diff --git a/.idea/DW_Pipeline_Test.iml b/.idea/DW_Pipeline_Test.iml index c554b68..08a5719 100644 --- a/.idea/DW_Pipeline_Test.iml +++ b/.idea/DW_Pipeline_Test.iml @@ -10,10 +10,23 @@ diff --git a/.idea/misc.xml b/.idea/misc.xml index 91bfa41..dc9ea49 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/Forums/AbyssForum/crawler_selenium.py b/Forums/AbyssForum/crawler_selenium.py index 129e6dc..4823db2 100644 --- a/Forums/AbyssForum/crawler_selenium.py +++ b/Forums/AbyssForum/crawler_selenium.py @@ -32,15 +32,15 @@ baseURL = 'http://qyvjopwdgjq52ehsx6paonv2ophy3p4ivfkul4svcaw6qxlzsaboyjid.onion def startCrawling(): # opentor() forumName = getForumName() - # 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(forumName, baseURL, True) @@ -121,6 +121,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver def getAccess(): @@ -241,14 +243,14 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: break try: - link = driver.find_element(by=By.XPATH, value = '/html/body/div[2]/div[2]/div[2]/div[2]/ul/li[9]/a').get_attribute('href') + link = driver.find_element(by=By.XPATH, value='/html/body/div[2]/div[2]/div[2]/div[2]/ul/li[9]/a').get_attribute('href') if link == "": raise NoSuchElementException count += 1 diff --git a/Forums/Altenens/crawler_selenium.py b/Forums/Altenens/crawler_selenium.py index 0f14223..e996150 100644 --- a/Forums/Altenens/crawler_selenium.py +++ b/Forums/Altenens/crawler_selenium.py @@ -42,7 +42,7 @@ def startCrawling(): print(driver.current_url, e) closetor(driver) - # new_parse(forumName, baseURL, True) + new_parse(forumName, baseURL, True) # Opens Tor Browser @@ -118,8 +118,8 @@ def createFFDriver(): 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("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) @@ -136,6 +136,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -253,7 +255,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: @@ -272,7 +274,7 @@ def crawlForum(driver): print(link, e) i += 1 - input("Crawling Altenens forum done successfully. Press ENTER to continue\n") + print("Crawling the Altenens forum done.") # Returns 'True' if the link is Topic link, may need to change for every website diff --git a/Forums/BestCardingWorld/crawler_selenium.py b/Forums/BestCardingWorld/crawler_selenium.py index 96821cd..22f6077 100644 --- a/Forums/BestCardingWorld/crawler_selenium.py +++ b/Forums/BestCardingWorld/crawler_selenium.py @@ -114,6 +114,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -238,8 +240,8 @@ def crawlForum(driver): try: nav = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div[2]/div[4]/ul') - li = nav.find_element_by_class_name('next') - page = li.find_element_by_tag_name('a').get_attribute('href') + li = nav.find_element(by=By.CLASS_NAME, value='next') + page = li.find_element(by=By.TAG_NAME, value='a').get_attribute('href') if page == "": raise NoSuchElementException counter += 1 @@ -252,7 +254,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: @@ -260,8 +262,8 @@ def crawlForum(driver): try: bar = driver.find_element(by=By.XPATH, value='/html/body/div[1]/div[2]/div[2]/div[3]/ul') - next = bar.find_element_by_class_name('next') - link = next.find_element_by_tag_name('a').get_attribute('href') + next = bar.find_element(by=By.CLASS_NAME, value='next') + link = next.find_element(by=By.TAG_NAME, value='a').get_attribute('href') if link == "": raise NoSuchElementException count += 1 @@ -273,7 +275,7 @@ def crawlForum(driver): print(link, e) i += 1 - input("Crawling BestCardingWorld forum done sucessfully. Press ENTER to continue\n") + print("Crawling the BestCardingWorld forum done.") # Returns 'True' if the link is a description link diff --git a/Forums/BestCardingWorld/parser.py b/Forums/BestCardingWorld/parser.py index 540435a..c4ca6e0 100644 --- a/Forums/BestCardingWorld/parser.py +++ b/Forums/BestCardingWorld/parser.py @@ -152,7 +152,7 @@ def bestcardingworld_description_parser(soup): # Populate the final variable (this should be a list with all fields scraped) - row = (topic, post, user, addDate, feedback, status, reputation, sign, interest) + row = (topic, user, status, reputation, interest, sign, post, feedback, addDate) # Sending the results @@ -166,15 +166,17 @@ def bestcardingworld_description_parser(soup): #return: 'row' that contains a variety of lists that each hold info on the listing page def bestcardingworld_listing_parser(soup): - nm = 0 # this variable should receive the number of topics - topic = [] # 1 all topics - board = "-1" # 2 board name (the previous level of the topic in the Forum categorization tree. + nm = 0 # *this variable should receive the number of topics + forum = "BestCardingWorld" # 0 *forum name + board = "-1" # 1 *board name (the previous level of the topic in the Forum categorization tree. # For instance: Security/Malware/Tools to hack Facebook. The board here should be Malware) - view = [] # 3 number of views of each topic - post = [] # 4 number of posts of each topic - user = [] # 5 all users of each topic - addDate = [] # 6 when the topic was created (difficult to find) - href = [] # 16 this variable should receive all cleaned urls (we will use this to do the marge between Listing and Description pages) + author = [] # 2 *all authors of each topic + topic = [] # 3 *all topics + views = [] # 4 number of views of each topic + posts = [] # 5 number of posts of each topic + href = [] # 6 this variable should receive all cleaned urls (we will use this to do the marge between + # Listing and Description pages) + addDate = [] # 7 when the topic was created (difficult to find) # Finding the board (should be just one) @@ -187,7 +189,12 @@ def bestcardingworld_listing_parser(soup): itopics = soup.find('ul', {"class": "topiclist topics"}).findAll('div',{"class": "list-inner"}) replies = soup.find('ul', {"class": "topiclist topics"}).findAll('dd',{"class": "posts"}) - views = soup.find('ul', {"class": "topiclist topics"}).findAll('dd',{"class": "views"}) + view = soup.find('ul', {"class": "topiclist topics"}).findAll('dd',{"class": "views"}) + + # Counting how many topics we have found so far + + nm = len(itopics) + index = 0 for itopic in itopics: @@ -213,10 +220,6 @@ def bestcardingworld_listing_parser(soup): topics = itopic.find('a', {"class": "topictitle"}).text topic.append(cleanString(topics)) - # Counting how many topics we have found so far - - nm = len(topic) - # Adding the url to the list of urls link = itopic.find('a', {"class": "topictitle"}).get('href') link = cleanLink(link) @@ -224,18 +227,18 @@ def bestcardingworld_listing_parser(soup): # Finding the author of the topic ps = itopic.find('div', {"class":"responsive-hide"}).find('a', {"class": "username-coloured"}).text - author = ps.strip() - user.append(cleanString(author)) + user = ps.strip() + author.append(cleanString(user)) # Finding the number of replies - posts = replies[index].text.split()[0] - posts = posts.strip() - post.append(cleanString(posts)) + post = replies[index].text.split()[0] + post = post.strip() + posts.append(cleanString(post)) # Finding the number of Views - tview = views[index].text.split()[0] + tview = view[index].text.split()[0] tview = tview.strip() - view.append(cleanString(tview)) + views.append(cleanString(tview)) # If no information about when the topic was added, just assign "-1" to the variable #CryptBB doesn't show when topic was first posted on listing page @@ -245,10 +248,9 @@ def bestcardingworld_listing_parser(soup): addDate.append(date_time_obj) #addDate.append("-1") - - index += 1 - return organizeTopics("BestCardingWorld", nm, topic, board, view, post, user, addDate, href) + + return organizeTopics(forum, nm, board, author, topic, views, posts, href, addDate) #called by the crawler to get description links on a listing page diff --git a/Forums/Cardingleaks/crawler_selenium.py b/Forums/Cardingleaks/crawler_selenium.py index 85538fd..70200ff 100644 --- a/Forums/Cardingleaks/crawler_selenium.py +++ b/Forums/Cardingleaks/crawler_selenium.py @@ -34,15 +34,15 @@ baseURL = 'https://leaks.ws/' def startCrawling(): # opentor() forumName = getForumName() - # 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(forumName, baseURL, True) @@ -144,6 +144,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -159,7 +161,7 @@ def getAccess(): # Saves the crawled html page -def savePage(page, url): +def savePage(driver, page, url): cleanPage = cleanHTML(driver, page) filePath = getFullPathName(url) os.makedirs(os.path.dirname(filePath), exist_ok=True) @@ -242,7 +244,7 @@ def crawlForum(driver): driver.get(itemURL) except: driver.refresh() - savePage(driver.page_source, topic + f"page{counter}") # very important + savePage(driver, driver.page_source, topic + f"page{counter}") # very important # comment out if counter == 2: @@ -261,7 +263,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/Forums/CryptBB/crawler_selenium.py b/Forums/CryptBB/crawler_selenium.py index 5e98a7d..a462a65 100644 --- a/Forums/CryptBB/crawler_selenium.py +++ b/Forums/CryptBB/crawler_selenium.py @@ -30,15 +30,15 @@ baseURL = 'http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion def startCrawling(): # opentor() forumName = getForumName() - # 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(forumName, baseURL, True) @@ -162,6 +162,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -289,7 +291,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/Forums/CryptBB/parser.py b/Forums/CryptBB/parser.py index 7fbd56d..bcef5f8 100644 --- a/Forums/CryptBB/parser.py +++ b/Forums/CryptBB/parser.py @@ -124,7 +124,7 @@ def cryptBB_description_parser(soup): stime = dt.replace('Yesterday,','').strip() date_time_obj = yesterday+ ', '+stime date_time_obj = datetime.strptime(date_time_obj,'%m-%d-%Y, %I:%M %p') - elif "hours ago" in dt: + elif "hour ago" in dt or "hours ago" in dt: day = day.strftime('%m-%d-%Y') date_time_obj = postarea.find('span', {"class": "post_date"}).find('span')['title'] date_time_obj = datetime.strptime(date_time_obj, '%m-%d-%Y, %I:%M %p') diff --git a/Forums/DB_Connection/db_connection.py b/Forums/DB_Connection/db_connection.py index fc29c07..8bb03bb 100644 --- a/Forums/DB_Connection/db_connection.py +++ b/Forums/DB_Connection/db_connection.py @@ -2,7 +2,6 @@ __author__ = 'DarkWeb' import psycopg2 import traceback -import configparser def connectDataBase(): diff --git a/Forums/HiddenAnswers/crawler_selenium.py b/Forums/HiddenAnswers/crawler_selenium.py index 6641b81..392c90f 100644 --- a/Forums/HiddenAnswers/crawler_selenium.py +++ b/Forums/HiddenAnswers/crawler_selenium.py @@ -32,15 +32,15 @@ baseURL = 'http://7eoz4h2nvw4zlr7gvlbutinqqpm546f5egswax54az6lt2u7e3t6d7yd.onion def startCrawling(): # opentor() forumName = getForumName() - # driver: webdriver.Firefox = getAccess() - # - # if driver != 'down': - # try: - # login(driver) - # crawlForum(driver) - # except Exception as e: - # print(driver.current_url, e) - # closetor(driver) + driver: webdriver.Firefox = getAccess() + + if driver != 'down': + try: + login(driver) + crawlForum(driver) + except Exception as e: + print(driver.current_url, e) + closetor(driver) new_parse(forumName, baseURL, True) @@ -121,6 +121,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver def getAccess(): @@ -235,7 +237,7 @@ def crawlForum(driver: webdriver.Firefox): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/Forums/HiddenAnswers/parser.py b/Forums/HiddenAnswers/parser.py index 1a3ee2d..16b56cb 100644 --- a/Forums/HiddenAnswers/parser.py +++ b/Forums/HiddenAnswers/parser.py @@ -127,15 +127,18 @@ def HiddenAnswers_listing_parser(soup: BeautifulSoup): if date_posted.find("day") > 0: datetime_obj = datetime.now() - timedelta(days=1) else: - datetime_obj = datetime.strptime(f"{date_posted} {date.today().year}", "%b %d %Y") + try: + datetime_obj = datetime.strptime(f"{date_posted} {date.today().year}", "%b %d %Y") + except ValueError: + datetime_obj = datetime.strptime(f"{date_posted}", "%b %d, %Y") addDate.append(datetime_obj) #this link will be cleaned listing_href = queries.find("div", {"class": "qa-q-item-title"}).find("a").get("href") href.append(listing_href) -#need to change this method nm = len(topic) + return organizeTopics(forum, nm, board, user, topic, view, post, href, addDate) #need to change this method diff --git a/Forums/Initialization/forumsList.txt b/Forums/Initialization/forumsList.txt index 3526771..efa9686 100644 --- a/Forums/Initialization/forumsList.txt +++ b/Forums/Initialization/forumsList.txt @@ -1,9 +1 @@ -AbyssForum -Altenens -BestCardingWorld -Cardingleaks -CryptBB -HiddenAnswers -Libre -OnniForums -Procrax \ No newline at end of file +BestCardingWorld \ No newline at end of file diff --git a/Forums/Initialization/prepare_parser.py b/Forums/Initialization/prepare_parser.py index 272cb44..1f089e6 100644 --- a/Forums/Initialization/prepare_parser.py +++ b/Forums/Initialization/prepare_parser.py @@ -12,6 +12,7 @@ from Forums.OnniForums.parser import * from Forums.Altenens.parser import * from Forums.Procrax.parser import * from Forums.Libre.parser import * +from Forums.HiddenAnswers.parser import * from Forums.Classifier.classify_product import predict # from DarkWebMining_Sample.Forums.Classifier.classify_product import predict_semi @@ -126,6 +127,8 @@ def parse_listing(forum, listingFile, soup, createLog, logFile): rw = procrax_listing_parser(soup) elif forum == "Libre": rw = libre_listing_parser(soup) + elif forum == "HiddenAnswers": + rw = HiddenAnswers_listing_parser(soup) else: print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!") raise Exception @@ -160,6 +163,8 @@ def parse_description(forum, descriptionFile, soup, createLog, logFile): rmm = procrax_description_parser(soup) elif forum == "Libre": rmm = libre_description_parser(soup) + elif forum == "HiddenAnswers": + rmm = HiddenAnswers_description_parser(soup) else: print("MISSING CALL TO DESCRIPTION PARSER IN PREPARE_PARSER.PY!") raise Exception diff --git a/Forums/Libre/crawler_selenium.py b/Forums/Libre/crawler_selenium.py index d06cd83..1033474 100644 --- a/Forums/Libre/crawler_selenium.py +++ b/Forums/Libre/crawler_selenium.py @@ -30,15 +30,15 @@ baseURL = 'http://libreeunomyly6ot7kspglmbd5cvlkogib6rozy43r2glatc6rmwauqd.onion def startCrawling(): # opentor() forumName = getForumName() - # 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(forumName, baseURL, True) @@ -144,6 +144,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -255,7 +257,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: @@ -275,7 +277,7 @@ def crawlForum(driver): print(link, e) i += 1 - input("Crawling the Libre forum done.") + print("Crawling the Libre forum done.") # Returns 'True' if the link is Topic link, may need to change for every website diff --git a/Forums/OnniForums/crawler_selenium.py b/Forums/OnniForums/crawler_selenium.py index 58b1313..0888d14 100644 --- a/Forums/OnniForums/crawler_selenium.py +++ b/Forums/OnniForums/crawler_selenium.py @@ -33,15 +33,15 @@ baseURL = 'http://onnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qd.onion def startCrawling(): # opentor() forumName = getForumName() - # 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(forum=forumName, url=baseURL, createLog=True) @@ -139,6 +139,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver @@ -267,7 +269,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/Forums/OnniForums/parser.py b/Forums/OnniForums/parser.py index 393e6b3..3854141 100644 --- a/Forums/OnniForums/parser.py +++ b/Forums/OnniForums/parser.py @@ -139,12 +139,14 @@ def onniForums_listing_parser(soup: BeautifulSoup): nm = len(thread_arrays) for thread in thread_arrays: #getting the information from the posts and sorting them into the arrays defined above - - try: - post_subject: str = thread.find("span",{"class": "subject_new"}).text #getting the topic + + body = thread.find("span",{"class": "subject_new"}) + try: + post_subject: str = body.text #getting the topic except AttributeError: - post_subject: str = thread.find("span",{"class": "subject_old"}).text + body = thread.find("span",{"class": "subject_old"}) + post_subject: str = body.text post_subject_cleaned = cleanString(post_subject.strip()) topic.append(post_subject_cleaned) @@ -163,9 +165,8 @@ def onniForums_listing_parser(soup: BeautifulSoup): author = thread.find("span",{"class" : "author smalltext"}).text author_cleaned = cleanString(author.strip()) user.append(author_cleaned) - - reply_anchor = thread.find_all("td", {"align": "center"})[2].find('a') - thread_link = reply_anchor.get('href') + + thread_link = body.find('a').get('href') href.append(thread_link) return organizeTopics( diff --git a/Forums/Procrax/crawler_selenium.py b/Forums/Procrax/crawler_selenium.py index f2ed372..2a8be96 100644 --- a/Forums/Procrax/crawler_selenium.py +++ b/Forums/Procrax/crawler_selenium.py @@ -33,15 +33,15 @@ FORUM_NAME = 'Procrax' # Opens Tor Browser, crawls the website def startCrawling(): # opentor() - # 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( forum=FORUM_NAME, @@ -140,6 +140,8 @@ def createFFDriver(): driver = webdriver.Firefox(firefox_binary=ff_binary, firefox_profile=ff_prof, service=service) + driver.maximize_window() + return driver def getAccess(): @@ -257,7 +259,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/AnonymousMarketplace/crawler_selenium.py b/MarketPlaces/AnonymousMarketplace/crawler_selenium.py index 99b4431..f7f9f17 100644 --- a/MarketPlaces/AnonymousMarketplace/crawler_selenium.py +++ b/MarketPlaces/AnonymousMarketplace/crawler_selenium.py @@ -187,12 +187,8 @@ def getNameFromURL(url): def getInterestedLinks(): links = [] - # # carding - # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/carding/') - # # hacked paypal - # links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacked-paypal-accounts/') - # hacking services - links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/product-category/hacking-services/') + # home + links.append('http://3fqr7fgjaslhgmeiin5e2ky6ra5xkiafyzg7i36sfcehv3jvpgydteqd.onion/') return links @@ -232,7 +228,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: @@ -240,7 +236,7 @@ def crawlForum(driver): #left in in case site changes try: - link = "" + link = driver.find_element(by=By.LINK_TEXT, value="→").get_attribute('href') if link == "": raise NoSuchElementException count += 1 diff --git a/MarketPlaces/AnonymousMarketplace/parser.py b/MarketPlaces/AnonymousMarketplace/parser.py index 08dbaa3..a85934c 100644 --- a/MarketPlaces/AnonymousMarketplace/parser.py +++ b/MarketPlaces/AnonymousMarketplace/parser.py @@ -41,12 +41,12 @@ def anonymousMarketplace_description_parser(soup: Tag): describe_output += div.text describe = cleanString(describe_output.strip()) - product_ratings: Tag = soup.find("div", {"class": "star-rating"}) + product_ratings: Tag = soup.find("div", {"class": "woocommerce-product-rating"}) - product_reviews = product_ratings.find("div", {"class": "woocommerce-product-rating"}).find("strong", {"class": "rating"}).text + product_reviews = product_ratings.find("span", {"class": "rating"}).text reviews = cleanString(product_reviews.strip()) - product_star_rating = product_ratings.find("span", {"class": "rating"}).text + product_star_rating = product_ratings.find("strong", {"class": "rating"}).text rating_item = cleanString(product_star_rating.strip()) product_price = soup.find("span", {"class": "woocommerce-Price-amount amount"}).text @@ -86,15 +86,16 @@ def anonymousMarketplace_listing_parser(soup: Tag): shipFrom = [] # 18 Product_ShippedFrom shipTo = [] # 19 Product_ShippedTo href = [] # 20 Product_Links - - - product_list: ResultSet[Tag] = soup.find("ul", {"class": "product_list_widget"}).find_all("li") + + woo = soup.find('div', {"class": "woocommerce"}) + + product_list = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li') for item in product_list: - item_href = item.find("a").get("href") + item_href = item.find("a", recursive=False).get("href") href.append(item_href) - item_name = item.find("span", {"class": "product-title"}).text + item_name = item.find("h2").text name.append(cleanString(item_name.strip())) item_rating = item.find("div", {"class": "star-rating"}).find("strong", {"class": "rating"}).text @@ -103,14 +104,11 @@ def anonymousMarketplace_listing_parser(soup: Tag): try: item_price = item.find("span", {"class": "woocommerce-Price-amount amount"}).text item_price = item_price.replace("$", "").strip() - USD.append(item_price) + USD.append(cleanNumbers(item_price)) except AttributeError: USD.append("-1") - - - - - vendor.append("Anonymous") + + vendor.append("AnonymousMarketplace") rating_vendor.append("-1") success.append("-1") CVE.append("-1") @@ -153,10 +151,6 @@ def anonymousMarketplace_listing_parser(soup: Tag): shipTo=shipTo, href=href ) - - - - #called by the crawler to get description links on a listing page @@ -167,10 +161,13 @@ def anonymous_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] - listing = soup.find('ul', {"class": "product_list_widget"}).findAll('li') + + woo = soup.find('div', {"class": "woocommerce"}) + + listing = woo.find('ul', {"class": "products columns-4"}, recursive=False).find_all('li') for a in listing: - bae = a.find('a', href=True) + bae = a.find('a', href=True, recursive=False) link = bae['href'] href.append(link) diff --git a/MarketPlaces/Apocalypse/crawler_selenium.py b/MarketPlaces/Apocalypse/crawler_selenium.py index c1f579d..4885c19 100644 --- a/MarketPlaces/Apocalypse/crawler_selenium.py +++ b/MarketPlaces/Apocalypse/crawler_selenium.py @@ -203,8 +203,12 @@ def getNameFromURL(url): def getInterestedLinks(): links = [] - # # Hacking Services - # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/subcategory/19') + # # Digital Goods + # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/74') + # # Fraud + # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/75') + # # Services + # links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/category/76') # software and malware links.append('http://apocam5hnoqskkmhr325nivjuh5phbmmggadxgcjabzzirap5iklkxad.onion/subcategory/30') @@ -243,7 +247,11 @@ def crawlForum(driver): except: driver.refresh() savePage(driver, driver.page_source, item) - driver.back() + # driver.back() + try: + driver.get(link) + except: + driver.refresh() # comment out # break @@ -282,7 +290,7 @@ def isDescriptionLink(url): #@param: url of any url crawled #return: true if is a Listing page, false if not def isListingLink(url): - if 'subcategory' in url: + if 'category' in url: return True return False diff --git a/MarketPlaces/DarkBazar/crawler_selenium.py b/MarketPlaces/DarkBazar/crawler_selenium.py new file mode 100644 index 0000000..1f80aec --- /dev/null +++ b/MarketPlaces/DarkBazar/crawler_selenium.py @@ -0,0 +1,276 @@ +__author__ = 'DarkWeb' + +''' +DarkBazar 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.DarkBazar.parser import darkbazar_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/' + + +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 +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 + + +# Returns the name of the website +def getMKTName(): + name = 'DarkBazar' + return name + + +# Return the base link of the website +def getFixedURL(): + url = 'http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.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.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", 1) + 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 you exit the newsletter\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="submit"]'))) + + +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 = 'DarkBazar' + 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 = [] + + # # Digital Goods + # links.append('http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/cat.php?category=4') + # Services + links.append('http://jw5e5sdywqupaqgtt43uq5ysfqpd2vzefl65s2fcjlj4qfxivynv6bqd.onion/cat.php?category=5') + + return links + + +def crawlForum(driver): + + print("Crawling the DarkBazar 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(), "Next")]').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 DarkBazar market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'item' 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 darkbazar_links_parser(soup) + + +def crawler(): + startCrawling() diff --git a/MarketPlaces/DarkBazar/parser.py b/MarketPlaces/DarkBazar/parser.py new file mode 100644 index 0000000..ccb7266 --- /dev/null +++ b/MarketPlaces/DarkBazar/parser.py @@ -0,0 +1,267 @@ +__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 darkbazar_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 + + # Finding Product Name + divmb = soup.findAll('div', {'class': "mb-1"}) + + name = divmb[0].text + name = name.replace('\n', ' ') + name = name.replace(",", "") + name = name.strip() + + # Finding Vendor + vendor = divmb[1].find('a').text.strip() + + # Finding Vendor Rating + temp = soup.find('div', {'class': ""}).text + temp = temp.split('(') + rating = temp[0].replace("Vendor's Review : ", "") + rating = rating.replace("%", "") + rating_vendor = rating.strip() + + # Finding the Product Rating and Number of Product Reviews + reviews = temp[2].replace(" review)", "") + reviews = reviews.strip() + + temp = temp[1].split(")") + rating = temp[1].replace("Product Review : ", "") + rating = rating.replace("%", "") + rating_item = rating.strip() + + # Finding Prices + USD = soup.find('div', {'class': "h3 text-primary"}).text.strip() + + # Finding the Product Category + pmb = soup.findAll('p', {'class': "mb-1"}) + + category = pmb[-1].text + category = category.replace("Category: ", "").strip() + + # Finding the Product Quantity Available + left = divmb[-1].text + left = left.split(",", 1)[1] + left = left.replace("in stock", "") + left = left.strip() + + # Finding Number Sold + sold = divmb[-1].text + sold = sold.split(",", 1)[0] + sold = sold.replace("sold", "") + sold = sold.strip() + + # Finding Shipment Information (Origin) + pmb[0].text + shipFrom = shipFrom.replace("Ships from: ", "").strip() + + # Finding Shipment Information (Destination) + pmb[1].text + shipTo = shipTo.replace("Ships to: ", "").strip() + + # Finding the Product description + cardbody = soup.findAll('div', {'class': "card-body"}) + describe = cardbody[1].text.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 + + +# 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 darkbazar_listing_parser(soup): + + # Fields to be parsed + nm = 0 # *Total_Products (Should be Integer) + mktName = "DarkBazar" # 0 *Marketplace_Name + vendor = [] # 1 *Vendor y + rating_vendor = [] # 2 Vendor_Rating + success = [] # 3 Vendor_Successful_Transactions + name = [] # 4 *Product_Name y + CVE = [] # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about this + MS = [] # 6 Product_MS_Classification (Microsoft Security) dont worry about this + category = [] # 7 Product_Category y + describe = [] # 8 Product_Description + views = [] # 9 Product_Number_Of_Views + reviews = [] # 10 Product_Number_Of_Reviews + rating_item = [] # 11 Product_Rating + addDate = [] # 12 Product_AddDate + BTC = [] # 13 Product_BTC_SellingPrice + USD = [] # 14 Product_USD_SellingPrice y + EURO = [] # 15 Product_EURO_SellingPrice + sold = [] # 16 Product_QuantitySold + qLeft = [] # 17 Product_QuantityLeft + shipFrom = [] # 18 Product_ShippedFrom + shipTo = [] # 19 Product_ShippedTo + href = [] # 20 Product_Links + + listing = soup.findAll('div', {"id": "itembox"}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + bae = a.findAll('a', href=True) + lb = a.findAll('div', {"id": "littlebox"}) + + # Adding the url to the list of urls + link = bae[0].get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product + product = lb[1].find('a').text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.replace("...", "") + product = product.strip() + name.append(product) + + # Finding Prices + price = lb[-1].find('div', {"class": "mb-1"}).text + price = price.replace("$","") + price = price.strip() + USD.append(price) + + # Finding the Vendor + vendor_name = lb[-1].find("a").text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + + # Finding the Category + cat = lb[-1].find("span").text + cat = cat.replace("class:", "") + cat = cat.strip() + category.append(cat) + + span = lb[0].findAll("span") + + # Finding Number of Views + num = span[0].text + num = num.replace("views:", "") + num = num.strip() + sold.append(num) + + # Finding Number Sold + num = span[2].text + num = num.replace("Sold:", "") + num = num.strip() + sold.append(num) + + # Finding Quantity Left + quant = span[1].text + quant = quant.replace("stock:", "") + quant = quant.strip() + qLeft.append(quant) + + + # Searching for CVE and MS categories + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if not cve: + cveValue = "-1" + else: + cee = " " + for idx in cve: + cee += (idx) + cee += " " + cee = cee.replace(',', ' ') + cee = cee.replace('\n', '') + cveValue = cee + CVE.append(cveValue) + + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + if not ms: + MSValue = "-1" + else: + me = " " + for im in ms: + me += (im) + me += " " + me = me.replace(',', ' ') + me = me.replace('\n', '') + MSValue = me + MS.append(MSValue) + + # 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) + + +# 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 darkbazar_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.findAll('div', {"id": "itembox"}) + + # for a in listing: + # bae = a.find('a', {"class": "text-info"}, href=True) + # link = bae['href'] + # href.append(link) + + for a in listing: + bae = a.findAll('a', href=True) + + # Adding the url to the list of urls + link = bae[0].get('href') + href.append(link) + + return href \ No newline at end of file diff --git a/MarketPlaces/DarkMatter/crawler_selenium.py b/MarketPlaces/DarkMatter/crawler_selenium.py index e0babcb..67183e5 100644 --- a/MarketPlaces/DarkMatter/crawler_selenium.py +++ b/MarketPlaces/DarkMatter/crawler_selenium.py @@ -229,17 +229,16 @@ def crawlForum(driver): for item in list: itemURL = urlparse.urljoin(baseURL, str(item)) try: - time.sleep(1.5) # to keep from detecting click speed + time.sleep(3) # to keep from detecting click speed driver.get(itemURL) except: driver.refresh() savePage(driver, driver.page_source, item) - time.sleep(1.5) + time.sleep(3) # to keep from detecting click speed driver.back() - # to keep from detecting click speed # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/DigitalThriftShop/crawler_selenium.py b/MarketPlaces/DigitalThriftShop/crawler_selenium.py index 132d2af..39d9f5d 100644 --- a/MarketPlaces/DigitalThriftShop/crawler_selenium.py +++ b/MarketPlaces/DigitalThriftShop/crawler_selenium.py @@ -235,7 +235,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/HiddenMarket/crawler_selenium.py b/MarketPlaces/HiddenMarket/crawler_selenium.py index 3813c76..b8cc323 100644 --- a/MarketPlaces/HiddenMarket/crawler_selenium.py +++ b/MarketPlaces/HiddenMarket/crawler_selenium.py @@ -277,7 +277,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/Initialization/marketsList.txt b/MarketPlaces/Initialization/marketsList.txt index fe4ac4a..540b444 100644 --- a/MarketPlaces/Initialization/marketsList.txt +++ b/MarketPlaces/Initialization/marketsList.txt @@ -1,8 +1,12 @@ Apocalypse +DarkBazar DarkMatter DigitalThriftShop HiddenMarket +LionMarketplace Nexus Robinhood +ThiefWorld TorBay +TorMarket ViceCity \ No newline at end of file diff --git a/MarketPlaces/Initialization/markets_mining.py b/MarketPlaces/Initialization/markets_mining.py index 4b9c02e..b93ef96 100644 --- a/MarketPlaces/Initialization/markets_mining.py +++ b/MarketPlaces/Initialization/markets_mining.py @@ -24,6 +24,7 @@ from MarketPlaces.HiddenMarket.crawler_selenium import crawler as crawlerHiddenM from MarketPlaces.RobinhoodMarket.crawler_selenium import crawler as crawlerRobinhoodMarket from MarketPlaces.Nexus.crawler_selenium import crawler as crawlerNexus from MarketPlaces.CypherMarketplace.crawler_selenium import crawler as crawlerCypher +from MarketPlaces.DarkBazar.crawler_selenium import crawler as crawlerDarkBazar import configparser import os @@ -137,5 +138,7 @@ if __name__ == '__main__': crawlerNexus() elif mkt == "CypherMarketplace": crawlerCypher() + elif mkt == "DarkBazar": + crawlerDarkBazar() print("\nScraping process completed!") diff --git a/MarketPlaces/Initialization/prepare_parser.py b/MarketPlaces/Initialization/prepare_parser.py index a460a18..68ba3b9 100644 --- a/MarketPlaces/Initialization/prepare_parser.py +++ b/MarketPlaces/Initialization/prepare_parser.py @@ -1,4 +1,4 @@ -__author__ = 'Helium' +__author__ = 'DarkWeb' import glob import os @@ -21,6 +21,7 @@ from MarketPlaces.HiddenMarket.parser import * from MarketPlaces.RobinhoodMarket.parser import * from MarketPlaces.Nexus.parser import * from MarketPlaces.MikesGrandStore.parser import * +from MarketPlaces.DarkBazar.parser import * from MarketPlaces.Classifier.classify_product import predict @@ -152,6 +153,8 @@ def parse_listing(marketPlace, listingFile, soup, createLog, logFile): rw = nexus_listing_parser(soup) elif marketPlace == "MikesGrandStore": rw = mikesGrandStore_listing_parser(soup) + elif marketPlace == "DarkBazar": + rw = darkbazar_listing_parser(soup) else: print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!") raise Exception @@ -203,6 +206,8 @@ def parse_description(marketPlace, descriptionFile, soup, createLog, logFile): rmm = nexus_description_parser(soup) elif marketPlace == "MikesGrandStore": rmm = mikesGrandStore_description_parser(soup) + elif marketPlace == "DarkBazar": + rmm = darkbazar_description_parser(soup) else: print("MISSING CALL TO DESCRIPTION PARSER IN PREPARE_PARSER.PY!") raise Exception diff --git a/MarketPlaces/LionMarketplace/crawler_selenium.py b/MarketPlaces/LionMarketplace/crawler_selenium.py index 237838f..ab8e41d 100644 --- a/MarketPlaces/LionMarketplace/crawler_selenium.py +++ b/MarketPlaces/LionMarketplace/crawler_selenium.py @@ -234,7 +234,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/LionMarketplace/parser.py b/MarketPlaces/LionMarketplace/parser.py index 726cc63..06a87e3 100644 --- a/MarketPlaces/LionMarketplace/parser.py +++ b/MarketPlaces/LionMarketplace/parser.py @@ -34,15 +34,11 @@ def lionmarketplace_description_parser(soup): shipTo = "-1" # 18 Product_ShippedTo # vendor name - try: - temp = soup.find('div', {'class': 'btn-group'}).find('a').text - vendor = (cleanString(temp.strip())) - except: - print('vendor') - vendor = "-1" + temp = soup.find('div', {'class': 'btn-group'}).find('a').text + vendor = (cleanString(temp.strip())) # table with info - table = soup.find('table', {'class', 'table border-0 text-left table-borderless'}) + table = soup.find('table') rows = table.findAll('tr') # successful transaction @@ -51,37 +47,20 @@ def lionmarketplace_description_parser(soup): # vendor rating 5 rating_vendor = '-1' - # product name - try: - temp = soup.find('div', {'class', 'row'}).find('h2').text - name = (cleanString(temp.strip())) - except: - name = '-1' - print('product name') + temp = soup.find('div', {'class', 'row'}).find('h2').text + name = (cleanString(temp.strip())) # product description - try: - temp = soup.find('div', {'class': "mt-4"}).findAll('p') - temp = temp[1].text - if "\n" in temp: - temp = temp.replace("\n", " ") - temp = temp.replace("\r", " ") - describe = cleanString(temp.strip()) - except: - describe="-1" - print('describe') + temp = soup.find('div', {'class': "mt-4"}).find(text=True, recursive=False) + describe = cleanString(temp.strip()) CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about that much MS = "-1" # 6 Product_MS_Classification (Microsoft Security) dont worry about that much # product category - try: - temp = rows[1].find('strong').text - category = cleanString(temp.strip()) - except: - category = "-1" - print('category') + temp = rows[1].find('strong').text + category = cleanString(temp.strip()) # product number of views views = "-1" @@ -92,54 +71,38 @@ def lionmarketplace_description_parser(soup): BTC = "-1" # USD selling price - try: - temp = rows[2].find('strong').text - if " $" in temp: - temp = temp.replace(" $", "") - elif "$" in temp: - temp = temp.replace("$", "") - USD = cleanString((temp.strip())) - except: - try: - temp = soup.find('li').find('strong').text - if " $" in temp: - temp = temp.replace(" $", "") - elif "$" in temp: - temp = temp.replace("$", "") - USD = cleanString((temp.strip())) - except: - print("USD") + temp = rows[2].find('strong').text + if " $" in temp: + temp = temp.replace(" $", "") + elif "$" in temp: + temp = temp.replace("$", "") + USD = cleanString((temp.strip())) EURO = "-1" # 14 Product_EURO_SellingPrice # product sold - try: - if (len(rows) <= 5): - temp = rows[4].find('td').text - string = cleanString(temp) - if (string == 'Left/Sold'): - temp = rows[4].findAll('td') - temp = temp[1].findAll('span') - - # left - temp2 = temp[1].text - temp3 = temp[1].text - - if(" items" in temp2): - temp2 = temp2.replace(" items", "") - if(" items" in temp3): - temp3 = temp3.replace(" items", "") - - sold = (cleanString(temp2.strip())) - left = cleanString(temp3.strip()) - else: - sold = '-1' - left = "-1" + if (len(rows) <= 5): + temp = rows[4].find('td').text + string = cleanString(temp) + if (string == 'Left/Sold'): + temp = rows[4].findAll('td') + temp = temp[1].findAll('span') + + # left + temp2 = temp[1].text + temp3 = temp[1].text + + if(" items" in temp2): + temp2 = temp2.replace(" items", "") + if(" items" in temp3): + temp3 = temp3.replace(" items", "") + + sold = (cleanString(temp2.strip())) + left = cleanString(temp3.strip()) else: sold = '-1' left = "-1" - except: - print("success") + else: sold = '-1' left = "-1" @@ -161,7 +124,7 @@ def lionmarketplace_description_parser(soup): def lionmarketplace_listing_parser(soup): # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) - mktName = "M00nkeyMarket" # 0 *Marketplace_Name + mktName = "LionMarketplace" # 0 *Marketplace_Name vendor = [] # 1 *Vendor y rating_vendor = [] # 2 Vendor_Rating success = [] # 3 Vendor_Successful_Transactions @@ -183,21 +146,20 @@ def lionmarketplace_listing_parser(soup): shipTo = [] # 19 Product_ShippedTo href = [] # 20 Product_Links - listing = soup.findAll('div', {"class": "card-body"}) + listings = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"}) # Populating the Number of Products - nm = len(listing) + nm = len(listings) - for a in listing: + for listing in listings: + a = listing.find('div', {"class": "card-body"}) row = a.findAll('p') + # vendor - try: - temp = row[3].text - vendor.append(cleanString(temp.strip())) - except: - vendor.append("-1") - print('vendor') + temp = row[3].text + temp = temp.replace("Vendor:", "") + vendor.append(cleanString(temp.strip())) # vendor rating rating_vendor.append("-1") @@ -206,25 +168,16 @@ def lionmarketplace_listing_parser(soup): success.append("-1") # product name - try: - temp = a.find('a').text - name.append(cleanString(temp.strip())) - except: - name.append("-1") - print('product name') + temp = a.find('a').text + name.append(cleanString(temp.strip())) CVE.append('-1') MS.append('-1') # product category - try: - temp = row[2].text - if "Category: " in temp: - temp = temp.replace("Category: ", "") - category.append(cleanString(temp.strip())) - - except: - print("Error in product category") + temp = row[2].text + temp = temp.replace("Category: ", "") + category.append(cleanString(temp.strip())) describe.append('-1') @@ -238,14 +191,10 @@ def lionmarketplace_listing_parser(soup): BTC.append('-1') # USD - try: - temp = row[0].find('strong').text - if ' $' in temp: - temp = temp.replace(" $", "") - USD.append(cleanString(temp.strip())) # 14 Product_USD_SellingPrice - except: - print("USD") - USD.append("-1") + temp = row[0].find('strong').text + if ' $' in temp: + temp = temp.replace(" $", "") + USD.append(cleanString(temp.strip())) # 14 Product_USD_SellingPrice EURO.append("-1") # 15 Product_EURO_SellingPrice @@ -257,11 +206,8 @@ def lionmarketplace_listing_parser(soup): shipTo.append('-1') # 19 Product_ShippedTo # href - try: - temp = a.find('a').get('href') - href.append(temp) - except: - print('product name') + temp = a.find('a').get('href') + href.append(temp) # 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, @@ -276,9 +222,10 @@ def lionmarketplace_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] - listing = soup.findAll('div', {"class": "container d-flex justify-content-center"}) + listings = soup.findAll('div', {"class": "col-md-4 my-md-0 my-2 col-12"}) - for a in listing: + for listing in listings: + a = listing.find('div', {"class": "card-body"}) bae = a.find('a', href=True) link = bae['href'] href.append(link) diff --git a/MarketPlaces/M00nkeyMarket/crawler_selenium.py b/MarketPlaces/M00nkeyMarket/crawler_selenium.py index ccd8f11..690913e 100644 --- a/MarketPlaces/M00nkeyMarket/crawler_selenium.py +++ b/MarketPlaces/M00nkeyMarket/crawler_selenium.py @@ -159,7 +159,7 @@ def login(driver): # 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/div/div[1]/div/div/div[2]/div[3]/div"))) + (By.XPATH, "/html/body/div/div[2]/div/div/div/div/div/div[1]/a/img"))) # Saves the crawled html page, makes the directory path for html pages if not made def savePage(driver, page, url): diff --git a/MarketPlaces/MetaVerseMarket/crawler_selenium.py b/MarketPlaces/MetaVerseMarket/crawler_selenium.py new file mode 100644 index 0000000..e624d51 --- /dev/null +++ b/MarketPlaces/MetaVerseMarket/crawler_selenium.py @@ -0,0 +1,306 @@ +__author__ = 'Helium' + +''' +MetaVerseMarket Marketplace Crawler (Selenium) +not complete +need to go through multiple pages... +''' + +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, re, time +from datetime import date +import subprocess +import configparser +from bs4 import BeautifulSoup +from MarketPlaces.Initialization.prepare_parser import new_parse +from MarketPlaces.MetaVerseMarket.parser import metaversemarket_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://mdbvvcfwl3fpckiraucv7gio57yoslnhfjxzpoihf4fgdkdd7bwyv7id.onion/login' + + +# 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(): + 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 + + +# Returns the name of the website +#return: name of site in string type +def getMKTName(): + name = 'MetaVerseMarket' + return name + + +# Return the base link of the website +#return: url of base site in string type +def getFixedURL(): + url = 'http://mdbvvcfwl3fpckiraucv7gio57yoslnhfjxzpoihf4fgdkdd7bwyv7id.onion/login' + 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(): + 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", 1)## + 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' +#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): + + # entering username and password into input boxes + usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]') + # Username here + usernameBox.send_keys('metotomoto') + passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]') + # Password here + passwordBox.send_keys('lionking_kumba1ya') + + input("Press ENTER when CAPTCHA is completed and you exit the newsletter\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="searchq"]'))) + +# Saves the crawled html page, makes the directory path for html pages if not made +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 + + +# 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 = 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, 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 = [] + + # hacking + links.append('http://mdbvvcfwl3fpckiraucv7gio57yoslnhfjxzpoihf4fgdkdd7bwyv7id.onion/products/hacking') + # hosting + links.append('http://mdbvvcfwl3fpckiraucv7gio57yoslnhfjxzpoihf4fgdkdd7bwyv7id.onion/products/hosting') + # hacking guides and tutorials + links.append('http://mdbvvcfwl3fpckiraucv7gio57yoslnhfjxzpoihf4fgdkdd7bwyv7id.onion/products/hacking-guides-and-tutorials') + + 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 MetaVerse 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[@class="page-link-next"]').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 MetaVerse market done.") + + +# 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 'PR' 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 'products' 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 metaversemarket_links_parser(soup) + + +# Drop links that "signout" +# def isSignOut(url): +# #absURL = urlparse.urljoin(url.base_url, url.url) +# if 'signout' in url.lower() or 'logout' in url.lower(): +# return True +# +# return False + + +def crawler(): + startCrawling() + # print("Crawling and Parsing MetaVerseMarket .... DONE!") diff --git a/MarketPlaces/MetaVerseMarket/parser.py b/MarketPlaces/MetaVerseMarket/parser.py new file mode 100644 index 0000000..8c83293 --- /dev/null +++ b/MarketPlaces/MetaVerseMarket/parser.py @@ -0,0 +1,285 @@ +__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 darkfox_description_parser(soup): + # Fields to be parsed + + name = "-1" # 0 Product_Name + describe = "-1" # 1 Product_Description + lastSeen = "-1" # 2 Product_LastViewDate + CVE = "-1" # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 5 Product_MS_Classification (Microsoft Security) + review = "-1" # 6 Product_Number_Of_Reviews + category = "-1" # 7 Product_Category + shipFrom = "-1" # 8 Product_ShippedFrom + shipTo = "-1" # 9 Product_ShippedTo + left = "-1" # 10 Product_QuantityLeft + escrow = "-1" # 11 Vendor_Warranty + terms = "-1" # 12 Vendor_TermsAndConditions + vendor = "-1" # 13 Vendor_Name + sold = "-1" # 14 Product_QuantitySold + addDate = "-1" # 15 Product_AddedDate + BTC = "-1" # 18 Product_BTC_SellingPrice + USD = "-1" # 19 Product_USD_SellingPrice + rating = "-1" # 20 Vendor_Rating + success = "-1" # 21 Vendor_Successful_Transactions + EURO = "-1" # 22 Product_EURO_SellingPrice + + # Finding Product Name + name = soup.find('h1').text + name = name.replace('\n', ' ') + name = name.replace(",", "") + name = name.strip() + + # Finding Vendor + vendor = soup.find('h3').find('a').text.strip() + + # Finding Vendor Rating + rating = soup.find('span', {'class': "tag is-dark"}).text.strip() + + # Finding Successful Transactions + success = soup.find('h3').text + success = success.replace("Vendor: ", "") + success = success.replace(vendor, "") + success = success.replace("(", "") + success = success.replace(")", "") + success = success.strip() + + bae = soup.find('div', {'class': "box"}).find_all('ul') + + # Finding Prices + USD = bae[1].find('strong').text.strip() + + li = bae[2].find_all('li') + + # Finding Escrow + escrow = li[0].find('span', {'class': "tag is-dark"}).text.strip() + + # Finding the Product Category + category = li[1].find('span', {'class': "tag is-dark"}).text.strip() + + # Finding the Product Quantity Available + left = li[3].find('span', {'class': "tag is-dark"}).text.strip() + + # Finding Number Sold + sold = li[4].find('span', {'class': "tag is-dark"}).text.strip() + + li = bae[3].find_all('li') + + # Finding Shipment Information (Origin) + if "Ships from:" in li[-2].text: + shipFrom = li[-2].text + shipFrom = shipFrom.replace("Ships from: ", "") + # shipFrom = shipFrom.replace(",", "") + shipFrom = shipFrom.strip() + + # Finding Shipment Information (Destination) + shipTo = li[-1].find('div', {'title': "List of countries is scrollable"}).text + shipTo = shipTo.replace("Ships to: ", "") + shipTo = shipTo.strip() + if "certain countries" in shipTo: + countries = "" + tags = li[-1].find_all('span', {'class': "tag"}) + for tag in tags: + country = tag.text.strip() + countries += country + ", " + shipTo = countries.strip(", ") + + # Finding the Product description + describe = soup.find('div', {'class': "pre-line"}).text + describe = describe.replace("\n", " ") + describe = describe.strip() + + '''# Finding the Number of Product Reviews + tag = soup.findAll(text=re.compile('Reviews')) + for index in tag: + reviews = index + par = reviews.find('(') + if par >=0: + reviews = reviews.replace("Reviews (","") + reviews = reviews.replace(")","") + reviews = reviews.split(",") + review = str(abs(int(reviews[0])) + abs(int(reviews[1]))) + else : + review = "-1"''' + + # Searching for CVE and MS categories + cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if cve: + CVE = " " + for idx in cve: + CVE += (idx) + CVE += " " + CVE = CVE.replace(',', ' ') + CVE = CVE.replace('\n', '') + ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}')) + if ms: + MS = " " + for im in ms: + MS += (im) + MS += " " + MS = MS.replace(',', ' ') + MS = MS.replace('\n', '') + + # Populating the final variable (this should be a list with all fields scraped) + row = (name, describe, lastSeen, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor, + sold, addDate, BTC, USD, rating, success, EURO) + + # 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 darkfox_listing_parser(soup): + # Fields to be parsed + nm = 0 # Total_Products (Should be Integer) + mktName = "DarkFox" # 0 Marketplace_Name + name = [] # 1 Product_Name + CVE = [] # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = [] # 3 Product_MS_Classification (Microsoft Security) + category = [] # 4 Product_Category + describe = [] # 5 Product_Description + escrow = [] # 6 Vendor_Warranty + views = [] # 7 Product_Number_Of_Views + reviews = [] # 8 Product_Number_Of_Reviews + addDate = [] # 9 Product_AddDate + lastSeen = [] # 10 Product_LastViewDate + BTC = [] # 11 Product_BTC_SellingPrice + USD = [] # 12 Product_USD_SellingPrice + EURO = [] # 13 Product_EURO_SellingPrice + sold = [] # 14 Product_QuantitySold + qLeft = [] # 15 Product_QuantityLeft + shipFrom = [] # 16 Product_ShippedFrom + shipTo = [] # 17 Product_ShippedTo + vendor = [] # 18 Vendor + rating = [] # 19 Vendor_Rating + success = [] # 20 Vendor_Successful_Transactions + href = [] # 23 Product_Links (Urls) + + listing = soup.findAll('div', {"class": "card"}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + bae = a.findAll('a', href=True) + + # Adding the url to the list of urls + link = bae[0].get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product + product = bae[1].find('p').text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.replace("...", "") + product = product.strip() + name.append(product) + + bae = a.find('div', {'class': "media-content"}).find('div').find_all('div') + + if len(bae) >= 5: + # Finding Prices + price = bae[0].text + ud = price.replace(" USD", " ") + # u = ud.replace("$","") + u = ud.replace(",", "") + u = u.strip() + USD.append(u) + # bc = (prc[1]).strip(' BTC') + # BTC.append(bc) + + # Finding the Vendor + vendor_name = bae[1].find('a').text + vendor_name = vendor_name.replace(",", "") + vendor_name = vendor_name.strip() + vendor.append(vendor_name) + + # Finding the Category + cat = bae[2].find('small').text + cat = cat.replace("Category: ", "") + cat = cat.replace(",", "") + cat = cat.strip() + category.append(cat) + + # Finding Number Sold and Quantity Left + num = bae[3].text + num = num.replace("Sold: ", "") + num = num.strip() + sold.append(num) + + quant = bae[4].find('small').text + quant = quant.replace("In stock: ", "") + quant = quant.strip() + qLeft.append(quant) + + # Finding Successful Transactions + freq = bae[1].text + freq = freq.replace(vendor_name, "") + freq = re.sub(r'Vendor Level \d+', "", freq) + freq = freq.replace("(", "") + freq = freq.replace(")", "") + freq = freq.strip() + success.append(freq) + + # Searching for CVE and MS categories + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if not cve: + cveValue = "-1" + else: + cee = " " + for idx in cve: + cee += (idx) + cee += " " + cee = cee.replace(',', ' ') + cee = cee.replace('\n', '') + cveValue = cee + CVE.append(cveValue) + + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + if not ms: + MSValue = "-1" + else: + me = " " + for im in ms: + me += (im) + me += " " + me = me.replace(',', ' ') + me = me.replace('\n', '') + MSValue = me + MS.append(MSValue) + + # Populate the final variable (this should be a list with all fields scraped) + return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen, + BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href) + + +# 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 metaversemarket_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.findAll('div', {"class": "col-12 p-0"}) + + for a in listing: + bae = a.find('a', href=True) + link = bae['href'] + href.append(link) + + return href \ No newline at end of file diff --git a/MarketPlaces/Nexus/crawler_selenium.py b/MarketPlaces/Nexus/crawler_selenium.py index 70e1480..1962d79 100644 --- a/MarketPlaces/Nexus/crawler_selenium.py +++ b/MarketPlaces/Nexus/crawler_selenium.py @@ -173,16 +173,24 @@ def getNameFromURL(url): def getInterestedLinks(): links = [] - # Bot nets - links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/botnets/') - # # Rats - # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/rats/') - # # Ransomware - # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/ransomware/') - # # Other Malware - # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/outros-malware/') - # # Hacking Tools & Scripting - # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/hacking-spam/ferramentas-de-hacking-scripts/') + # malware + links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/malware/') + # # hacking-spam + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/hacking-spam/') + # # hacking services + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/hacking/') + # # programming services + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/programacao/') + # # remote admin services + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/servicos/administracao-remota/') + # # hacking guides + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-hacking/') + # # malware guides + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-malware/') + # # fraud guides + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/guias-tutoriais/guia-de-fraudes/') + # # fraud software + # links.append('http://nexus2bmba34euohk3xo7og2zelkgbtc2p7rjsbxrjjknlecja2tdvyd.onion/categoria-produto/fraudes/software-de-fraude/') return links @@ -222,7 +230,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/PabloEscobarMarket/crawler_selenium.py b/MarketPlaces/PabloEscobarMarket/crawler_selenium.py new file mode 100644 index 0000000..cc9b890 --- /dev/null +++ b/MarketPlaces/PabloEscobarMarket/crawler_selenium.py @@ -0,0 +1,268 @@ +__author__ = 'DarkWeb' + +''' +PabloEscobarMarket 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.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 +from bs4 import BeautifulSoup +from MarketPlaces.Initialization.prepare_parser import new_parse +from MarketPlaces.PabloEscobarMarket.parser import pabloescobarmarket_links_parser +from MarketPlaces.Utilities.utilities import cleanHTML + +counter = 1 +baseURL = 'http://niejmptjzwhlfywruoab4pbuxg7kp2mtcr4c6mgpeykju5matewg36yd.onion/' + + +# Opens Tor Browser, crawls the website +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 +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): + 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='//*[@id="username"]') + # Username here + usernameBox.send_keys('snorlaxrights') + passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="inputPassword3"]') + # Password here + passwordBox.send_keys('$noringAllday') + + 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) + # wait for 50 sec until id = tab_content is found, then cont + WebDriverWait(driver, 50).until(EC.visibility_of_element_located( + (By.XPATH, '//*[@id="collapse3"]'))) + + +# Returns the name of the website +def getMKTName() -> str: + name = 'PabloEscobarMarket' + return name + + +# Return the link of the website +def getFixedURL(): + url = 'http://niejmptjzwhlfywruoab4pbuxg7kp2mtcr4c6mgpeykju5matewg36yd.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.close() #close tab + 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", True) + 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(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 + + +# 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 + +# FIX +def getInterestedLinks(): + links = [] + + # hire hacker + links.append('http://niejmptjzwhlfywruoab4pbuxg7kp2mtcr4c6mgpeykju5matewg36yd.onion/?sub_id=36') + # hacker + links.append('http://niejmptjzwhlfywruoab4pbuxg7kp2mtcr4c6mgpeykju5matewg36yd.onion/?sub_id=34') + + return links + + +def crawlForum(driver): + print("Crawling the PabloEscobarMarket 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[@rel="next"]').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 PabloEscobarMarket market done.") + + +# Returns 'True' if the link is Topic link, may need to change for every website +def isDescriptionLink(url): + if 'single_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 'sub_id' in url: + return True + return False + + +# calling the parser to define the links +def productPages(html): + soup = BeautifulSoup(html, "html.parser") + return pabloescobarmarket_links_parser(soup) + + +def crawler(): + startCrawling() + # print("Crawling and Parsing PabloEscobarMarket .... DONE!") diff --git a/MarketPlaces/PabloEscobarMarket/parser.py b/MarketPlaces/PabloEscobarMarket/parser.py new file mode 100644 index 0000000..ecdd086 --- /dev/null +++ b/MarketPlaces/PabloEscobarMarket/parser.py @@ -0,0 +1,241 @@ +__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 pabloescobarmarket_description_parser(soup): + # Fields to be parsed + + name = "-1" # 0 Product_Name + describe = "-1" # 1 Product_Description + lastSeen = "-1" # 2 Product_LastViewDate + CVE = "-1" # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = "-1" # 5 Product_MS_Classification (Microsoft Security) + review = "-1" # 6 Product_Number_Of_Reviews + category = "-1" # 7 Product_Category + shipFrom = "-1" # 8 Product_ShippedFrom + shipTo = "-1" # 9 Product_ShippedTo + left = "-1" # 10 Product_QuantityLeft + escrow = "-1" # 11 Vendor_Warranty + terms = "-1" # 12 Vendor_TermsAndConditions + vendor = "-1" # 13 Vendor_Name + sold = "-1" # 14 Product_QuantitySold + addDate = "-1" # 15 Product_AddedDate + BTC = "-1" # 18 Product_BTC_SellingPrice + USD = "-1" # 19 Product_USD_SellingPrice + rating = "-1" # 20 Vendor_Rating + success = "-1" # 21 Vendor_Successful_Transactions + EURO = "-1" # 22 Product_EURO_SellingPrice + + # Finding Product Name + # NA + + divmd7 = soup.find('div', {'class': "col-md-7"}) + ptag = soup.findAll('p') + # Finding Vendor + vendor = divmd7.find('a').text.strip() + + # Finding Vendor Rating + # NA + + # Finding Successful Transactions + success = soup.find('span', {'class': "badge-primary"}) + + # Finding Prices + USD = soup.find('span', {'class': "total"}).text.strip() + + BTC = soup.find('div', {'class': "text-center"}).text.strip() + + # Finding Escrow + escrow = ptag[-1].text.strip() + + # Finding the Product Category + category = ptag[-2].text.strip() + + # Finding the Product Quantity Available + # NA + + # Finding Number Sold + # NA + + # Finding Shipment Information (Origin) + # NA + + # Finding Shipment Information (Destination) + # NA + + # Finding the Product description + describe = soup.find('div', {'class': "text-white"}).text + describe = describe.replace("\n", " ") + describe = describe.strip() + + '''# Finding the Number of Product Reviews + tag = soup.findAll(text=re.compile('Reviews')) + for index in tag: + reviews = index + par = reviews.find('(') + if par >=0: + reviews = reviews.replace("Reviews (","") + reviews = reviews.replace(")","") + reviews = reviews.split(",") + review = str(abs(int(reviews[0])) + abs(int(reviews[1]))) + else : + review = "-1"''' + + # Searching for CVE and MS categories + cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if cve: + CVE = " " + for idx in cve: + CVE += (idx) + CVE += " " + CVE = CVE.replace(',', ' ') + CVE = CVE.replace('\n', '') + ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}')) + if ms: + MS = " " + for im in ms: + MS += (im) + MS += " " + MS = MS.replace(',', ' ') + MS = MS.replace('\n', '') + + # Populating the final variable (this should be a list with all fields scraped) + row = (name, describe, lastSeen, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor, + sold, addDate, BTC, USD, rating, success, EURO) + + # 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 pabloescobarmarket_listing_parser(soup): + # Fields to be parsed + nm = 0 # Total_Products (Should be Integer) + mktName = "PabloEscobarMarket" # 0 Marketplace_Name + name = [] # 1 Product_Name + CVE = [] # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures) + MS = [] # 3 Product_MS_Classification (Microsoft Security) + category = [] # 4 Product_Category + describe = [] # 5 Product_Description + escrow = [] # 6 Vendor_Warranty + views = [] # 7 Product_Number_Of_Views + reviews = [] # 8 Product_Number_Of_Reviews + addDate = [] # 9 Product_AddDate + lastSeen = [] # 10 Product_LastViewDate + BTC = [] # 11 Product_BTC_SellingPrice + USD = [] # 12 Product_USD_SellingPrice + EURO = [] # 13 Product_EURO_SellingPrice + sold = [] # 14 Product_QuantitySold + qLeft = [] # 15 Product_QuantityLeft + shipFrom = [] # 16 Product_ShippedFrom + shipTo = [] # 17 Product_ShippedTo + vendor = [] # 18 Vendor + rating = [] # 19 Vendor_Rating + success = [] # 20 Vendor_Successful_Transactions + href = [] # 23 Product_Links (Urls) + + listing = soup.findAll('div', {"class": "p-4"}) + + # Populating the Number of Products + nm = len(listing) + + for a in listing: + bae = a.findAll('a', href=True) + + # Adding the url to the list of urls + link = bae[0].get('href') + link = cleanLink(link) + href.append(link) + + # Finding the Product + product = a.find('h4').text + product = product.replace('\n', ' ') + product = product.replace(",", "") + product = product.replace("...", "") + product = product.strip() + name.append(product) + + + # Finding Prices + price = a.find('div', {"class": "price"}).text + tempUSD = price.split("~")[0] + tempUSD = tempUSD.replace("$", "") + tempUSD = tempUSD.strip() + USD.append(tempUSD) + + tempBTC = price.split("~")[1] + tempBTC = tempBTC.replace("BTC", "") + tempBTC = tempBTC.strip() + BTC.append(tempBTC) + + # Finding the Vendor + #NA + + # Finding the Category + # NA + + # Finding Number Sold and Quantity Left + # NA + + # Finding Successful Transactions + # NA + + # Searching for CVE and MS categories + cve = a.findAll(text=re.compile('CVE-\d{4}-\d{4}')) + if not cve: + cveValue = "-1" + else: + cee = " " + for idx in cve: + cee += (idx) + cee += " " + cee = cee.replace(',', ' ') + cee = cee.replace('\n', '') + cveValue = cee + CVE.append(cveValue) + + ms = a.findAll(text=re.compile('MS\d{2}-\d{3}')) + if not ms: + MSValue = "-1" + else: + me = " " + for im in ms: + me += (im) + me += " " + me = me.replace(',', ' ') + me = me.replace('\n', '') + MSValue = me + MS.append(MSValue) + + # Populate the final variable (this should be a list with all fields scraped) + return organizeProducts(mktName, nm, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen, + BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href) + + +# 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 FIX +def pabloescobarmarket_links_parser(soup): + # Returning all links that should be visited by the Crawler + + href = [] + listing = soup.findAll('div', {"class": "p-4"}) + + for a in listing: + bae = a.find('a', href=True) + link = bae['href'] + href.append(link) + + return href \ No newline at end of file diff --git a/MarketPlaces/RobinhoodMarket/crawler_selenium.py b/MarketPlaces/RobinhoodMarket/crawler_selenium.py index 9124a8f..4ce1cfe 100644 --- a/MarketPlaces/RobinhoodMarket/crawler_selenium.py +++ b/MarketPlaces/RobinhoodMarket/crawler_selenium.py @@ -218,7 +218,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: @@ -266,5 +266,6 @@ def crawler(): startCrawling() # print("Crawling and Parsing BestCardingWorld .... DONE!") + if __name__ == '__main__': - startCrawling() \ No newline at end of file + startCrawling() diff --git a/MarketPlaces/ThiefWorld/crawler_selenium.py b/MarketPlaces/ThiefWorld/crawler_selenium.py index 345bdbe..e532006 100644 --- a/MarketPlaces/ThiefWorld/crawler_selenium.py +++ b/MarketPlaces/ThiefWorld/crawler_selenium.py @@ -144,7 +144,7 @@ def getAccess(): def login(driver): # wait for 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[1]/div/div[1]/div[1]/ul"))) + (By.XPATH, "/html/body/div/header/div[2]/div/nav/div[2]/a[1]"))) temp = driver.find_element(By.XPATH, '/html/body/div/header/div[2]/div/nav/div[2]/a[1]').get_attribute( 'href') # /html/body/div/div[2]/div/div[2]/div @@ -242,7 +242,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/ThiefWorld/parser.py b/MarketPlaces/ThiefWorld/parser.py index ee15092..dbf7584 100644 --- a/MarketPlaces/ThiefWorld/parser.py +++ b/MarketPlaces/ThiefWorld/parser.py @@ -53,7 +53,7 @@ def thiefWorld_description_parser(soup: BeautifulSoup) -> Tuple: USD = cleanString(usdText.replace("USD", "").strip()) ratingDiv = soup.find('div', {'class': 'rating_star'}) - rating_vendor = ratingDiv.get('title').strip(' ')[1] + rating_vendor = ratingDiv.get('title').split(' ')[1] # 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, diff --git a/MarketPlaces/TorBay/crawler_selenium.py b/MarketPlaces/TorBay/crawler_selenium.py index 5035999..4c8de5b 100644 --- a/MarketPlaces/TorBay/crawler_selenium.py +++ b/MarketPlaces/TorBay/crawler_selenium.py @@ -228,7 +228,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: diff --git a/MarketPlaces/TorMarket/crawler_selenium.py b/MarketPlaces/TorMarket/crawler_selenium.py index b76fb1c..e1612ea 100644 --- a/MarketPlaces/TorMarket/crawler_selenium.py +++ b/MarketPlaces/TorMarket/crawler_selenium.py @@ -37,7 +37,6 @@ def startCrawling(): if driver != 'down': try: - # login(driver) crawlForum(driver) except Exception as e: print(driver.current_url, e) @@ -101,8 +100,8 @@ def createFFDriver(): 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("network.dns.disablePrefetch", True) + # ff_prof.set_preference("network.http.sendRefererHeader", 0) ff_prof.set_preference("permissions.default.image", 1) ff_prof.set_preference("browser.download.folderList", 2) ff_prof.set_preference("browser.download.manager.showWhenStarting", False) @@ -186,12 +185,12 @@ def getNameFromURL(url): def getInterestedLinks(): links = [] - # # Hacking Tutorials - # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/guides-tutorials/hacking/') + # # Tutorials + # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/guides-tutorials/') # Malware links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/malware/') - # # Hacking Services - # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/services/hacking-services/') + # # Services + # links.append('http://22222253ebafysmwyrl4uxfcs2xm6k7zb4xyse2csne73atvxu53gfad.onion/product-category/services/') return links @@ -238,8 +237,7 @@ def crawlForum(driver): break try: - link = driver.find_element(by=By.XPATH, value= - '/html/body/div[2]/div/div/div[1]/main/nav/ul/li[5]/a').get_attribute('href') + link = driver.find_element(by=By.LINK_TEXT, value='Next').get_attribute('href') if link == "": raise NoSuchElementException count += 1 diff --git a/MarketPlaces/TorMarket/parser.py b/MarketPlaces/TorMarket/parser.py index 69d680c..e6e14b9 100644 --- a/MarketPlaces/TorMarket/parser.py +++ b/MarketPlaces/TorMarket/parser.py @@ -104,61 +104,58 @@ def tormarket_listing_parser(soup): shipFrom = [] # 18 Product_ShippedFrom shipTo = [] # 19 Product_ShippedTo href = [] # 20 Product_Links - products_list = soup.find_all('li') - nm = 0 + + products_list = soup.find('ul', {"class": "products columns-3 tablet-columns-2 mobile-columns-1"}).find_all('li') + nm = len(products_list) + for product in products_list: + # Finding the name of the product + name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text + name_of_product_cleaned = cleanString(name_of_product.strip()) + # print(name_of_product_cleaned) + name.append(name_of_product_cleaned) + #finding the URL try: - # Finding the name of the product - name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text - name_of_product_cleaned = cleanString(name_of_product.strip()) - print(name_of_product_cleaned) - name.append(name_of_product_cleaned) - #finding the URL - try: - url = product.find("div", {"class": "product-loop-content text-center"}).find("a").get("href") - print(url) - href.append(url) - except AttributeError as e: - print("I can't find the link") - raise e - - #finding the rating of the product - rating_score_of_product = product.find("div", {"class": "product-loop-content text-center"}).find("div").find("span").text - rating_item.append(cleanString(rating_score_of_product.strip())) - print("done") - #finding the rating of the vendors - rating_score_of_vendor = product.find("div", {"class": "wcfmmp-store-rating"}).find("strong").text - rating_vendor.append(cleanString(rating_score_of_vendor.strip())) - print("done") - #finding the cost in USD - cost = product.find("span", {"class": "woocommerce-Price-amount amount"}).text - USD.append(cost) - print("done") - #finding the name of the vendor - vendor_name = product.find("div", {"class": "wcfmmp_sold_by_wrapper"}).find("a").text - vendor.append(cleanString(vendor_name.strip())) - print("done") - #everything else appends a -1 - success.append("-1") - CVE.append("-1") - MS.append("-1") - category.append("-1") - describe.append("-1") - views.append("-1") - reviews.append("-1") - addDate.append("-1") - BTC.append("-1") - EURO.append("-1") - sold.append("-1") - qLeft.append("-1") - shipFrom.append("-1") - shipTo.append("-1") - print("Done! moving onto the next product!") - print(len(shipTo)) - nm += 1 + url = product.find("div", {"class": "product-loop-content text-center"}).find("a").get("href") + # print(url) + href.append(url) except AttributeError as e: - print("I'm somewhere I don't belong. I'm going to leave") - continue + print("I can't find the link") + raise e + + #finding the rating of the product + rating_score_of_product = product.find("div", {"class": "product-loop-content text-center"}).find("div").find("span").text + rating_item.append(cleanString(rating_score_of_product.strip())) + # print("done") + #finding the rating of the vendors + rating_score_of_vendor = product.find("div", {"class": "wcfmmp-store-rating"}).find("strong").text + rating_vendor.append(cleanString(rating_score_of_vendor.strip())) + # print("done") + #finding the cost in USD + cost = product.find("span", {"class": "woocommerce-Price-amount amount"}).text + USD.append(cost) + # print("done") + #finding the name of the vendor + vendor_name = product.find("div", {"class": "wcfmmp_sold_by_wrapper"}).find("a").text + vendor.append(cleanString(vendor_name.strip())) + # print("done") + #everything else appends a -1 + success.append("-1") + CVE.append("-1") + MS.append("-1") + category.append("-1") + describe.append("-1") + views.append("-1") + reviews.append("-1") + addDate.append("-1") + BTC.append("-1") + EURO.append("-1") + sold.append("-1") + qLeft.append("-1") + shipFrom.append("-1") + shipTo.append("-1") + # print("Done! moving onto the next product!") + # print(len(shipTo)) # Populate the final variable (this should be a list with all fields scraped) diff --git a/MarketPlaces/ViceCity/crawler_selenium.py b/MarketPlaces/ViceCity/crawler_selenium.py index cf7ea82..05250e9 100644 --- a/MarketPlaces/ViceCity/crawler_selenium.py +++ b/MarketPlaces/ViceCity/crawler_selenium.py @@ -271,7 +271,7 @@ def crawlForum(driver): driver.back() # comment out - break + # break # comment out if count == 1: