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 2196307..c451758 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"]*style=\"[^\"]*background-image.*?>", "", clean_html) + clean_html = re.sub(r"]*style=\"[^\"]*background-image.*?>|background-image:url\(\'(.*?)\'\);", "", clean_html) return clean_html diff --git a/MarketPlaces/HiddenMarket/crawler_selenium.py b/MarketPlaces/HiddenMarket/crawler_selenium.py new file mode 100644 index 0000000..c89d467 --- /dev/null +++ b/MarketPlaces/HiddenMarket/crawler_selenium.py @@ -0,0 +1,324 @@ +__author__ = 'DarkWeb' + +''' +HiddenMarket Market 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.common.by import By +from selenium.webdriver.support import expected_conditions as EC +from selenium.webdriver.support.ui import WebDriverWait +from PIL import Image + +import urllib.parse as urlparse +import os, re, time +import subprocess +import configparser +from bs4 import BeautifulSoup +from MarketPlaces.Initialization.prepare_parser import new_parse +from MarketPlaces.HiddenMarket.parser import hiddenmarket_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/' + + +# Opens Tor Browser, crawls the website +def startCrawling(): + opentor() + marketName = getMKTName() + driver = getAccess() + + if driver != 'down': + try: + login(driver) + crawlForum(driver) + except Exception as e: + print(driver.current_url, e) + closetor(driver) + + new_parse(marketName, baseURL, False) + + +# Opens Tor Browser +def opentor(): + from MarketPlaces.Initialization.markets_mining import config + + 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 + + +# Login using premade account credentials and do login captcha manually +def login(driver): + # wait for login page + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, "/html/body/div[3]/div[3]"))) + + # entering username and password into input boxes + # usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]') + # Username here + # usernameBox.send_keys('ct1234') + # passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]') + # Password here + # passwordBox.send_keys('DementedBed1230') + + ''' + # wait for captcha page show up + WebDriverWait(driver, 100).until(EC.visibility_of_element_located( + (By.XPATH, "/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img"))) + + # save captcha to local + driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[3]/div/div[1]/label/img').screenshot( + r'..\captcha.png') + + # This method will show image in any image viewer + im = Image.open(r'..\captcha.png') + + im.show() + + # wait until input space show up + inputBox = driver.find_element(by=By.XPATH, value='//*[@id="captcha"]') + + # ask user input captcha solution in terminal + userIn = input("Enter solution: ") + + # send user solution into the input space + inputBox.send_keys(userIn) + + # click the verify(submit) button + driver.find_element(by=By.XPATH, value="/html/body/main/div/div/div/div/div/form/div[4]/button").click() + ''' + # input("Press ENTER when CAPTCHA is completed\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/main/div/div/div[1]/div/div[1]/div/h5'))) + + +# Returns the name of the website +def getMKTName(): + name = 'HiddenMarket' + return name + + +# Return the link of the website +def getFixedURL(): + url = 'http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/' + + return url + + +# Closes Tor Browser +def closetor(driver): + # global pid + # os.system("taskkill /pid " + str(pro.pid)) + # os.system("taskkill /t /f /im tor.exe") + print('Closing Tor...') + driver.quit() + 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) + + return driver + + +def getAccess(): + url = getFixedURL() + driver = createFFDriver() + try: + driver.get(url) + return driver + except: + driver.close() + return 'down' + + +# Saves the crawled html page +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 +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 + + +# Creates the file name from passed URL +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 = [] + + # # Civil Software + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/civil_softwares') + # # Tutorials - Carding + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/carding') + # # Digital - Hacks + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/hacks') + # Digital - Exploit Kit + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/exploit_kit') + # # 0Day + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/0day') + # Digital Forensics + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/digital_forensics') + # Tutorials - Mining + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/mining') + # Tutorials - Worms + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/worms') + # Tutorials - Viruses + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/viruses') + # Tutorials - Trojans + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/trojans') + # Tutorials - Botnets + links.append('http://mipx6eedtsvfgfcmbm3utjedgjez2w4dzjdrbhtd2mt3cicwhhzspxqd.onion/category/botnets') + + return links + + +def crawlForum(driver): + print("Crawling the HiddenMarket market") + + linksToCrawl = getInterestedLinks() + + i = 0 + while i < len(linksToCrawl): + link = linksToCrawl[i] + print('Crawling :', link) + categoryLink = link + maxNumPages = 0 # temp value. + try: + has_next_page = True + count = 0 + pageCount = 1 + + while has_next_page: + try: + driver.get(link) + if pageCount == 1: + maxNumPages = int(driver.find_element(by=By.CLASS_NAME, value='main') + .find_element(by=By.CLASS_NAME, value='pages') + .find_elements(By.CLASS_NAME, value='page')[-1].text) + except: + driver.refresh() + html = driver.page_source + savePage(html, link) + + list = productPages(html) + for item in list: + itemURL = urlparse.urljoin(baseURL, str(item)) + try: + driver.get(itemURL) + except: + driver.refresh() + savePage(driver.page_source, item) + driver.back() + + # comment out + # break + + # comment out + # if count == 2: + # break + + try: + pageCount += 1 + if pageCount > maxNumPages: + raise NoSuchElementException + pageLink = "/" + str(pageCount) + "/" + link = categoryLink + pageLink + count += 1 + + except NoSuchElementException: + has_next_page = False + + except Exception as e: + print(link, e) + i += 1 + + input("Crawling HiddenMarket market done sucessfully. Press ENTER to continue\n") + + +# Returns 'True' if the link is Topic link +def isDescriptionLink(url): + if 'product' in url: + return True + return False + + +# Returns True if the link is a listingPage link +def isListingLink(url): + if 'category' in url: + return True + return False + + +# calling the parser to define the links +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return hiddenmarket_links_parser(soup) + + +def crawler(): + startCrawling() + # print("Crawling and Parsing BestCardingWorld .... DONE!") diff --git a/MarketPlaces/HiddenMarket/parser.py b/MarketPlaces/HiddenMarket/parser.py new file mode 100644 index 0000000..8f77f9d --- /dev/null +++ b/MarketPlaces/HiddenMarket/parser.py @@ -0,0 +1,280 @@ +__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 hiddenmarket_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': "main"}) + + # Finding Product Name + name = bae.find('div', {'class': "heading"}).text + name = name.replace('\n', ' ') + name = name.replace(",", "") + name = name.strip() + + mb = bae.find('div', {'class': "information"}).findAll('tr') + + # Finding Vendor + vendor = mb[1].find('a').text + vendor = vendor.replace(",", "") + 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 Left + temp = mb[-3].text + left = temp.replace("Quantity in stock:", "") + left = left.strip() + + # Finding USD + USD = mb[0].text + USD = USD.replace("Price:", "") + USD = USD.replace("USD", "") + USD = USD.strip() + + # Finding BTC + # temp = bae.find('div', {"class": "small"}).text.split("BTC") + + # BTC = temp[0].strip() + + # Finding Shipment Information (Origin) + shipFrom = mb[2].text + shipFrom = shipFrom.replace("Seller location:", "") + shipFrom = shipFrom.strip() + + # Finding Shipment Information (Destination) + shipTo = mb[3].text + shipTo = shipTo.replace("Ships to (seller):", "") + shipTo = shipTo.strip() + + # Finding the Product description + describe = bae.find('div', {"class": "twotabs"}).find('div', {'class': "tab1"}).text + describe = describe.replace("\n", " ") + describe = describe.replace("\r", " ") + describe = describe.replace("-", " ") + describe = describe.strip() + + # Finding the Product Category + category = mb[-4].text + category = category.replace("Category:", "") + category = category.strip() + + #Finding the number of reviews + reviews = bae.find_all('div', {'class': "heading"}) + reviews = reviews[-2].text + reviews = reviews.replace("Comments (", "") + reviews = reviews.replace(")", "") + + # 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 hiddenmarket_listing_parser(soup): + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "HiddenMarket" # 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": "item"}) + + # Populating the Number of Products + nm = len(listing) + + # Finding Category + # cat = soup.find("div", {'class': "heading"}).text + # cat = cat.replace(",", "") + # cat = cat.strip() + + for card in listing: + # category.append(cat) + + + # Adding the url to the list of urls + link = card.find_all('a') + link = link[1].get('href') + + href.append(link) + + # Finding Product Name + product = card.next_sibling.find('div', {'class': "title"}) + product = product.text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.strip() + name.append(product) + + # Finding Vendor + vendor_name = card.text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + + # Finding USD + usd = card.next_sibling.find('div', {"class": "buttons"}).find('div', {'class': "price"}).text + usd = usd.replace("USD", "") + usd = usd.strip() + USD.append(usd) + + tb = card.next_sibling.find("div", {"class": "stats"}) + tb = tb.find_all('td') + + # Finding Reviews + num = tb[-1].text + num = num.strip() + reviews.append(num) + + # Finding Views + view = tb[-3].text.strip() + views.append(view) + + # Finding Num of Sales + sale = tb[-2].text.strip() + sold.append(sale) + + # Finding Item Rating + if num == '0': + item_rating = '-1' + else: + item_rating = card.next_sibling.find('div', {'class': 'stats'}).find('div', {'class': "stars2"}) + item_rating = item_rating.get('style') + item_rating = item_rating.replace("width:", "") + item_rating = item_rating.replace("%", "") + item_rating = (float(item_rating) * 5.0) / 100.0 + item_rating = "{:.{}f}".format(item_rating, 2) + rating_item.append(item_rating) + + + # Finding shipping info + shipping = card.next_sibling.find('div', {'class': "shipping"}).text.split('>') + # SHip from + origin = shipping[0].strip() + shipFrom.append(origin) + #Ship to + destination = shipping[1].strip() + shipTo.append(destination) + + # Finding description (site only shows partial description on listing pages) + # description = card.next_sibling.find('div', {'class': "description"}).text + # description = description.replace("\n", " ") + # description = description.replace("\r", " ") + # description = description.replace("-", " ") + # description = description.strip() + # describe.append(description) + + # 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 hiddenmarket_links_parser(soup): + # Returning all links that should be visited by the Crawler + href = [] + + listing = soup.findAll('div', {"class": "item"}) + + for div in listing: + link = div.findAll('a') + link = link[1] + link = link['href'] + href.append(link) + + return href diff --git a/MarketPlaces/Initialization/marketsList.txt b/MarketPlaces/Initialization/marketsList.txt index 0393154..2e6ee5b 100644 --- a/MarketPlaces/Initialization/marketsList.txt +++ b/MarketPlaces/Initialization/marketsList.txt @@ -1 +1 @@ -TorMarket \ No newline at end of file +HiddenMarket \ No newline at end of file diff --git a/MarketPlaces/Initialization/markets_mining.py b/MarketPlaces/Initialization/markets_mining.py index 1c533ad..3b2e333 100644 --- a/MarketPlaces/Initialization/markets_mining.py +++ b/MarketPlaces/Initialization/markets_mining.py @@ -21,6 +21,7 @@ from MarketPlaces.CityMarket.crawler_selenium import crawler as crawlerCityMarke 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 +from MarketPlaces.HiddenMarket.crawler_selenium import crawler as crawlerHiddenMarket import configparser import time @@ -109,6 +110,8 @@ if __name__ == '__main__': crawlerM00nkeyMarket() elif mkt == "ViceCity": crawlerViceCity() + elif mkt == "HiddenMarket": + crawlerHiddenMarket() diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index 75090b1..90086a8 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -17,6 +17,8 @@ from MarketPlaces.DarkMatter.parser import * from MarketPlaces.DigitalThriftShop.parser import * from MarketPlaces.LionMarketplace.parser import * from MarketPlaces.TorMarket.parser import * +from MarketPlaces.HiddenMarket.parser import * + from MarketPlaces.Classifier.classify_product import predict @@ -160,6 +162,8 @@ def new_parse(marketPlace, url, createLog): rmm = torbay_description_parser(soup) elif marketPlace == "M00nkeyMarket": rmm = m00nkey_description_parser(soup) + elif marketPlace == "HiddenMarket": + rmm = hiddenmarket_description_parser(soup) elif marketPlace == "DarkMatter": rmm = darkmatter_description_parser(soup) elif marketPlace == "DigitalThriftShop": @@ -175,7 +179,7 @@ def new_parse(marketPlace, url, createLog): detPage[key] = {'rmm': rmm, 'filename': os.path.basename(line2)} except Exception as e: - raise e + raise e nError += 1 print("There was a problem to parse the file " + line2 + " in the Description section!") @@ -227,6 +231,8 @@ def new_parse(marketPlace, url, createLog): rw = torbay_listing_parser(soup) elif marketPlace == "M00nkeyMarket": rw = m00nkey_listing_parser(soup) + elif marketPlace == "HiddenMarket": + rw =hiddenmarket_listing_parser(soup) elif marketPlace == "DarkMatter": rw = darkmatter_listing_parser(soup) elif marketPlace == "DigitalThriftShop": @@ -242,8 +248,6 @@ def new_parse(marketPlace, url, createLog): nError += 1 print("There was a problem to parse the file " + line1 + " in the listing section!") - print("I am here for some reason!") - raise e if createLog: logFile.write( str(nError) + ". There was a problem to parse the file " + line1 + " in the Listing section.\n") @@ -283,7 +287,7 @@ def new_parse(marketPlace, url, createLog): try: persist_data(url, tuple(rec), cur) con.commit() - except: + except Exception as e: trace = traceback.format_exc() @@ -307,6 +311,7 @@ def new_parse(marketPlace, url, createLog): shutil.move(source, destination) num_persisted_moved += 1 except: + print("There was a problem to move the file " + detPage[key]['filename'] + " in the Description section!") nError += 1 if createLog: diff --git a/MarketPlaces/Utilities/utilities.py b/MarketPlaces/Utilities/utilities.py index b1ecba4..60798fb 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"]*style=\"[^\"]*background-image.*?>", "", clean_html) + clean_html = re.sub(r"]*style=\"[^\"]*background-image.*?>|background-image:url\(\'(.*?)\'\);", "", clean_html) return clean_html diff --git a/setup.ini b/setup.ini index 3ff6f3e..1202985 100644 --- a/setup.ini +++ b/setup.ini @@ -1,17 +1,15 @@ [TOR] -firefox_binary_path = C:\Users\dabadcuber5\Desktop\Tor Browser\Browser\firefox.exe -firefox_profile_path = C:\Users\dabadcuber5\Desktop\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default -geckodriver_path = C:\Users\dabadcuber5\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\dabadcuber5\dw_pipeline_test -shared_folder = \\Mac\\Shared - - +project_directory = C:\Users\John Wick\PycharmProjects\dw_pipeline_test +shared_folder = Z:\VBoxSvr\VM_Files_ (shared) [PostgreSQL] ip = localhost username = postgres -password = Ilovelucky1! +password = postgres database = darkweb_markets_forums \ No newline at end of file