From db93632843bc3705e5958a393eb3922c3aed7d13 Mon Sep 17 00:00:00 2001 From: Joshua Date: Thu, 13 Jul 2023 19:59:40 -0700 Subject: [PATCH 1/4] updated utilities.py to fix bug with clean_html() --- .idea/DW_Pipeline_Test.iml | 2 +- .idea/misc.xml | 2 +- Forums/Utilities/utilities.py | 2 +- MarketPlaces/Utilities/utilities.py | 2 +- MarketPlaces/ViceCity/crawler_selenium.py | 0 MarketPlaces/ViceCity/parser.py | 232 ++++++++++++++++++++++ 6 files changed, 236 insertions(+), 4 deletions(-) create mode 100644 MarketPlaces/ViceCity/crawler_selenium.py create mode 100644 MarketPlaces/ViceCity/parser.py diff --git a/.idea/DW_Pipeline_Test.iml b/.idea/DW_Pipeline_Test.iml index b4b832d..c554b68 100644 --- a/.idea/DW_Pipeline_Test.iml +++ b/.idea/DW_Pipeline_Test.iml @@ -2,7 +2,7 @@ - + diff --git a/.idea/misc.xml b/.idea/misc.xml index baf04e9..91bfa41 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/Forums/Utilities/utilities.py b/Forums/Utilities/utilities.py index d8ca9eb..2196307 100644 --- a/Forums/Utilities/utilities.py +++ b/Forums/Utilities/utilities.py @@ -292,7 +292,7 @@ def cleanHTML(html): clean_html = re.sub(r"", "", clean_html) # image and JavaScript - clean_html = re.sub(r"", "", clean_html) + clean_html = re.sub(r"]*style=\"[^\"]*background-image.*?>", "", clean_html) return clean_html diff --git a/MarketPlaces/Utilities/utilities.py b/MarketPlaces/Utilities/utilities.py index 50bbf89..b1ecba4 100644 --- a/MarketPlaces/Utilities/utilities.py +++ b/MarketPlaces/Utilities/utilities.py @@ -315,7 +315,7 @@ def cleanHTML(html): clean_html = re.sub(r"", "", clean_html) # image and JavaScript - clean_html = re.sub(r"", "", clean_html) + clean_html = re.sub(r"]*style=\"[^\"]*background-image.*?>", "", clean_html) return clean_html diff --git a/MarketPlaces/ViceCity/crawler_selenium.py b/MarketPlaces/ViceCity/crawler_selenium.py new file mode 100644 index 0000000..e69de29 diff --git a/MarketPlaces/ViceCity/parser.py b/MarketPlaces/ViceCity/parser.py new file mode 100644 index 0000000..2508b2d --- /dev/null +++ b/MarketPlaces/ViceCity/parser.py @@ -0,0 +1,232 @@ +__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 + + +# This is the method to parse the Description Pages (one page to each Product in the Listing Pages) +def tor2door_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 + + bae = soup.find('div', {'class': "col-9"}) + + # Finding Product Name + name = bae.find('h2').text + name = name.replace('\n', ' ') + name = name.replace(",", "") + name = name.strip() + + mb = bae.findAll('div', {"class": "mb-1"}) + + # Finding Vendor + vendor = mb[0].text + vendor = vendor.replace(",", "") + vendor = vendor.replace("Sold by:", "") + vendor = vendor.strip() + + # # Finding Vendor Rating + # full_stars = bae[2].find_all('i', {'class': "fas fa-star"}) + # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"}) + # rating = len(full_stars) + (0.5 if half_star is not None else 0) + + # Finding Quantity Sold and Left + temp = mb[4].text.split(',') + + sold = temp[0].replace("sold", "") + sold = sold.strip() + + left = temp[1].replace("in stock", "") + left = left.strip() + + # Finding USD + USD = bae.find('div', {"class": "h3 text-secondary"}).text + USD = USD.replace("$", "") + USD = USD.strip() + + # Finding BTC + temp = bae.find('div', {"class": "small"}).text.split("BTC") + + BTC = temp[0].strip() + + # shipping_info = bae[4].text + # if "Digital" not in shipping_info: + # shipping_info = shipping_info.split(" ") + # + # # Finding Shipment Information (Origin) + # shipFrom = shipping_info[0].strip() + # + # # Finding Shipment Information (Destination) + # shipTo = shipping_info[1].strip() + + # Finding the Product description + describe = bae.find('div', {"class": "card border-top-0"}).text + describe = describe.replace("\n", " ") + describe = describe.replace("\r", " ") + describe = describe.strip() + + # 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) + + # Sending the results + return row + + +# This is the method to parse the Listing Pages +def tor2door_listing_parser(soup): + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "Tor2door" # 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) + MS = [] # 6 Product_MS_Classification (Microsoft Security) + 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 product-card mb-3"}) + + # Populating the Number of Products + nm = len(listing) + + # Finding Category + cat = soup.find("div", {"class": "col-9"}) + cat = cat.find("h2").text + cat = cat.replace("Category: ", "") + cat = cat.replace(",", "") + cat = cat.strip() + + for card in listing: + category.append(cat) + + bae = card.findAll('a') + + # Adding the url to the list of urls + link = bae[0].get('href') + href.append(link) + + # Finding Product Name + product = bae[1].text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.strip() + name.append(product) + + # Finding Vendor + vendor_name = bae[2].text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + + # Finding USD + usd = card.find('div', {"class": "mb-1"}).text + usd = usd.replace("$", "") + usd = usd.strip() + USD.append(usd) + + # Finding Reviews + num = card.find("span", {"class": "rate-count"}).text + num = num.replace("(", "") + num = num.replace("review)", "") + num = num.replace("reviews)", "") + num = num.strip() + reviews.append(num) + + # Searching for CVE and MS categories + cve = card.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 = card.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) + + +def tor2door_links_parser(soup): + # Returning all links that should be visited by the Crawler + href = [] + + listing = soup.findAll('div', {"class": "card product-card mb-3"}) + + for div in listing: + link = div.find('a')['href'] + href.append(link) + + return href \ No newline at end of file From bd5a05ffb46afded758c48989bcb8e5e631c17a6 Mon Sep 17 00:00:00 2001 From: Joshua Date: Thu, 13 Jul 2023 20:16:48 -0700 Subject: [PATCH 2/4] finished crawler and parser --- MarketPlaces/Initialization/markets_mining.py | 3 + MarketPlaces/Initialization/prepare_parser.py | 7 +- MarketPlaces/ViceCity/crawler_selenium.py | 333 ++++++++++++++++++ MarketPlaces/ViceCity/parser.py | 166 +++++---- 4 files changed, 435 insertions(+), 74 deletions(-) diff --git a/MarketPlaces/Initialization/markets_mining.py b/MarketPlaces/Initialization/markets_mining.py index 664454a..1c533ad 100644 --- a/MarketPlaces/Initialization/markets_mining.py +++ b/MarketPlaces/Initialization/markets_mining.py @@ -20,6 +20,7 @@ from MarketPlaces.Apocalypse.crawler_selenium import crawler as crawlerApocalyps from MarketPlaces.CityMarket.crawler_selenium import crawler as crawlerCityMarket from MarketPlaces.DarkMatter.crawler_selenium import crawler as crawlerDarkMatter from MarketPlaces.M00nkeyMarket.crawler_selenium import crawler as crawlerM00nkeyMarket +from MarketPlaces.ViceCity.crawler_selenium import crawler as crawlerViceCity import configparser import time @@ -106,6 +107,8 @@ if __name__ == '__main__': crawlerDarkMatter() elif mkt == "M00nkeyMarket": crawlerM00nkeyMarket() + elif mkt == "ViceCity": + crawlerViceCity() diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index 4d5508b..5739f30 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -10,6 +10,7 @@ from MarketPlaces.Tor2door.parser import * from MarketPlaces.Apocalypse.parser import * from MarketPlaces.ThiefWorld.parser import * from MarketPlaces.AnonymousMarketplace.parser import * +from MarketPlaces.ViceCity.parser import * from MarketPlaces.Classifier.classify_product import predict @@ -148,6 +149,8 @@ def new_parse(marketPlace, url, createLog): rmm = thiefWorld_description_parser(soup) elif marketPlace =="AnonymousMarketplace": rmm = anonymousMarketplace_description_parser(soup) + elif marketPlace == "ViceCity": + rmm = vicecity_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", "") @@ -200,7 +203,9 @@ def new_parse(marketPlace, url, createLog): elif marketPlace == "ThiefWorld": rw = thiefWorld_listing_parser(soup) elif marketPlace == "AnonymousMarketplace": - rw = anonymousMarketplace_listing_parser(soup) + rw = anonymousMarketplace_listing_parser(soup) + elif marketPlace == "ViceCity": + rw = vicecity_listing_parser(soup) else: parseError = True diff --git a/MarketPlaces/ViceCity/crawler_selenium.py b/MarketPlaces/ViceCity/crawler_selenium.py index e69de29..0b22082 100644 --- a/MarketPlaces/ViceCity/crawler_selenium.py +++ b/MarketPlaces/ViceCity/crawler_selenium.py @@ -0,0 +1,333 @@ +__author__ = 'DarkWeb' + +''' +ViceCity Market Forum 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 import expected_conditions as EC +from selenium.webdriver.common.by import By + +from PIL import Image +import urllib.parse as urlparse +import os, time +from datetime import date +import subprocess +import configparser +import subprocess +from bs4 import BeautifulSoup +from MarketPlaces.Initialization.prepare_parser import new_parse +from MarketPlaces.ViceCity.parser import vicecity_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +config = configparser.ConfigParser() +config.read('../../setup.ini') +counter = 1 +baseURL = 'http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/' + + +# Opens Tor Browser, crawls the website, then parses, then closes tor +#acts like the main method for the crawler, another function at the end of this code calls this function later +def startCrawling(): + # opentor() + mktName = getMKTName() + # driver = getAccess() + # + # if driver != 'down': + # try: + # login(driver) + # crawlForum(driver) + # except Exception as e: + # print(driver.current_url, e) + # closetor(driver) + + new_parse(mktName, baseURL, True) + + +# Opens Tor Browser +#prompts for ENTER input to continue +def opentor(): + global pid + print("Connecting Tor...") + pro = subprocess.Popen(config.get('TOR', 'firefox_binary_path')) + pid = pro.pid + time.sleep(7.5) + input('Tor Connected. Press ENTER to continue\n') + return + + +# Returns the name of the website +#return: name of site in string type +def getMKTName(): + name = 'ViceCity' + return name + + +# Return the base link of the website +#return: url of base site in string type +def getFixedURL(): + url = 'http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/' + return url + + +# Closes Tor Browser +#@param: current selenium driver +def closetor(driver): + # global pid + # os.system("taskkill /pid " + str(pro.pid)) + # os.system("taskkill /t /f /im tor.exe") + print('Closing Tor...') + driver.close() + time.sleep(3) + return + + +# Creates FireFox 'driver' and configure its 'Profile' +# to use Tor proxy and socket +def createFFDriver(): + 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) + + return driver + +#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down' +#return: return the selenium driver or string 'down' +def getAccess(): + url = getFixedURL() + driver = createFFDriver() + try: + driver.get(url) + return driver + except: + driver.close() + return 'down' + + +# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha +# then allows for manual solving of captcha in the terminal +#@param: current selenium web driver +def login(driver): + # wait for first captcha page to show up (This Xpath may need to change based on different seed url) + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, "/html/body/div/div/form/div/div[1]"))) + input("Press Enter once captcha done (dont press done)") + #clicks button after captcha is inputted + driver.find_element(by=By.XPATH, value='/html/body/div/div/form/button').click() + + #wait for login page to show up + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, '/html/body/div/div/div/form'))) + #puts username into box + userBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]') + userBox.send_keys('ct1234') + + #waits for second catpcha to be inputted by user + input("Press Enter once captcha done (dont press continue)") + #clicks on continue + driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/input[2]').click() + + #waits for password to show + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, '/html/body/div/div/div/form/div[3]/input'))) + time.sleep(10) # give time for site to catch up + # puts password into box + passBox = driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/div[2]/input') + passBox.send_keys('DementedBed123-') + driver.find_element(by=By.XPATH, value='/html/body/div/div/div/form/div[3]/input').click() + + # wait for pin input to show + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, '/html/body/div[1]/div/form/span'))) + pinBox = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div/form/input[1]') + pinBox.send_keys('12345') + driver.find_element(by=By.XPATH, value='/html/body/div[1]/div/form/input[2]').click() + + # waits for main listing page before crawling to ensure everything goes well + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, '/html/body/div[1]/div/div[2]'))) + + +# Saves the crawled html page, makes the directory path for html pages if not made +def savePage(page, url): + cleanPage = cleanHTML(page) + filePath = getFullPathName(url) + os.makedirs(os.path.dirname(filePath), exist_ok=True) + open(filePath, 'wb').write(cleanPage.encode('utf-8')) + return + + +# Gets the full path of the page to be saved along with its appropriate file name +#@param: raw url as crawler crawls through every site +def getFullPathName(url): + fileName = getNameFromURL(url) + if isDescriptionLink(url): + fullPath = r'..\ViceCity\HTML_Pages\\' + str( + "%02d" % date.today().month) + str("%02d" % date.today().day) + str( + "%04d" % date.today().year) + r'\\' + r'Description\\' + fileName + '.html' + else: + fullPath = r'..\ViceCity\HTML_Pages\\' + str( + "%02d" % date.today().month) + str("%02d" % date.today().day) + str( + "%04d" % date.today().year) + r'\\' + r'Listing\\' + fileName + '.html' + return fullPath + + +# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned +#@param: raw url as crawler crawls through every site +def getNameFromURL(url): + global counter + name = ''.join(e for e in url if e.isalnum()) + if (name == ''): + name = str(counter) + counter = counter + 1 + return name + + +# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list +#in this example, there are a couple of categories some threads fall under such as +# Guides and Tutorials, Digital Products, and Software and Malware +#as you can see they are categories of products +def getInterestedLinks(): + links = [] + + # Digital - Fraud Software, Has Hacking and Guides + links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=150') + # Digital - Guides and Tutorials + # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=94') + # Carding Services + # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=155') + # Digital - Other (half junk half random stuff like: bots, rats, viruses, and guides) + # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=153') + + return links + + +# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through +#topic and description pages are crawled through here, where both types of pages are saved +#@param: selenium driver +def crawlForum(driver): + print("Crawling the ViceCity Market") + + linksToCrawl = getInterestedLinks() + visited = set(linksToCrawl) + initialTime = time.time() + + count = 0 + i = 0 + while i < len(linksToCrawl): + link = linksToCrawl[i] + print('Crawling :', link) + try: + try: + driver.get(link) + except: + driver.refresh() + html = driver.page_source + savePage(html, link) + + has_next_page = True + while has_next_page: + list = productPages(html) + j = 0 + for item in list: + itemURL = urlparse.urljoin(baseURL, str(item)) + try: + driver.get(itemURL) + except: + driver.refresh() + time.sleep(2.5) # to let page catchup + savePage(driver.page_source, item) + driver.back() + + #comment out + break + + # # comment out + # if count == 1: + # count = 0 + # break + + try: + temp = driver.find_element(by=By.CLASS_NAME, value='pagination') + link = temp.find_element(by=By.LINK_TEXT, value='Next').get_attribute('href') + if link == "": + raise NoSuchElementException + try: + driver.get(link) + except: + driver.refresh() + html = driver.page_source + savePage(html, link) + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + # finalTime = time.time() + # print finalTime - initialTime + + input("Crawling ViceCity done sucessfully. Press ENTER to continue\n") + + +# Returns 'True' if the link is a description link +#@param: url of any url crawled +#return: true if is a description page, false if not +def isDescriptionLink(url): + if 'listing' in url: + return True + return False + + +# Returns True if the link is a listingPage link +#@param: url of any url crawled +#return: true if is a Listing page, false if not +def isListingLink(url): + if 'category' in url: + return True + return False + + +# calling the parser to define the links, the html is the url of a link from the list of interested link list +#@param: link from interested link list ie. getInterestingLinks() +#return: list of description links that should be crawled through +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return vicecity_links_parser(soup) + + +def crawler(): + startCrawling() + # print("Crawling and Parsing BestCardingWorld .... DONE!") diff --git a/MarketPlaces/ViceCity/parser.py b/MarketPlaces/ViceCity/parser.py index 2508b2d..65d6b8f 100644 --- a/MarketPlaces/ViceCity/parser.py +++ b/MarketPlaces/ViceCity/parser.py @@ -8,7 +8,7 @@ from bs4 import BeautifulSoup # This is the method to parse the Description Pages (one page to each Product in the Listing Pages) -def tor2door_description_parser(soup): +def vicecity_description_parser(soup): # Fields to be parsed vendor = "-1" # 0 *Vendor_Name @@ -31,62 +31,68 @@ def tor2door_description_parser(soup): shipFrom = "-1" # 17 Product_ShippedFrom shipTo = "-1" # 18 Product_ShippedTo - bae = soup.find('div', {'class': "col-9"}) - # Finding Product Name - name = bae.find('h2').text + name = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}) + name = name.find('span', {'style': "font-size:18px;font-weight: bold;color: #fff"}).text name = name.replace('\n', ' ') name = name.replace(",", "") name = name.strip() - mb = bae.findAll('div', {"class": "mb-1"}) - # Finding Vendor - vendor = mb[0].text - vendor = vendor.replace(",", "") - vendor = vendor.replace("Sold by:", "") - vendor = vendor.strip() + vendor = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').text.strip() - # # Finding Vendor Rating - # full_stars = bae[2].find_all('i', {'class': "fas fa-star"}) - # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"}) - # rating = len(full_stars) + (0.5 if half_star is not None else 0) + # Finding Vendor Rating + rating = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title') + rating = str(re.match(r"\d+%", rating)).strip() # Finding Quantity Sold and Left - temp = mb[4].text.split(',') + # temp = mb[4].text.split(',') + # + # sold = temp[0].replace("sold", "") + # sold = sold.strip() + # + # left = temp[1].replace("in stock", "") + # left = left.strip() - sold = temp[0].replace("sold", "") - sold = sold.strip() + # Finding Successful Transactions + success = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title') + success = str(re.compile(r"\d+(?= sales)", success)).strip() - left = temp[1].replace("in stock", "") - left = left.strip() + bae = soup.find('pre') # Finding USD - USD = bae.find('div', {"class": "h3 text-secondary"}).text - USD = USD.replace("$", "") - USD = USD.strip() + USD = bae.find('span').text + USD = str(re.compile(r"\$\d+(?:\.\d+)?", USD)) + USD = USD.replace("$", "").strip() # Finding BTC - temp = bae.find('div', {"class": "small"}).text.split("BTC") + BTC = bae.findall('span') + BTC = str(re.compile(r"\d+(?:\.\d+)?", BTC[1].text)).strip() - BTC = temp[0].strip() + # Finding the Product Category + category = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}) + category = category.find('span', {'style': "font-size:15px;color: #a1a1a1"}).text + category = category.replace("Category:", "").strip() - # shipping_info = bae[4].text - # if "Digital" not in shipping_info: - # shipping_info = shipping_info.split(" ") - # - # # Finding Shipment Information (Origin) - # shipFrom = shipping_info[0].strip() - # - # # Finding Shipment Information (Destination) - # shipTo = shipping_info[1].strip() + li = bae.find('span', {'style': "float:right"}).find_all('span') + + # Finding Shipment Information (Origin) + shipFrom = li[1].text.strip() + + # Finding Shipment Information (Destination) + shipTo = li[-2].text.strip() # Finding the Product description - describe = bae.find('div', {"class": "card border-top-0"}).text + describe = soup.find('p', { + 'style': "width:705px;margin-left:-305px;background-color: #242424;border-radius: 3px;border: 1px solid #373737;padding: 5px;"}).text describe = describe.replace("\n", " ") - describe = describe.replace("\r", " ") describe = describe.strip() + # Finding the Number of Product Reviews + li = soup.find_all('label', {'class': "tc_label threetabs"}) + review = li[1].text + review = str(re.compile(r"\d+", review)).strip() + # Searching for CVE and MS categories cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) if cve: @@ -114,10 +120,10 @@ def tor2door_description_parser(soup): # This is the method to parse the Listing Pages -def tor2door_listing_parser(soup): +def vicecity_listing_parser(soup): # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) - mktName = "Tor2door" # 0 *Marketplace_Name + mktName = "ViceCity" # 0 *Marketplace_Name vendor = [] # 1 *Vendor y rating_vendor = [] # 2 Vendor_Rating success = [] # 3 Vendor_Successful_Transactions @@ -139,56 +145,69 @@ def tor2door_listing_parser(soup): shipTo = [] # 19 Product_ShippedTo href = [] # 20 Product_Links - listing = soup.findAll('div', {"class": "card product-card mb-3"}) + listing = soup.find('div', {"class": "frontpage"}).findAll('div', {"class": "wLf"}) # Populating the Number of Products nm = len(listing) - # Finding Category - cat = soup.find("div", {"class": "col-9"}) - cat = cat.find("h2").text - cat = cat.replace("Category: ", "") - cat = cat.replace(",", "") - cat = cat.strip() + # # Finding Category + # cat = soup.find("div", {"class": "col-9"}) + # cat = cat.find("h2").text + # cat = cat.replace("Category: ", "") + # cat = cat.replace(",", "") + # cat = cat.strip() - for card in listing: - category.append(cat) + for a in listing: + # category.append(cat) - bae = card.findAll('a') + # bae = card.findAll('a') # Adding the url to the list of urls - link = bae[0].get('href') + link = a.find('div', {"class": "wLfLeft"}).find('a', href=True).get('href') + link = cleanLink(link) href.append(link) - # Finding Product Name - product = bae[1].text + # Finding the Product Name + product = a.find('div', {"class": "wLfName"}).find('a').text product = product.replace('\n', ' ') product = product.replace(",", "") + product = product.replace("...", "") product = product.strip() name.append(product) - # Finding Vendor - vendor_name = bae[2].text + # Finding the Vendor + vendor_name = a.find('div', {"class": "wLfVendor"}).find('a').text vendor_name = vendor_name.replace(",", "") vendor_name = vendor_name.strip() vendor.append(vendor_name) - # Finding USD - usd = card.find('div', {"class": "mb-1"}).text - usd = usd.replace("$", "") - usd = usd.strip() - USD.append(usd) - - # Finding Reviews - num = card.find("span", {"class": "rate-count"}).text - num = num.replace("(", "") - num = num.replace("review)", "") - num = num.replace("reviews)", "") - num = num.strip() - reviews.append(num) + # Finding Prices + price = a.find('div', {"class": "wLfPrice"}).find_all('span') + ud = price[0].text.replace(" USD", " ") + # u = ud.replace("$","") + u = ud.replace(",", "") + u = u.strip() + USD.append(u) + bc = price[1].text + bc = str(re.compile(r"\d+(?:\.\d+)?", bc)) + BTC.append(bc) + + # # Finding Reviews + # num = card.find("span", {"class": "rate-count"}).text + # num = num.replace("(", "") + # num = num.replace("review)", "") + # num = num.replace("reviews)", "") + # num = num.strip() + # reviews.append(num) + + # Finding Successful Transactions + freq = a.find('div', {"class": "wLfVendor"}).find('a').get('title') + freq = re.compile(r'\d+(?= sales)', freq) + freq = freq.strip() + success.append(freq) # Searching for CVE and MS categories - cve = card.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) if not cve: cveValue = "-1" else: @@ -201,7 +220,7 @@ def tor2door_listing_parser(soup): cveValue = cee CVE.append(cveValue) - ms = card.findAll(text=re.compile('MS\d{2}-\d{3}')) + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) if not ms: MSValue = "-1" else: @@ -219,14 +238,15 @@ def tor2door_listing_parser(soup): reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href) -def tor2door_links_parser(soup): +def vicecity_links_parser(soup): # Returning all links that should be visited by the Crawler - href = [] - listing = soup.findAll('div', {"class": "card product-card mb-3"}) + href = [] + listing = soup.find('div', {"class": "frontpage"}).findAll('div', {"class": "wLf"}) - for div in listing: - link = div.find('a')['href'] + for a in listing: + bae = a.find('div', {"class": "wLfLeft"}).find('a', href=True) + link = bae['href'] href.append(link) - return href \ No newline at end of file + return href From abeb2c0df0f87e6d22760d0f89d2591c6948235a Mon Sep 17 00:00:00 2001 From: Joshua Date: Fri, 14 Jul 2023 12:21:36 -0700 Subject: [PATCH 3/4] fixed bugs with crawler not getting all pages and parser breaking --- MarketPlaces/Initialization/geckodriver.log | 147 ++++++++++++++++++++ MarketPlaces/Initialization/marketsList.txt | 2 +- MarketPlaces/ViceCity/crawler_selenium.py | 16 +-- MarketPlaces/ViceCity/parser.py | 58 ++++++-- setup.ini | 13 +- 5 files changed, 206 insertions(+), 30 deletions(-) diff --git a/MarketPlaces/Initialization/geckodriver.log b/MarketPlaces/Initialization/geckodriver.log index 8b61c4e..c45f256 100644 --- a/MarketPlaces/Initialization/geckodriver.log +++ b/MarketPlaces/Initialization/geckodriver.log @@ -15532,3 +15532,150 @@ DevTools listening on ws://localhost:51081/devtools/browser/ef699bfb-b8a4-403a-a 1689136181511 RemoteAgent WARN TLS certificate errors will be ignored for this session JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +1689305282590 geckodriver INFO Listening on 127.0.0.1:57612 +1689305286344 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "57613" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofileW1wjHz" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689305287006 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:57613/devtools/browser/9cb995f7-f1d0-45e1-a9ae-0903f91679e2 +1689305288403 Marionette INFO Listening on port 57618 +1689305288510 RemoteAgent WARN TLS certificate errors will be ignored for this session +1689305558621 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689305591430 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689305927779 Marionette INFO Stopped listening on port 57618 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +!!! error running onStopped callback: TypeError: callback is not a function +1689305927959 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 +1689306152997 geckodriver INFO Listening on 127.0.0.1:62728 +1689306156730 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "62729" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofileQfWfpc" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689306157335 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:62729/devtools/browser/90212f30-1413-403a-a4d6-85a9ad71de86 +1689306158784 Marionette INFO Listening on port 62734 +1689306158827 RemoteAgent WARN TLS certificate errors will be ignored for this session +1689306327168 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689306352097 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689306672567 Marionette INFO Stopped listening on port 62734 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +!!! error running onStopped callback: TypeError: callback is not a function + +###!!! [Parent][MessageChannel] Error: (msgtype=0x390076,name=PContent::Msg_DestroyBrowsingContextGroup) Closed channel: cannot send/recv + + +###!!! [Child][MessageChannel] Error: (msgtype=0x23002E,name=PBrowser::Msg___delete__) Channel closing: too late to send/recv, messages will be lost + + +###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost + +1689306672742 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 +1689353148352 geckodriver INFO Listening on 127.0.0.1:57720 +1689353152386 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "57721" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofilebdVBHT" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689353153078 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:57721/devtools/browser/66aa6550-8450-49a2-be19-7728fc52cb65 +1689353154754 Marionette INFO Listening on port 57726 +1689353155234 RemoteAgent WARN TLS certificate errors will be ignored for this session +JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\John Wick\AppData\Local\Temp\rust_mozprofilebdVBHT\thumbnails) because it does not exist +1689353351388 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689353375169 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689353609409 Marionette INFO Stopped listening on port 57726 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +!!! error running onStopped callback: TypeError: callback is not a function +1689353609555 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 +1689358893192 geckodriver INFO Listening on 127.0.0.1:53304 +1689358897088 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "53305" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofile5c9ZQ4" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689358897866 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:53305/devtools/browser/2f57a39e-c4c4-4c89-af0b-cc8d26d8a863 +1689358899540 Marionette INFO Listening on port 53310 +1689358899767 RemoteAgent WARN TLS certificate errors will be ignored for this session +JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\John Wick\AppData\Local\Temp\rust_mozprofile5c9ZQ4\thumbnails) because it does not exist +1689359085260 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689359112369 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +1689360786237 Marionette INFO Stopped listening on port 53310 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +!!! error running onStopped callback: TypeError: callback is not a function + +###!!! [Child][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost + + +###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost + +1689360786406 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 diff --git a/MarketPlaces/Initialization/marketsList.txt b/MarketPlaces/Initialization/marketsList.txt index 19c6d10..a427446 100644 --- a/MarketPlaces/Initialization/marketsList.txt +++ b/MarketPlaces/Initialization/marketsList.txt @@ -1 +1 @@ -M00nkeyMarket +ViceCity diff --git a/MarketPlaces/ViceCity/crawler_selenium.py b/MarketPlaces/ViceCity/crawler_selenium.py index 0b22082..584a90c 100644 --- a/MarketPlaces/ViceCity/crawler_selenium.py +++ b/MarketPlaces/ViceCity/crawler_selenium.py @@ -46,7 +46,7 @@ def startCrawling(): # print(driver.current_url, e) # closetor(driver) - new_parse(mktName, baseURL, True) + new_parse(mktName, baseURL, False) # Opens Tor Browser @@ -189,15 +189,14 @@ def savePage(page, url): # Gets the full path of the page to be saved along with its appropriate file name #@param: raw url as crawler crawls through every site def getFullPathName(url): + from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE + + mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getMKTName() + "/HTML_Pages") fileName = getNameFromURL(url) if isDescriptionLink(url): - fullPath = r'..\ViceCity\HTML_Pages\\' + str( - "%02d" % date.today().month) + str("%02d" % date.today().day) + str( - "%04d" % date.today().year) + r'\\' + r'Description\\' + fileName + '.html' + fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html') else: - fullPath = r'..\ViceCity\HTML_Pages\\' + str( - "%02d" % date.today().month) + str("%02d" % date.today().day) + str( - "%04d" % date.today().year) + r'\\' + r'Listing\\' + fileName + '.html' + fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html') return fullPath @@ -266,10 +265,11 @@ def crawlForum(driver): driver.refresh() time.sleep(2.5) # to let page catchup savePage(driver.page_source, item) + time.sleep(2.5) # so site doesnt crash driver.back() #comment out - break + # break # # comment out # if count == 1: diff --git a/MarketPlaces/ViceCity/parser.py b/MarketPlaces/ViceCity/parser.py index 65d6b8f..eeb97a3 100644 --- a/MarketPlaces/ViceCity/parser.py +++ b/MarketPlaces/ViceCity/parser.py @@ -1,5 +1,7 @@ __author__ = 'DarkWeb' +import re + # Here, we are importing the auxiliary functions to clean or convert data from MarketPlaces.Utilities.utilities import * @@ -39,11 +41,16 @@ def vicecity_description_parser(soup): name = name.strip() # Finding Vendor - vendor = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').text.strip() + vendor = soup.find('div', {'class': "listing_info"}) + vendor = vendor.find('div', {'class': "listing_right"}) + numbers = vendor.find('a').find('span').text + vendor = vendor.find('a').text + vendor = vendor.replace(numbers, "").strip() # removes numbers at the end of vendor name # Finding Vendor Rating rating = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title') - rating = str(re.match(r"\d+%", rating)).strip() + rating = re.search(r"\d+%", rating) + rating_vendor = rating.group(0).strip() # Finding Quantity Sold and Left # temp = mb[4].text.split(',') @@ -56,28 +63,31 @@ def vicecity_description_parser(soup): # Finding Successful Transactions success = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title') - success = str(re.compile(r"\d+(?= sales)", success)).strip() + success = re.search(r"\d+(?= sales)", success) + success = success.group(0).strip() + bae = soup.find('pre') # Finding USD USD = bae.find('span').text - USD = str(re.compile(r"\$\d+(?:\.\d+)?", USD)) + USD = re.search(r"\$\d+(?:\.\d+)?", USD).group(0) USD = USD.replace("$", "").strip() # Finding BTC - BTC = bae.findall('span') - BTC = str(re.compile(r"\d+(?:\.\d+)?", BTC[1].text)).strip() + BTC = bae.find_all('span') + BTC = re.search(r"\d+(?:\.\d+)?", BTC[1].text).group(0) + BTC = BTC.strip() # Finding the Product Category category = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}) category = category.find('span', {'style': "font-size:15px;color: #a1a1a1"}).text category = category.replace("Category:", "").strip() - li = bae.find('span', {'style': "float:right"}).find_all('span') + li = bae.find_all('span') # Finding Shipment Information (Origin) - shipFrom = li[1].text.strip() + shipFrom = li[-4].text.strip() # Finding Shipment Information (Destination) shipTo = li[-2].text.strip() @@ -91,7 +101,11 @@ def vicecity_description_parser(soup): # Finding the Number of Product Reviews li = soup.find_all('label', {'class': "tc_label threetabs"}) review = li[1].text - review = str(re.compile(r"\d+", review)).strip() + review = re.search(r"\d+", review) + if review: + reviews = review.group(0).strip() + else: + reviews = '0' # Searching for CVE and MS categories cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) @@ -145,7 +159,7 @@ def vicecity_listing_parser(soup): shipTo = [] # 19 Product_ShippedTo href = [] # 20 Product_Links - listing = soup.find('div', {"class": "frontpage"}).findAll('div', {"class": "wLf"}) + listing = soup.findAll('div', {"class": "wLf"}) # should be 30 # Populating the Number of Products nm = len(listing) @@ -177,7 +191,9 @@ def vicecity_listing_parser(soup): # Finding the Vendor vendor_name = a.find('div', {"class": "wLfVendor"}).find('a').text + addedNums = a.find('div', {"class": "wLfVendor"}).find('a').find('span').text # finds numbers added at end vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.replace(addedNums, "") # removes numbers added at end vendor_name = vendor_name.strip() vendor.append(vendor_name) @@ -185,11 +201,12 @@ def vicecity_listing_parser(soup): price = a.find('div', {"class": "wLfPrice"}).find_all('span') ud = price[0].text.replace(" USD", " ") # u = ud.replace("$","") - u = ud.replace(",", "") + ud = ud.replace(",", "") + u = ud.replace(price[1].text, "") u = u.strip() USD.append(u) bc = price[1].text - bc = str(re.compile(r"\d+(?:\.\d+)?", bc)) + bc = re.search(r"\d+(?:\.\d+)?", bc).group(0).strip() BTC.append(bc) # # Finding Reviews @@ -202,10 +219,23 @@ def vicecity_listing_parser(soup): # Finding Successful Transactions freq = a.find('div', {"class": "wLfVendor"}).find('a').get('title') - freq = re.compile(r'\d+(?= sales)', freq) + freq = re.search(r'\d+(?= sales)', freq).group(0) freq = freq.strip() success.append(freq) + # Finding Ship from and ship to + place = a.find('div', {"class": "wLfPrice"}) + place = place.find('span', {'style': "font-size: 12px;"}).text + place = place.split('⟶') + varFrom = place[0].strip() + varTo = place[1].strip() + if varFrom == "WW": + varFrom = "Worldwide" + if varTo == "WW": + varTo = "Worldwide" + shipFrom.append(varFrom) + shipTo.append(varTo) + # Searching for CVE and MS categories cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) if not cve: @@ -242,7 +272,7 @@ def vicecity_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] - listing = soup.find('div', {"class": "frontpage"}).findAll('div', {"class": "wLf"}) + listing = soup.findAll('div', {"class": "wLf"}) for a in listing: bae = a.find('div', {"class": "wLfLeft"}).find('a', href=True) diff --git a/setup.ini b/setup.ini index 641d3f1..c87990a 100644 --- a/setup.ini +++ b/setup.ini @@ -1,15 +1,14 @@ - [TOR] -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 +firefox_binary_path = C:\Users\John Wick\Desktop\Tor Browser\Browser\firefox.exe +firefox_profile_path = C:\Users\John Wick\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default +geckodriver_path = C:\Users\John Wick\PycharmProjects\dw_pipeline_test\selenium\geckodriver.exe [Project] -project_directory = C:\\Users\\Helium\\PycharmProjects\\dw_pipeline_test -shared_folder = \\VBoxSvr\\Shared +project_directory = C:\Users\John Wick\PycharmProjects\dw_pipeline_test +shared_folder = Z:\\VBoxSvr\\VM_Files_ (shared) [PostgreSQL] ip = localhost username = postgres -password = password +password = postgres database = darkweb_markets_forums \ No newline at end of file From c50fe116c210663ae9673ed32a3dcc7b74df4898 Mon Sep 17 00:00:00 2001 From: Joshua Date: Mon, 17 Jul 2023 19:39:45 -0700 Subject: [PATCH 4/4] Completed and Tested Vicecity --- MarketPlaces/Initialization/geckodriver.log | 67 +++++++++++++++++++++ MarketPlaces/ViceCity/crawler_selenium.py | 26 ++++---- 2 files changed, 80 insertions(+), 13 deletions(-) diff --git a/MarketPlaces/Initialization/geckodriver.log b/MarketPlaces/Initialization/geckodriver.log index c45f256..3aaedfc 100644 --- a/MarketPlaces/Initialization/geckodriver.log +++ b/MarketPlaces/Initialization/geckodriver.log @@ -15679,3 +15679,70 @@ unwatchForTargets()@TargetList.jsm:37 destructor()@TargetList.jsm:109 stop()@CDP.jsm:104 close()@RemoteAgent.jsm:138 +1689645823453 geckodriver INFO Listening on 127.0.0.1:62446 +1689645827490 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "62447" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofilepVLlk4" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689645828210 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:62447/devtools/browser/a3aaa3d3-8117-40bb-a1c4-fb8dd951c8b4 +1689645829865 Marionette INFO Listening on port 62452 +1689645830203 RemoteAgent WARN TLS certificate errors will be ignored for this session +1689645966231 Marionette INFO Stopped listening on port 62452 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData] +!!! error running onStopped callback: TypeError: callback is not a function +1689645966414 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 +1689646027040 geckodriver INFO Listening on 127.0.0.1:51479 +1689646031030 mozrunner::runner INFO Running command: "C:\\Users\\John Wick\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "51480" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\JOHNWI~1\\AppData\\Local\\Temp\\rust_mozprofilea9Xzpl" +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observed profile-after-change" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.log: "TorSettings: Observed profile-after-change" +1689646031751 Marionette INFO Marionette enabled +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +console.error: "Could not load engine blockchair-onion@search.mozilla.org: Error: Extension is invalid" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:51480/devtools/browser/8c1f9a42-7805-4208-a9e1-870a0b3b2d6b +1689646033369 Marionette INFO Listening on port 56864 +1689646033727 RemoteAgent WARN TLS certificate errors will be ignored for this session +1689646216510 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689646242045 Marionette WARN Ignoring event 'DOMContentLoaded' because document has an invalid readyState of 'complete'. +1689647720305 Marionette INFO Stopped listening on port 56864 +JavaScript error: resource:///modules/Interactions.jsm, line 209: NS_ERROR_FAILURE: Component returned failure code: 0x80004005 (NS_ERROR_FAILURE) [nsIUserIdleService.removeIdleObserver] +JavaScript error: chrome://remote/content/marionette/cert.js, line 55: NS_ERROR_NOT_AVAILABLE: Component returned failure code: 0x80040111 (NS_ERROR_NOT_AVAILABLE) [nsICertOverrideService.setDisableAllSecurityChecksAndLetAttackersInterceptMyData] +!!! error running onStopped callback: TypeError: callback is not a function + +###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost + +1689647720428 RemoteAgent ERROR unable to stop listener: [Exception... "Component returned failure code: 0x8000ffff (NS_ERROR_UNEXPECTED) [nsIWindowMediator.getEnumerator]" nsresult: "0x8000ffff (NS_ERROR_UNEXPECTED)" location: "JS frame :: chrome://remote/content/cdp/observers/TargetObserver.jsm :: stop :: line 64" data: no] Stack trace: stop()@TargetObserver.jsm:64 +unwatchForTabs()@TargetList.jsm:70 +unwatchForTargets()@TargetList.jsm:37 +destructor()@TargetList.jsm:109 +stop()@CDP.jsm:104 +close()@RemoteAgent.jsm:138 diff --git a/MarketPlaces/ViceCity/crawler_selenium.py b/MarketPlaces/ViceCity/crawler_selenium.py index 584a90c..e49bbda 100644 --- a/MarketPlaces/ViceCity/crawler_selenium.py +++ b/MarketPlaces/ViceCity/crawler_selenium.py @@ -34,17 +34,17 @@ baseURL = 'http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion # Opens Tor Browser, crawls the website, then parses, then closes tor #acts like the main method for the crawler, another function at the end of this code calls this function later def startCrawling(): - # opentor() + opentor() mktName = getMKTName() - # driver = getAccess() - # - # if driver != 'down': - # try: - # login(driver) - # crawlForum(driver) - # except Exception as e: - # print(driver.current_url, e) - # closetor(driver) + driver = getAccess() + + if driver != 'down': + try: + login(driver) + crawlForum(driver) + except Exception as e: + print(driver.current_url, e) + closetor(driver) new_parse(mktName, baseURL, False) @@ -221,11 +221,11 @@ def getInterestedLinks(): # Digital - Fraud Software, Has Hacking and Guides links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=150') # Digital - Guides and Tutorials - # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=94') + links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=94') # Carding Services - # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=155') + links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=155') # Digital - Other (half junk half random stuff like: bots, rats, viruses, and guides) - # links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=153') + links.append('http://52qlucglu6fuaqist2herssakipapig2higaaayu7446n55xw4ylxqid.onion/?category=153') return links