From bcf6ed0b7bea17f684e76ecb682e83d4856b9f34 Mon Sep 17 00:00:00 2001 From: Helium Date: Thu, 20 Jul 2023 16:15:42 -0700 Subject: [PATCH] completed lionmarketplace scraper --- MarketPlaces/Initialization/marketsList.txt | 2 +- MarketPlaces/Initialization/prepare_parser.py | 5 + .../LionMarketplace/crawler_selenium.py | 36 +- MarketPlaces/LionMarketplace/parser.py | 471 +++++++++--------- setup.ini | 8 +- 5 files changed, 257 insertions(+), 265 deletions(-) diff --git a/MarketPlaces/Initialization/marketsList.txt b/MarketPlaces/Initialization/marketsList.txt index e7488f3..356649b 100644 --- a/MarketPlaces/Initialization/marketsList.txt +++ b/MarketPlaces/Initialization/marketsList.txt @@ -1 +1 @@ -DigitalThriftShop \ No newline at end of file +LionMarketplace \ No newline at end of file diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index f2ff464..21663fb 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -15,6 +15,7 @@ from MarketPlaces.TorBay.parser import * from MarketPlaces.M00nkeyMarket.parser import * from MarketPlaces.DarkMatter.parser import * from MarketPlaces.DigitalThriftShop.parser import * +from MarketPlaces.LionMarketplace.parser import * from MarketPlaces.Classifier.classify_product import predict @@ -163,6 +164,8 @@ def new_parse(marketPlace, url, createLog): rmm = darkmatter_description_parser(soup) elif marketPlace == "DigitalThriftShop": rmm = digitalThriftShop_description_parser(soup) + elif marketPlace == "LionMarketplace": + rmm = lionmarketplace_description_parser(soup) # key = u"Pr:" + rmm[0].upper()[:desc_lim1] + u" Vendor:" + rmm[13].upper()[:desc_lim2] key = u"Url:" + os.path.basename(line2).replace(".html", "") @@ -227,6 +230,8 @@ def new_parse(marketPlace, url, createLog): rw = darkmatter_listing_parser(soup) elif marketPlace == "DigitalThriftShop": rw = digitalThriftShop_listing_parser(soup) + elif marketPlace == "LionMarketplace": + rw = lionmarketplace_listing_parser(soup) else: parseError = True diff --git a/MarketPlaces/LionMarketplace/crawler_selenium.py b/MarketPlaces/LionMarketplace/crawler_selenium.py index d969235..d6a613b 100644 --- a/MarketPlaces/LionMarketplace/crawler_selenium.py +++ b/MarketPlaces/LionMarketplace/crawler_selenium.py @@ -32,7 +32,7 @@ baseURL = 'http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion #acts like the main method for the crawler, another function at the end of this code calls this function later def startCrawling(): opentor() - # mktName = getMKTName() + mktName = getMKTName() driver = getAccess() if driver != 'down': @@ -43,7 +43,7 @@ def startCrawling(): print(driver.current_url, e) closetor(driver) - # new_parse(forumName, baseURL, False) + new_parse(mktName, baseURL, False) # Opens Tor Browser @@ -187,20 +187,12 @@ def getInterestedLinks(): # Software/Malware links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/16') - # # Carding - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/20') - # # Hacker for hire - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/0b19f3a0-c7e8-11ec-997b-0dcb6b05ce1d') - # # Phishing - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/18098bb0-c7e8-11ec-95e9-45b5e8898cbd') - # # Ransomware - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/ce72cee0-c7e7-11ec-a86b-c1ff2d3b2020') - # # Exploits - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/e26387c0-c7e7-11ec-a708-ab6dc5117763') - # # Spamming and Anti-Captcha - # links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/f08a9380-c7e7-11ec-918c-ffef7c670c97') - # hacked accounts - #links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/fd47b4a0-c7e7-11ec-937b-61246c4b12b3') + # Carding + links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/20') + # Hacking + links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/ba142ac0-c7e7-11ec-9bd1-fdd89c3d3f91') + # tutorial + links.append('http://lionznqc2hg2wsp5vgruqait4cpknihwlje6hkjyi52lcl5ivyf7bcad.onion/category/19') return links @@ -239,12 +231,12 @@ def crawlForum(driver): savePage(driver.page_source, item) driver.back() - # comment out - break - - # comment out - if count == 1: - break + # # comment out + # break + # + # # comment out + # if count == 1: + # break try: link = driver.find_element(by=By.XPATH, value= diff --git a/MarketPlaces/LionMarketplace/parser.py b/MarketPlaces/LionMarketplace/parser.py index 61ee0de..726cc63 100644 --- a/MarketPlaces/LionMarketplace/parser.py +++ b/MarketPlaces/LionMarketplace/parser.py @@ -11,133 +11,144 @@ from bs4 import BeautifulSoup #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 darkfox_description_parser(soup): - +def lionmarketplace_description_parser(soup): # Fields to be parsed + vendor = "-1" # 0 *Vendor_Name + success = "-1" # 1 Vendor_Successful_Transactions + rating_vendor = "-1" # 2 Vendor_Rating + name = "-1" # 3 *Product_Name + describe = "-1" # 4 Product_Description + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about that much + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) dont worry about that much + category = "-1" # 7 Product_Category + views = "-1" # 8 Product_Number_Of_Views + reviews = "-1" # 9 Product_Number_Of_Reviews + rating_item = "-1" # 10 Product_Rating + addDate = "-1" # 11 Product_AddedDate + BTC = "-1" # 12 Product_BTC_SellingPrice + USD = "-1" # 13 Product_USD_SellingPrice + EURO = "-1" # 14 Product_EURO_SellingPrice + sold = "-1" # 15 Product_QuantitySold + left = "-1" # 16 Product_QuantityLeft + shipFrom = "-1" # 17 Product_ShippedFrom + shipTo = "-1" # 18 Product_ShippedTo + + # vendor name + try: + temp = soup.find('div', {'class': 'btn-group'}).find('a').text + vendor = (cleanString(temp.strip())) + except: + print('vendor') + vendor = "-1" + + # table with info + table = soup.find('table', {'class', 'table border-0 text-left table-borderless'}) + rows = table.findAll('tr') + + # successful transaction + success = "-1" + + # vendor rating 5 + rating_vendor = '-1' + + + # product name + try: + temp = soup.find('div', {'class', 'row'}).find('h2').text + name = (cleanString(temp.strip())) + except: + name = '-1' + print('product name') + + # product description + try: + temp = soup.find('div', {'class': "mt-4"}).findAll('p') + temp = temp[1].text + if "\n" in temp: + temp = temp.replace("\n", " ") + temp = temp.replace("\r", " ") + describe = cleanString(temp.strip()) + except: + describe="-1" + print('describe') + + CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about that much + MS = "-1" # 6 Product_MS_Classification (Microsoft Security) dont worry about that much + + # product category + try: + temp = rows[1].find('strong').text + category = cleanString(temp.strip()) + except: + category = "-1" + print('category') + + # product number of views + views = "-1" + reviews = "-1" # 9 Product_Number_Of_Reviews + rating_item = "-1" # 10 Product_Rating + addDate = "-1" # 11 Product_AddedDate + # BTC selling price box box-rounded mt-2 + BTC = "-1" + + # USD selling price + try: + temp = rows[2].find('strong').text + if " $" in temp: + temp = temp.replace(" $", "") + elif "$" in temp: + temp = temp.replace("$", "") + USD = cleanString((temp.strip())) + except: + try: + temp = soup.find('li').find('strong').text + if " $" in temp: + temp = temp.replace(" $", "") + elif "$" in temp: + temp = temp.replace("$", "") + USD = cleanString((temp.strip())) + except: + print("USD") + + EURO = "-1" # 14 Product_EURO_SellingPrice + + # product sold + try: + if (len(rows) <= 5): + temp = rows[4].find('td').text + string = cleanString(temp) + if (string == 'Left/Sold'): + temp = rows[4].findAll('td') + temp = temp[1].findAll('span') + + # left + temp2 = temp[1].text + temp3 = temp[1].text + + if(" items" in temp2): + temp2 = temp2.replace(" items", "") + if(" items" in temp3): + temp3 = temp3.replace(" items", "") + + sold = (cleanString(temp2.strip())) + left = cleanString(temp3.strip()) + else: + sold = '-1' + left = "-1" + else: + sold = '-1' + left = "-1" + except: + print("success") + sold = '-1' + left = "-1" - name = "-1" # 0 Product_Name - describe = "-1" # 1 Product_Description - lastSeen = "-1" # 2 Product_LastViewDate - rules = "-1" # 3 NOT USED ... - CVE = "-1" # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures) - MS = "-1" # 5 Product_MS_Classification (Microsoft Security) - review = "-1" # 6 Product_Number_Of_Reviews - category = "-1" # 7 Product_Category - shipFrom = "-1" # 8 Product_ShippedFrom - shipTo = "-1" # 9 Product_ShippedTo - left = "-1" # 10 Product_QuantityLeft - escrow = "-1" # 11 Vendor_Warranty - terms = "-1" # 12 Vendor_TermsAndConditions - vendor = "-1" # 13 Vendor_Name - sold = "-1" # 14 Product_QuantitySold - addDate = "-1" # 15 Product_AddedDate - available = "-1" # 16 NOT USED ... - endDate = "-1" # 17 NOT USED ... - BTC = "-1" # 18 Product_BTC_SellingPrice - USD = "-1" # 19 Product_USD_SellingPrice - rating = "-1" # 20 Vendor_Rating - success = "-1" # 21 Vendor_Successful_Transactions - EURO = "-1" # 22 Product_EURO_SellingPrice - - # Finding Product Name - name = soup.find('h1').text - name = name.replace('\n', ' ') - name = name.replace(",", "") - name = name.strip() - - # Finding Vendor - vendor = soup.find('h3').find('a').text.strip() - - # Finding Vendor Rating - rating = soup.find('span', {'class': "tag is-dark"}).text.strip() - - # Finding Successful Transactions - success = soup.find('h3').text - success = success.replace("Vendor: ", "") - success = success.replace(vendor, "") - success = success.replace("(", "") - success = success.replace(")", "") - success = success.strip() - - bae = soup.find('div', {'class': "box"}).find_all('ul') - - # Finding Prices - USD = bae[1].find('strong').text.strip() - - li = bae[2].find_all('li') - - # Finding Escrow - escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip() - - # Finding the Product Category - category = li[1].find('span', {'class': "tag is-dark"}).text.strip() - - # Finding the Product Quantity Available - left = li[3].find('span', {'class': "tag is-dark"}).text.strip() - - # Finding Number Sold - sold = li[4].find('span', {'class': "tag is-dark"}).text.strip() - - li = bae[3].find_all('li') - - # Finding Shipment Information (Origin) - if "Ships from:" in li[-2].text: - shipFrom = li[-2].text - shipFrom = shipFrom.replace("Ships from: ", "") - # shipFrom = shipFrom.replace(",", "") - shipFrom = shipFrom.strip() - - # Finding Shipment Information (Destination) - shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text - shipTo = shipTo.replace("Ships to: ", "") - shipTo = shipTo.strip() - if "certain countries" in shipTo: - countries = "" - tags = li[-1].find_all('span', {'class': "tag"}) - for tag in tags: - country = tag.text.strip() - countries += country + ", " - shipTo = countries.strip(", ") - - # Finding the Product description - describe = soup.find('div', {'class': "pre-line"}).text - describe = describe.replace("\n", " ") - describe = describe.strip() - - '''# Finding the Number of Product Reviews - tag = soup.findAll(text=re.compile('Reviews')) - for index in tag: - reviews = index - par = reviews.find('(') - if par >=0: - reviews = reviews.replace("Reviews (","") - reviews = reviews.replace(")","") - reviews = reviews.split(",") - review = str(abs(int(reviews[0])) + abs(int(reviews[1]))) - else : - review = "-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', '') + shipFrom = "-1" # 17 Product_ShippedFrom + shipTo = "-1" # 18 Product_ShippedTo # Populating the final variable (this should be a list with all fields scraped) - row = (name, describe, lastSeen, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor, - sold, addDate, available, endDate, BTC, USD, rating, success, EURO) + row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, + BTC, USD, EURO, sold, left, shipFrom, shipTo) # Sending the results return row @@ -147,130 +158,114 @@ def darkfox_description_parser(soup): #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 darkfox_listing_parser(soup): - +def lionmarketplace_listing_parser(soup): # Fields to be parsed - nm = 0 # Total_Products (Should be Integer) - mktName = "DarkFox" # 0 Marketplace_Name - name = [] # 1 Product_Name - CVE = [] # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures) - MS = [] # 3 Product_MS_Classification (Microsoft Security) - category = [] # 4 Product_Category - describe = [] # 5 Product_Description - escrow = [] # 6 Vendor_Warranty - views = [] # 7 Product_Number_Of_Views - reviews = [] # 8 Product_Number_Of_Reviews - addDate = [] # 9 Product_AddDate - lastSeen = [] # 10 Product_LastViewDate - BTC = [] # 11 Product_BTC_SellingPrice - USD = [] # 12 Product_USD_SellingPrice - EURO = [] # 13 Product_EURO_SellingPrice - sold = [] # 14 Product_QuantitySold - qLeft =[] # 15 Product_QuantityLeft - shipFrom = [] # 16 Product_ShippedFrom - shipTo = [] # 17 Product_ShippedTo - vendor = [] # 18 Vendor - rating = [] # 19 Vendor_Rating - success = [] # 20 Vendor_Successful_Transactions - href = [] # 23 Product_Links (Urls) - - listing = soup.findAll('div', {"class": "card"}) + nm = 0 # *Total_Products (Should be Integer) + mktName = "M00nkeyMarket" # 0 *Marketplace_Name + vendor = [] # 1 *Vendor y + rating_vendor = [] # 2 Vendor_Rating + success = [] # 3 Vendor_Successful_Transactions + name = [] # 4 *Product_Name y + CVE = [] # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about this + MS = [] # 6 Product_MS_Classification (Microsoft Security) dont worry about this + category = [] # 7 Product_Category y + describe = [] # 8 Product_Description + views = [] # 9 Product_Number_Of_Views + reviews = [] # 10 Product_Number_Of_Reviews + rating_item = [] # 11 Product_Rating + addDate = [] # 12 Product_AddDate + BTC = [] # 13 Product_BTC_SellingPrice + USD = [] # 14 Product_USD_SellingPrice y + EURO = [] # 15 Product_EURO_SellingPrice + sold = [] # 16 Product_QuantitySold + qLeft = [] # 17 Product_QuantityLeft + shipFrom = [] # 18 Product_ShippedFrom + shipTo = [] # 19 Product_ShippedTo + href = [] # 20 Product_Links + + listing = soup.findAll('div', {"class": "card-body"}) # Populating the Number of Products nm = len(listing) for a in listing: - bae = a.findAll('a', href=True) - # Adding the url to the list of urls - link = bae[0].get('href') - link = cleanLink(link) - href.append(link) - - # Finding the Product - product = bae[1].find('p').text - product = product.replace('\n', ' ') - product = product.replace(",", "") - product = product.replace("...", "") - product = product.strip() - name.append(product) - - bae = a.find('div', {'class': "media-content"}).find('div').find_all('div') - - if len(bae) >= 5: - # Finding Prices - price = bae[0].text - ud = price.replace(" USD", " ") - # u = ud.replace("$","") - u = ud.replace(",", "") - u = u.strip() - USD.append(u) - # bc = (prc[1]).strip(' BTC') - # BTC.append(bc) - - # Finding the Vendor - vendor_name = bae[1].find('a').text - vendor_name = vendor_name.replace(",", "") - vendor_name = vendor_name.strip() - vendor.append(vendor_name) - - # Finding the Category - cat = bae[2].find('small').text - cat = cat.replace("Category: ", "") - cat = cat.replace(",", "") - cat = cat.strip() - category.append(cat) - - # Finding Number Sold and Quantity Left - num = bae[3].text - num = num.replace("Sold: ", "") - num = num.strip() - sold.append(num) - - quant = bae[4].find('small').text - quant = quant.replace("In stock: ", "") - quant = quant.strip() - qLeft.append(quant) - - # Finding Successful Transactions - freq = bae[1].text - freq = freq.replace(vendor_name, "") - freq = re.sub(r'Vendor Level \d+', "", freq) - freq = freq.replace("(", "") - freq = freq.replace(")", "") - freq = freq.strip() - success.append(freq) - - # 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) + row = a.findAll('p') + # vendor + try: + temp = row[3].text + vendor.append(cleanString(temp.strip())) + except: + vendor.append("-1") + print('vendor') + + # vendor rating + rating_vendor.append("-1") + + # successful transactions CHECK AGAIN HERE + success.append("-1") + + # product name + try: + temp = a.find('a').text + name.append(cleanString(temp.strip())) + except: + name.append("-1") + print('product name') + + CVE.append('-1') + MS.append('-1') + + # product category + try: + temp = row[2].text + if "Category: " in temp: + temp = temp.replace("Category: ", "") + category.append(cleanString(temp.strip())) + + except: + print("Error in product category") + + describe.append('-1') + + # product views + views.append("-1") + reviews.append('-1') # 10 Product_Number_Of_Reviews + rating_item.append('-1') # 11 Product_Rating + addDate.append('-1') # 12 Product_AddDate + + # BTC + BTC.append('-1') + + # USD + try: + temp = row[0].find('strong').text + if ' $' in temp: + temp = temp.replace(" $", "") + USD.append(cleanString(temp.strip())) # 14 Product_USD_SellingPrice + except: + print("USD") + USD.append("-1") + + EURO.append("-1") # 15 Product_EURO_SellingPrice + + # product sold + sold.append("-1") + + qLeft.append('-1') # 17 Product_QuantityLeft + shipFrom.append('-1') # 18 Product_ShippedFrom + shipTo.append('-1') # 19 Product_ShippedTo + + # href + try: + temp = a.find('a').get('href') + href.append(temp) + except: + print('product name') # Populate the final variable (this should be a list with all fields scraped) - return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen, - BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href) + return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, + reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href) #called by the crawler to get description links on a listing page diff --git a/setup.ini b/setup.ini index 3bebcab..641d3f1 100644 --- a/setup.ini +++ b/setup.ini @@ -1,11 +1,11 @@ [TOR] -firefox_binary_path = C:\Users\minhkhoitran\Desktop\Tor Browser\Browser\firefox.exe -firefox_profile_path = C:\Users\minhkhoitran\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default -geckodriver_path = C:\nsf-reu\dw_pipeline_test\selenium\geckodriver.exe +firefox_binary_path = C:\\Users\\Helium\\Desktop\\Tor Browser\\Browser\\firefox.exe +firefox_profile_path = C:\\Users\\Helium\\Desktop\\Tor Browser\\Browser\\TorBrowser\\Data\\Browser\\profile.default +geckodriver_path = C:\\Users\\Helium\\PycharmProjects\\dw_pipeline_test\\selenium\\geckodriver.exe [Project] -project_directory = C:\nsf-reu\dw_pipeline_test +project_directory = C:\\Users\\Helium\\PycharmProjects\\dw_pipeline_test shared_folder = \\VBoxSvr\\Shared [PostgreSQL]