Added incomplete MGM crawler manually due to issues with vm

MarketPlaces/MGMGrand/crawler_selenium.py

@@ -0,0 +1,277 @@
+__author__ = 'DarkWeb'
+
+'''
+MGMGrand 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.MGMGrand.parser import mgm_links_parser
+from MarketPlaces.Utilities.utilities import cleanHTML
+
+counter = 1
+baseURL = 'http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.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 = 'MGMGrand'
+    return name
+
+
+# Return the base link of the website
+def getFixedURL():
+    url = 'http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.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):
+    WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
+        (By.XPATH, '//*[@id="username"]')))
+
+    # entering username and password into input boxes
+    usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
+    # Username here
+    usernameBox.send_keys('blabri')
+    passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
+    # Password here
+    passwordBox.send_keys('fishowal')
+
+    input("Press ENTER when captcha is solved and you're logged in")
+
+    # Wait for the element to be visible
+    WebDriverWait(driver, 100).until(
+        EC.visibility_of_element_located((By.XPATH, '/html/body/div[2]/div[2]/a/span'))
+    )
+
+    # Find the element and click it
+    temp = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/a/span')
+    temp.click()
+
+
+def savePage(driver, page, url):
+    cleanPage = cleanHTML(driver, page)
+    filePath = getFullPathName(url)
+    os.makedirs(os.path.dirname(filePath), exist_ok=True)
+    open(filePath, 'wb').write(cleanPage.encode('utf-8'))
+    return
+
+
+def getFullPathName(url):
+    from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE
+
+    mainDir = os.path.join(config.get('Project', 'shared_folder'), "MarketPlaces/" + getMKTName() + "/HTML_Pages")
+    fileName = getNameFromURL(url)
+    if isDescriptionLink(url):
+        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Description\\' + fileName + '.html')
+    else:
+        fullPath = os.path.join(mainDir, CURRENT_DATE + r'\\Listing\\' + fileName + '.html')
+    return fullPath
+
+
+def getMKTName() -> str:
+    name = 'MGMGrand'
+    return name
+
+
+def getNameFromURL(url):
+    global counter
+    name = ''.join(e for e in url if e.isalnum())
+    if name == '':
+        name = str(counter)
+        counter = counter + 1
+    return name
+
+
+def getInterestedLinks():
+    links = []
+
+
+    # Carding
+    links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/c54f4d30-9060-11eb-be9c-630550815967')
+    # # softwares and malwares
+    # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/6a211fa0-9062-11eb-b3bd-d7d946c69ce2')
+    # # social engineering tutorial
+    # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/5596f690-9063-11eb-9ebb-6b44dbdbc454')
+    # # misc services
+    # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/b212fe30-9063-11eb-a479-35581612f6c2')
+    # # hacking tutorials
+    # links.append('http://duysanjqxo4svh35yqkxxe5r54z2xc5tjf6r3ichxd3m2rwcgabf44ad.onion/category/2ed713f0-9063-11eb-bf9c-232fd3b49a98')
+    return links
+
+
+def crawlForum(driver):
+
+    print("Crawling the MGM 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 == 4:
+                #     break
+
+                try:
+                    li_tags = driver.find_element(by=By.CLASS_NAME, value='pagination mb-0').find_elements(by=By.TAG_NAME, value='li')
+                    a_tag = li_tags[-1].find_element(by=By.TAG_NAME, value='a')
+                    if a_tag:
+                        try:
+                            link = a_tag.get_attribute('href')
+                            print(link)
+                        except:
+                            link = ''
+                    if link == "":
+                        raise NoSuchElementException
+                    count += 1
+
+                except NoSuchElementException:
+                    has_next_page = False
+
+        except Exception as e:
+            print(link, e)
+        i += 1
+
+    print("Crawling the MGMGrand market done.")
+
+
+# Returns 'True' if the link is Topic link, may need to change for every website
+def isDescriptionLink(url):
+    if 'product' 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 mgm_links_parser(soup)
+
+
+def crawler():
+    startCrawling()