rounded-0"}).text - name = name.replace('\n', ' ') - name = name.replace(",", "") + # Finding Product Name + div_name = soup.find('div', {'class': "exploit_title"}) + name = div_name.find('h1', {'class': "YellowText"}).text 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" + # Finding Product description + describe = soup.find('meta', attrs={'name': "description"}).get("content") # Searching for CVE and MS categories cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) @@ -106,6 +71,31 @@ def zeroday_description_parser(soup): MS = MS.replace(',', ' ') MS = MS.replace('\n', '') + # Finding category + div_category = soup.find('div', {'class': "td"}, text="Category").find_next_sibling('div', {'class': "td"}) + category = div_category.text.strip() + + # Finding views + div_views = soup.find('div', {'class': "td"}, text="Views").find_next_sibling('div', {'class': "td"}) + views = div_views.text.replace(' ', '').strip() + + # Finding added date + div_date = soup.find('div', {'class': 'td'}, text='Date add').find_next_sibling('div', {'class': "td"}) + addDate = div_date.text.strip() + + # Finding BTC and USD/GOLD + div_price = soup.find('div', {'class': "td"}, text="Price") + price = div_price.find_next_sibling('div', {'class': "td"}).text.strip() + + if "free" in price.lower(): + BTC = 0 + USD = 0 + else: + price = ''.join(price.split()) + index = price.index('BTC') + BTC = price[:index] + USD = price[index + 3:].replace('USD', '') + # 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) @@ -119,88 +109,53 @@ def zeroday_description_parser(soup): # @param: soup object looking at html page of listing page # return: 'row' that contains a variety of lists that each hold info on the listing page def zeroday_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'}) + mktName = "0Days" # 0 *Marketplace_Name y + vendor = [] # 1 *Vendor y + rating_vendor = [] # 2 Vendor_Rating y + success = [] # 3 Vendor_Successful_Transactions n + 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 n + views = [] # 9 Product_Number_Of_Views y + reviews = [] # 10 Product_Number_Of_Reviews n + rating_item = [] # 11 Product_Rating n + addDate = [] # 12 Product_AddDate y + BTC = [] # 13 Product_BTC_SellingPrice y + USD = [] # 14 Product_USD_SellingPrice y + EURO = [] # 15 Product_EURO_SellingPrice n + sold = [] # 16 Product_QuantitySold n + qLeft = [] # 17 Product_QuantityLeft n + shipFrom = [] # 18 Product_ShippedFrom n + shipTo = [] # 19 Product_ShippedTo n + image = [] # 20 Product_Image n + image_vendor = [] # 21 Vendor_Image n + href = [] # 22 Product_Links y + + listings = soup.findAll('div', {"class": "ExploitTableContent"}) # Populating the Number of Products - nm = len(listing) + nm = len(listings) - 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() + for listing in listings: + # Finding the vendor name + vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text.strip() vendor.append(vendor_name) - image_vendor.append("-1") + # Finding the vendor rating + vendor_level_div = listing.find('div', {'class': "tips_bl"}) + vendor_level = vendor_level_div.find('div', {'class': "tips_value_big"}).text + rating_vendor.append(vendor_level) + + # Finding the product name + product_name = listing.find('h3').text.strip() + name.append(product_name) # Searching for CVE and MS categories - cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + cve = listing.findAll(text=re.compile('CVE-\d{4}-\d{4}')) if not cve: cveValue = "-1" else: @@ -213,7 +168,7 @@ def zeroday_listing_parser(soup): cveValue = cee CVE.append(cveValue) - ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + ms = listing.findAll(text=re.compile('MS\d{2}-\d{3}')) if not ms: MSValue = "-1" else: @@ -226,9 +181,48 @@ def zeroday_listing_parser(soup): MSValue = me MS.append(MSValue) + # Finding the category + category_text = listing.find_all('div', {'class': "td"})[2].text.strip() + category.append(category_text) + + # Finding the hrefs + description_link = listing.find('h3').find('a')['href'] + href.append(description_link) + + # Finding the views + views_text = listing.find_all('div', {'class': "td"})[3].text.strip() + views.append(views_text) + + # Finding the date added + date = listing.find('div', {'class': "td"}).find('a').text.strip() + addDate.append(date) + + # Finding the BTC and USD/GOLD + btc_listing = listing.find('div', {"class": 'tips_price_btc'}) + if btc_listing: + btc_price = btc_listing.text.strip().replace('Open this exploit for ', '').replace(' BTC', '') + crossed = btc_listing.find('span', {'class': "crossed"}) + if crossed: + btc_price = crossed.next_sibling.strip().replace(' BTC', '') + else: + btc_price = 0 + BTC.append(btc_price) + + usd_listing = listing.find('div', {"class": 'tips_price_1'}) + if usd_listing: + usd_price = usd_listing.text.strip().replace('Open this exploit for ', '').replace(' GOLD', '') + crossed = usd_listing.find('span', {'class': "crossed"}) + if crossed: + usd_price = crossed.next_sibling.strip().replace(' GOLD', '') + usd_price = ''.join(usd_price.replace(' ', '')) + else: + usd_price = 0 + USD.append(usd_price) + # 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) + 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 @@ -238,13 +232,11 @@ def zeroday_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] - listing = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"}) - - for a in listing: - bae = a.findAll('a', href=True) + listings = soup.findAll('div', {"class": "ExploitTableContent"}) + for listing in listings: # Adding the url to the list of urls - link = bae[0].get('href') - href.append(link) + description_link = listing.find('h3').find('a')['href'] + href.append(description_link) - return href \ No newline at end of file + return href From 2ba47f0ac8845450a8873fe7969f3ca275b98747 Mon Sep 17 00:00:00 2001 From: loki1001 Date: Mon, 26 Feb 2024 22:49:18 -0800 Subject: [PATCH 4/5] fixed naming of initial 0days parser --- MarketPlaces/Initialization/prepare_parser.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index 1901f76..a2a6279 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -25,6 +25,7 @@ from MarketPlaces.Ares.parser import * from MarketPlaces.CypherMarketplace.parser import * from MarketPlaces.WeTheNorth.parser import * from MarketPlaces.GoFish.parser import * +from MarketPlaces.ZeroDay.parser import * from MarketPlaces.Classifier.classify_product import predict @@ -160,6 +161,8 @@ def parse_listing(marketPlace, listingFile, soup, createLog, logFile): rw = wethenorth_listing_parser(soup) elif marketPlace == "GoFish": rw = gofish_listing_parser(soup) + elif marketPlace == "ZeroDay": + rw = zeroday_listing_parser() else: print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!") raise Exception @@ -214,6 +217,8 @@ def parse_description(marketPlace, descriptionFile, soup, createLog, logFile): rmm = wethenorth_description_parser(soup) elif marketPlace == "GoFish": rmm = gofish_description_parser(soup) + elif marketPlace == "ZeroDay": + rmm = zeroday_description_parser(soup) else: print("MISSING CALL TO DESCRIPTION PARSER IN PREPARE_PARSER.PY!") raise Exception From fa8cb71d3719da25a934fc24dba1c2226433fb7b Mon Sep 17 00:00:00 2001 From: Kimtaiyo Mech Date: Tue, 27 Feb 2024 12:31:41 -0800 Subject: [PATCH 5/5] minor naming fix and used cleanString and cleanNumbers --- MarketPlaces/Initialization/prepare_parser.py | 2 +- MarketPlaces/ZeroDay/parser.py | 28 +++++++++++++------ 2 files changed, 21 insertions(+), 9 deletions(-) diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index a2a6279..a5a8d2c 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -162,7 +162,7 @@ def parse_listing(marketPlace, listingFile, soup, createLog, logFile): elif marketPlace == "GoFish": rw = gofish_listing_parser(soup) elif marketPlace == "ZeroDay": - rw = zeroday_listing_parser() + rw = zeroday_listing_parser(soup) else: print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!") raise Exception diff --git a/MarketPlaces/ZeroDay/parser.py b/MarketPlaces/ZeroDay/parser.py index e3a50f5..7caafbe 100644 --- a/MarketPlaces/ZeroDay/parser.py +++ b/MarketPlaces/ZeroDay/parser.py @@ -39,19 +39,22 @@ def zeroday_description_parser(soup): # Finding Vendor div_vendor = soup.find('div', {'class': "exploit_view_table_user_content"}) - vendor = div_vendor.find('a').text.strip() + vendor = div_vendor.find('a').text + vendor = cleanString(vendor).strip() # Finding Vendor Rating (bug in their system shows standard rating) div_rating = div_vendor.find_next_sibling('div') rating_vendor = div_rating.find_all('div', {'class': "td"})[1].text + rating_vendor = cleanNumbers(rating_vendor).strip() # Finding Product Name div_name = soup.find('div', {'class': "exploit_title"}) name = div_name.find('h1', {'class': "YellowText"}).text - name = name.strip() + name = cleanString(name).strip() # Finding Product description describe = soup.find('meta', attrs={'name': "description"}).get("content") + describe = cleanString(describe).strip() # Searching for CVE and MS categories cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) @@ -62,6 +65,7 @@ def zeroday_description_parser(soup): CVE += " " CVE = CVE.replace(',', ' ') CVE = CVE.replace('\n', '') + CVE = CVE.replace('\t', '') ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}')) if ms: MS = " " @@ -73,7 +77,8 @@ def zeroday_description_parser(soup): # Finding category div_category = soup.find('div', {'class': "td"}, text="Category").find_next_sibling('div', {'class': "td"}) - category = div_category.text.strip() + category = div_category.text + category = cleanString(category).strip() # Finding views div_views = soup.find('div', {'class': "td"}, text="Views").find_next_sibling('div', {'class': "td"}) @@ -82,6 +87,7 @@ def zeroday_description_parser(soup): # Finding added date div_date = soup.find('div', {'class': 'td'}, text='Date add').find_next_sibling('div', {'class': "td"}) addDate = div_date.text.strip() + # addDate = datetime.strptime(addDate, "%d-%m-%Y") # Finding BTC and USD/GOLD div_price = soup.find('div', {'class': "td"}, text="Price") @@ -111,7 +117,7 @@ def zeroday_description_parser(soup): def zeroday_listing_parser(soup): # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) - mktName = "0Days" # 0 *Marketplace_Name y + mktName = "ZeroDay" # 0 *Marketplace_Name y vendor = [] # 1 *Vendor y rating_vendor = [] # 2 Vendor_Rating y success = [] # 3 Vendor_Successful_Transactions n @@ -142,16 +148,19 @@ def zeroday_listing_parser(soup): for listing in listings: # Finding the vendor name - vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text.strip() + vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text + vendor_name = cleanString(vendor_name).strip() vendor.append(vendor_name) # Finding the vendor rating vendor_level_div = listing.find('div', {'class': "tips_bl"}) vendor_level = vendor_level_div.find('div', {'class': "tips_value_big"}).text + vendor_level = cleanNumbers(vendor_level) rating_vendor.append(vendor_level) # Finding the product name - product_name = listing.find('h3').text.strip() + product_name = listing.find('h3').text + product_name = cleanString(product_name).strip() name.append(product_name) # Searching for CVE and MS categories @@ -165,6 +174,7 @@ def zeroday_listing_parser(soup): cee += " " cee = cee.replace(',', ' ') cee = cee.replace('\n', '') + cee = cee.replace('\t', '') cveValue = cee CVE.append(cveValue) @@ -182,7 +192,8 @@ def zeroday_listing_parser(soup): MS.append(MSValue) # Finding the category - category_text = listing.find_all('div', {'class': "td"})[2].text.strip() + category_text = listing.find_all('div', {'class': "td"})[2].text + category_text = cleanString(category_text).strip() category.append(category_text) # Finding the hrefs @@ -190,11 +201,12 @@ def zeroday_listing_parser(soup): href.append(description_link) # Finding the views - views_text = listing.find_all('div', {'class': "td"})[3].text.strip() + views_text = listing.find_all('div', {'class': "td"})[3].text.replace(' ', '').strip() views.append(views_text) # Finding the date added date = listing.find('div', {'class': "td"}).find('a').text.strip() + # date = datetime.strptime(date, "%d-%m-%Y") addDate.append(date) # Finding the BTC and USD/GOLD