westernmeadow
1 year ago
8 changed files with 612 additions and 162 deletions
Unified View
Diff Options
-
+12 -10MarketPlaces/Ares/crawler_selenium.py
-
+30 -97MarketPlaces/Ares/parser.py
-
+8 -9MarketPlaces/Kingdom/crawler_selenium.py
-
+28 -34MarketPlaces/Kingdom/parser.py
-
+8 -5MarketPlaces/Quest/crawler_selenium.py
-
+25 -7MarketPlaces/Quest/parser.py
-
+263 -0MarketPlaces/Sonanza/crawler_selenium.py
-
+238 -0MarketPlaces/Sonanza/parser.py
+ 12
- 10
MarketPlaces/Ares/crawler_selenium.py
View File
+ 30
- 97
MarketPlaces/Ares/parser.py
View File
+ 8
- 9
MarketPlaces/Kingdom/crawler_selenium.py
View File
+ 28
- 34
MarketPlaces/Kingdom/parser.py
View File
+ 8
- 5
MarketPlaces/Quest/crawler_selenium.py
View File
+ 25
- 7
MarketPlaces/Quest/parser.py
View File
+ 263
- 0
MarketPlaces/Sonanza/crawler_selenium.py
View File
| @ -0,0 +1,263 @@ | |||||
| __author__ = 'DarkWeb' | |||||
| ''' | |||||
| Sonanza Marketplace Crawler (Selenium) | |||||
| ''' | |||||
| from selenium import webdriver | |||||
| from selenium.common.exceptions import NoSuchElementException | |||||
| from selenium.webdriver.firefox.firefox_profile import FirefoxProfile | |||||
| from selenium.webdriver.firefox.firefox_binary import FirefoxBinary | |||||
| from selenium.webdriver.firefox.service import Service | |||||
| from selenium.webdriver.support.ui import WebDriverWait | |||||
| from selenium.webdriver.support.ui import Select | |||||
| from selenium.webdriver.support import expected_conditions as EC | |||||
| from selenium.webdriver.common.by import By | |||||
| from PIL import Image | |||||
| import urllib.parse as urlparse | |||||
| import os, re, time | |||||
| from datetime import date | |||||
| import subprocess | |||||
| import configparser | |||||
| from bs4 import BeautifulSoup | |||||
| from MarketPlaces.Initialization.prepare_parser import new_parse | |||||
| from MarketPlaces.Sonanza.parser import sonanza_links_parser | |||||
| from MarketPlaces.Utilities.utilities import cleanHTML | |||||
| counter = 1 | |||||
| baseURL = 'http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/' | |||||
| def startCrawling(): | |||||
| mktName = getMKTName() | |||||
| driver = getAccess() | |||||
| if driver != 'down': | |||||
| try: | |||||
| login(driver) | |||||
| crawlForum(driver) | |||||
| except Exception as e: | |||||
| print(driver.current_url, e) | |||||
| closeDriver(driver) | |||||
| new_parse(mktName, baseURL, True) | |||||
| # Returns the name of the website | |||||
| def getMKTName(): | |||||
| name = 'Sonanza' | |||||
| return name | |||||
| # Return the base link of the website | |||||
| def getFixedURL(): | |||||
| url = 'http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/' | |||||
| return url | |||||
| # Closes Tor Browser | |||||
| def closeDriver(driver): | |||||
| # global pid | |||||
| # os.system("taskkill /pid " + str(pro.pid)) | |||||
| # os.system("taskkill /t /f /im tor.exe") | |||||
| print('Closing Tor...') | |||||
| driver.close() | |||||
| time.sleep(3) | |||||
| return | |||||
| # Creates FireFox 'driver' and configure its 'Profile' | |||||
| # to use Tor proxy and socket | |||||
| def createFFDriver(): | |||||
| from MarketPlaces.Initialization.markets_mining import config | |||||
| ff_binary = FirefoxBinary(config.get('TOR', 'firefox_binary_path')) | |||||
| ff_prof = FirefoxProfile(config.get('TOR', 'firefox_profile_path')) | |||||
| ff_prof.set_preference("places.history.enabled", False) | |||||
| ff_prof.set_preference("privacy.clearOnShutdown.offlineApps", True) | |||||
| ff_prof.set_preference("privacy.clearOnShutdown.passwords", True) | |||||
| ff_prof.set_preference("privacy.clearOnShutdown.siteSettings", True) | |||||
| ff_prof.set_preference("privacy.sanitize.sanitizeOnShutdown", True) | |||||
| ff_prof.set_preference("signon.rememberSignons", False) | |||||
| ff_prof.set_preference("network.cookie.lifetimePolicy", 2) | |||||
| ff_prof.set_preference("network.dns.disablePrefetch", True) | |||||
| ff_prof.set_preference("network.http.sendRefererHeader", 0) | |||||
| ff_prof.set_preference("permissions.default.image", 3) | |||||
| ff_prof.set_preference("browser.download.folderList", 2) | |||||
| ff_prof.set_preference("browser.download.manager.showWhenStarting", False) | |||||
| ff_prof.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain") | |||||
| ff_prof.set_preference('network.proxy.type', 1) | |||||
| ff_prof.set_preference("network.proxy.socks_version", 5) | |||||
| ff_prof.set_preference('network.proxy.socks', '127.0.0.1') | |||||
| ff_prof.set_preference('network.proxy.socks_port', 9150) | |||||
| ff_prof.set_preference('network.proxy.socks_remote_dns', True) | |||||
| ff_prof.set_preference("javascript.enabled", False) | |||||
| ff_prof.update_preferences() | |||||
| service = Service(config.get('TOR', 'geckodriver_path')) | |||||
| driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) | |||||
| driver.maximize_window() | |||||
| return driver | |||||
| #the driver 'gets' the url, attempting to get on the site, if it can't access return 'down' | |||||
| def getAccess(): | |||||
| url = getFixedURL() | |||||
| driver = createFFDriver() | |||||
| try: | |||||
| driver.get(url) | |||||
| return driver | |||||
| except: | |||||
| driver.close() | |||||
| return 'down' | |||||
| def login(driver): | |||||
| # input("Press ENTER when CAPTCHA is complete and login page has loaded\n") | |||||
| # | |||||
| # # entering username and password into input boxes | |||||
| # usernameBox = driver.find_element(by=By.XPATH, value='//input[@name="username"]') | |||||
| # # Username here | |||||
| # usernameBox.send_keys('aliciamykeys') | |||||
| # passwordBox = driver.find_element(by=By.XPATH, value='//input[@name="password"]') | |||||
| # # Password here | |||||
| # passwordBox.send_keys('aliciawherearemykey$') | |||||
| # # session time | |||||
| # session_select = Select(driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[4]/div/div[2]/select')) | |||||
| # session_select.select_by_visible_text('Session 60min') | |||||
| input("Press ENTER when CAPTCHA is completed and listing page loaded\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, '//*[@id="searchbar"]'))) | |||||
| def savePage(driver, page, url): | |||||
| cleanPage = cleanHTML(driver, page) | |||||
| filePath = getFullPathName(url) | |||||
| os.makedirs(os.path.dirname(filePath), exist_ok=True) | |||||
| open(filePath, 'wb').write(cleanPage.encode('utf-8')) | |||||
| return | |||||
| def getFullPathName(url): | |||||
| from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE | |||||
| mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getMKTName() + "/HTML_Pages") | |||||
| fileName = getNameFromURL(url) | |||||
| if isDescriptionLink(url): | |||||
| fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html') | |||||
| else: | |||||
| fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html') | |||||
| return fullPath | |||||
| def 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 = [] | |||||
| # Guides and Tutorials | |||||
| links.append('http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/category/3') | |||||
| # Software and Malware | |||||
| links.append('http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/category/4') | |||||
| # Fraud | |||||
| links.append('http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/category/5') | |||||
| # Digital Products | |||||
| links.append('http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/category/21') | |||||
| # Services | |||||
| links.append('http://sonanzazddbd3lqw2ai6uwmnb4fx7tj7h6hmdwkfqe7bnzgpuvkxqpyd.onion/category/22') | |||||
| return links | |||||
| def crawlForum(driver): | |||||
| print("Crawling the Sonanza market") | |||||
| linksToCrawl = getInterestedLinks() | |||||
| i = 0 | |||||
| while i < len(linksToCrawl): | |||||
| link = linksToCrawl[i] | |||||
| print('Crawling :', link) | |||||
| try: | |||||
| has_next_page = True | |||||
| count = 0 | |||||
| while has_next_page: | |||||
| try: | |||||
| driver.get(link) | |||||
| except: | |||||
| driver.refresh() | |||||
| html = driver.page_source | |||||
| savePage(driver, html, link) | |||||
| list = productPages(html) | |||||
| for item in list: | |||||
| itemURL = urlparse.urljoin(baseURL, str(item)) | |||||
| try: | |||||
| driver.get(itemURL) | |||||
| except: | |||||
| driver.refresh() | |||||
| savePage(driver, driver.page_source, item) | |||||
| driver.back() | |||||
| # # comment out | |||||
| # break | |||||
| # | |||||
| # # comment out | |||||
| # if count == 1: | |||||
| # break | |||||
| try: | |||||
| link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "›")]').get_attribute('href') | |||||
| if link == "": | |||||
| raise NoSuchElementException | |||||
| count += 1 | |||||
| except NoSuchElementException: | |||||
| has_next_page = False | |||||
| except Exception as e: | |||||
| print(link, e) | |||||
| i += 1 | |||||
| print("Crawling the Sonanza market done.") | |||||
| # Returns 'True' if the link is Topic link, may need to change for every website | |||||
| def isDescriptionLink(url): | |||||
| if 'article' in url: | |||||
| return True | |||||
| return False | |||||
| # Returns True if the link is a listingPage link, may need to change for every website | |||||
| def isListingLink(url): | |||||
| if 'category' in url: | |||||
| return True | |||||
| return False | |||||
| def productPages(html): | |||||
| soup = BeautifulSoup(html, "html.parser") | |||||
| return sonanza_links_parser(soup) | |||||
| def crawler(): | |||||
| startCrawling() | |||||
+ 238
- 0
MarketPlaces/Sonanza/parser.py
View File
| @ -0,0 +1,238 @@ | |||||
| __author__ = 'DarkWeb' | |||||
| # Here, we are importing the auxiliary functions to clean or convert data | |||||
| from MarketPlaces.Utilities.utilities import * | |||||
| # Here, we are importing BeautifulSoup to search through the HTML tree | |||||
| from bs4 import BeautifulSoup | |||||
| # parses description pages, so takes html pages of description pages using soup object, and parses it for info it needs | |||||
| # stores info it needs in different lists, these lists are returned after being organized | |||||
| # @param: soup object looking at html page of description page | |||||
| # return: 'row' that contains a variety of lists that each hold info on the description page | |||||
| def sonanza_description_parser(soup): | |||||
| # Fields to be parsed | |||||
| vendor = "-1" # 0 *Vendor_Name | |||||
| success = "-1" # 1 Vendor_Successful_Transactions | |||||
| rating_vendor = "-1" # 2 Vendor_Rating | |||||
| name = "-1" # 3 *Product_Name | |||||
| describe = "-1" # 4 Product_Description | |||||
| CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) | |||||
| MS = "-1" # 6 Product_MS_Classification (Microsoft Security) | |||||
| category = "-1" # 7 Product_Category | |||||
| views = "-1" # 8 Product_Number_Of_Views | |||||
| reviews = "-1" # 9 Product_Number_Of_Reviews | |||||
| rating_item = "-1" # 10 Product_Rating | |||||
| addDate = "-1" # 11 Product_AddedDate | |||||
| BTC = "-1" # 12 Product_BTC_SellingPrice | |||||
| USD = "-1" # 13 Product_USD_SellingPrice | |||||
| EURO = "-1" # 14 Product_EURO_SellingPrice | |||||
| sold = "-1" # 15 Product_QuantitySold | |||||
| left = "-1" # 16 Product_QuantityLeft | |||||
| shipFrom = "-1" # 17 Product_ShippedFrom | |||||
| shipTo = "-1" # 18 Product_ShippedTo | |||||
| image = "-1" # 19 Product_Image | |||||
| vendor_image = "-1" # 20 Vendor_Image | |||||
| listing = soup.find('div', {"id": "article_page"}) | |||||
| # Finding the Product | |||||
| name = listing.find('div', {"class": "row box"}).text | |||||
| name = cleanString(name).strip() | |||||
| # Finding Product Image | |||||
| product_image = listing.find('img') | |||||
| product_image = product_image.get('src') | |||||
| product_image = product_image.split('base64,')[-1] | |||||
| image = product_image | |||||
| table = listing.find('div', {"class": "col-md-5"}) | |||||
| # Finding Prices | |||||
| USD = table.find('span', {"class": "pr"}).text | |||||
| USD = USD.replace("$", "").strip() | |||||
| BTC = table.find_all('span', {"class": "pr1"})[1].text | |||||
| BTC = BTC.replace("BTC", "").strip() | |||||
| rows = table.find_all('p', {"class": "mb-0"}) | |||||
| for row in rows: | |||||
| temp = row.text | |||||
| if "CATEGORY" in temp: | |||||
| category = temp.replace("CATEGORY :", "") | |||||
| category = cleanString(category).strip() | |||||
| elif "VENDOR LEVEL" in temp: | |||||
| rating_vendor = temp.replace("VENDOR LEVEL :", "") | |||||
| rating_vendor = cleanString(rating_vendor).strip() | |||||
| rows = listing.find_all('p', {"class": "mb-1"}) | |||||
| for row in rows: | |||||
| temp = row.text | |||||
| if "VENDOR" in temp: | |||||
| vendor = temp.replace("VENDOR :", "") | |||||
| vendor = cleanString(vendor).strip() | |||||
| elif "SHIPS TO" in temp: | |||||
| shipTo = temp.replace("SHIPS TO :", "") | |||||
| shipTo = cleanString(shipTo).strip() | |||||
| elif "SOLD" in temp: | |||||
| sold = cleanNumbers(temp).strip() | |||||
| # Finding Product Description | |||||
| describe = listing.find('pre').text | |||||
| describe = cleanString(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, image, vendor_image) | |||||
| # Sending the results | |||||
| return row | |||||
| # parses listing pages, so takes html pages of listing pages using soup object, and parses it for info it needs | |||||
| # stores info it needs in different lists, these lists are returned after being organized | |||||
| # @param: soup object looking at html page of listing page | |||||
| # return: 'row' that contains a variety of lists that each hold info on the listing page | |||||
| def sonanza_listing_parser(soup): | |||||
| # Fields to be parsed | |||||
| nm = 0 # *Total_Products (Should be Integer) | |||||
| mktName = "Sonanza" # 0 *Marketplace_Name | |||||
| vendor = [] # 1 *Vendor y | |||||
| rating_vendor = [] # 2 Vendor_Rating | |||||
| success = [] # 3 Vendor_Successful_Transactions | |||||
| name = [] # 4 *Product_Name y | |||||
| CVE = [] # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about this | |||||
| MS = [] # 6 Product_MS_Classification (Microsoft Security) dont worry about this | |||||
| category = [] # 7 Product_Category y | |||||
| describe = [] # 8 Product_Description | |||||
| views = [] # 9 Product_Number_Of_Views | |||||
| reviews = [] # 10 Product_Number_Of_Reviews | |||||
| rating_item = [] # 11 Product_Rating | |||||
| addDate = [] # 12 Product_AddDate | |||||
| BTC = [] # 13 Product_BTC_SellingPrice | |||||
| USD = [] # 14 Product_USD_SellingPrice y | |||||
| EURO = [] # 15 Product_EURO_SellingPrice | |||||
| sold = [] # 16 Product_QuantitySold | |||||
| qLeft = [] # 17 Product_QuantityLeft | |||||
| shipFrom = [] # 18 Product_ShippedFrom | |||||
| shipTo = [] # 19 Product_ShippedTo | |||||
| image = [] # 20 Product_Image | |||||
| image_vendor = [] # 21 Vendor_Image | |||||
| href = [] # 22 Product_Links | |||||
| listings = soup.findAll('div', {"class": "col-sm-4 col-md-3"}) | |||||
| # Populating the Number of Products | |||||
| nm = len(listings) | |||||
| for listing in listings: | |||||
| # Adding the url to the list of urls | |||||
| bae = listing.find('a', href=True) | |||||
| link = bae.get('href') | |||||
| href.append(link) | |||||
| # Finding Product Image | |||||
| product_image = listing.find('img') | |||||
| product_image = product_image.get('src') | |||||
| product_image = product_image.split('base64,')[-1] | |||||
| image.append(product_image) | |||||
| # Finding the Product | |||||
| product = listing.find('h5', {"class": "art_title"}).text | |||||
| product = cleanString(product) | |||||
| name.append(product.strip()) | |||||
| # Finding Prices | |||||
| price = listing.find('span', {"class": "priceP"}).text | |||||
| price = price.replace("$", "") | |||||
| USD.append(price.strip()) | |||||
| rows = listing.find_all('p', {"class": "mb-0 card-text"}) | |||||
| for row in rows: | |||||
| temp = row.text | |||||
| if "CATEGORY" in temp: | |||||
| cat = temp.replace("CATEGORY :", "") | |||||
| cat = cleanString(cat) | |||||
| category.append(cat.strip()) | |||||
| elif "VENDOR" in temp: | |||||
| vendor_name = temp.replace("VENDOR :", "") | |||||
| vendor_name = cleanString(vendor_name) | |||||
| vendor.append(vendor_name.strip()) | |||||
| # Finding Vendor Rating | |||||
| rating = listing.find('span', {"class": "badge badge-info"}).text | |||||
| rating = rating.replace("VENDOR LEVEL :", "") | |||||
| rating = cleanString(rating) | |||||
| rating_vendor.append(rating.strip()) | |||||
| # Searching for CVE and MS categories | |||||
| cve = listing.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 = listing.findAll(text=re.compile('MS\d{2}-\d{3}')) | |||||
| if not ms: | |||||
| MSValue = "-1" | |||||
| else: | |||||
| me = " " | |||||
| for im in ms: | |||||
| me += (im) | |||||
| me += " " | |||||
| me = me.replace(',', ' ') | |||||
| me = me.replace('\n', '') | |||||
| MSValue = me | |||||
| MS.append(MSValue) | |||||
| # Populate the final variable (this should be a list with all fields scraped) | |||||
| return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, | |||||
| reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image, image_vendor) | |||||
| # called by the crawler to get description links on a listing page | |||||
| # @param: beautifulsoup object that is using the correct html page (listing page) | |||||
| # return: list of description links from a listing page | |||||
| def sonanza_links_parser(soup): | |||||
| # Returning all links that should be visited by the Crawler | |||||
| href = [] | |||||
| listings = soup.findAll('div', {"class": "col-sm-4 col-md-3"}) | |||||
| for listing in listings: | |||||
| a = listing.find('a', href=True) | |||||
| # Adding the url to the list of urls | |||||
| link = a.get('href') | |||||
| href.append(link) | |||||
| return href | |||||