You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
291 lines
11 KiB
291 lines
11 KiB
__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
|
|
rules = "-1" # 3 NOT USED ...
|
|
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
|
|
available = "-1" # 16 NOT USED ...
|
|
endDate = "-1" # 17 NOT USED ...
|
|
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, rules, CVE, MS, review, category, shipFrom, shipTo, left, escrow, terms, vendor,
|
|
sold, addDate, available, endDate, 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 tormarket_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.findAll('div', {"class": "product-loop-content text-center"})
|
|
|
|
for a in listing:
|
|
bae = a.find('h2', {"class": "woocommerce-loop-product__title"}).find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|