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.
295 lines
10 KiB
295 lines
10 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 metaversemarket_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('div', {'class': "panel-heading"}).text.strip
|
|
|
|
# Finding Vendor
|
|
temp = soup.findAll('div', {'class': "col-xs-12 col-sm-6 mt-5"})
|
|
temp = temp[1].findAll('span')
|
|
temp = temp[1].find('b').text
|
|
name = temp.replace("@", "")
|
|
|
|
# Finding Product Reviews
|
|
review = soup.find('span', {'class': "badge bg-success fs-12px"}).text.strip()
|
|
|
|
# Finding Successful Transactions
|
|
# NA
|
|
|
|
|
|
# Finding Prices
|
|
USD = soup.find('h3', {'class': "mb-2"}).text()
|
|
USD = USD.replace("Price: $", "").strip()
|
|
|
|
# Finding Escrow
|
|
escrow = soup.find('div', {'class': "alert alert-info text-center fw-bold"}).text
|
|
escrow = escrow.replace('You are protected by ', "").strip()
|
|
|
|
# Finding the Product Category
|
|
temp = soup.select('div[class="mt-2"]')
|
|
temp = temp[0].findAll('span')
|
|
category = temp[1].text.strip()
|
|
|
|
# Finding the Product Quantity Available
|
|
# temp = soup.find('em', {'class': "icon ni ni-layers-fill"}).parent.parent.parent
|
|
# left = temp.text
|
|
# left = left.replace("Supply:", "")
|
|
# left = left.strip()
|
|
temp = soup.findAll('span', {'class': "badge bg-success"})
|
|
temp = temp[1].text.split("/")
|
|
left = temp[1].strip()
|
|
|
|
# Finding Number Sold
|
|
sold = temp[0].strip()
|
|
|
|
|
|
# Finding Shipment Information (Origin)
|
|
temp = soup.findAll('div', {'class': "alert alert-info"})
|
|
temp = temp[1].text.split("to")
|
|
shipFrom = temp[0].replace("Shipping from ", "").strip()
|
|
|
|
# Finding Shipment Information (Destination)
|
|
shipTo = temp[1].split("for")
|
|
shipTo = shipTo[0].strip()
|
|
|
|
# Finding the Product description
|
|
describe = soup.find('p', {'class': "card-text"}).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 metaversemarket_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": "col-12 col-sm-4 col-xl-3 product_item_col p-1"})
|
|
|
|
# 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('span', {"class": "text-primary"}).text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding Prices
|
|
price = a.find('strong').text
|
|
price = price.replace("Buy for $", "")
|
|
price = price.strip()
|
|
USD.append(price)
|
|
|
|
|
|
# Finding the Vendor
|
|
temp = a.find('div', {'class': "mt-1 fs-12px"})
|
|
temp = temp.findAll('span')
|
|
temp = temp[1].find('b').text
|
|
vendor_name = temp.replace("@", "").strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# Finding the Category
|
|
cat = a.select_one('div[class="fs-12px"]')
|
|
cat = cat.findAll('span')[1].text
|
|
cat = cat.text
|
|
cat = cat.strip()
|
|
category.append(cat)
|
|
|
|
badge = a.findAll('span', {'class': "badge bg-success"})
|
|
# Finding Number Sold and Quantity Left
|
|
temp = badge[1].text
|
|
temp = temp.split("/")
|
|
num = temp[0]
|
|
num = num.strip()
|
|
sold.append(num)
|
|
|
|
quant = temp[1]
|
|
quant = quant.strip()
|
|
qLeft.append(quant)
|
|
|
|
# Finding Successful Transactions
|
|
# NA
|
|
|
|
# Finding Product review
|
|
review = a.find('span', {'class': "badge bg-success fs-12px"}).text
|
|
review = review.replace("+ ", "")
|
|
reviews.append(review)
|
|
|
|
# Finding Descrption
|
|
description = a.find('p', {'class': "alert alert-light text-ssbold p-1"}).text
|
|
description = description.replace("\n", " ")
|
|
description = description.strip()
|
|
describe.append(description)
|
|
|
|
# Finding Escrow
|
|
es = a.find('span', {'class': "fw-bold"}).text.strip()
|
|
escrow.append(es)
|
|
|
|
# Finding Number of Views
|
|
view = a.find('span', {'class': "badge bg-primary"}).text.strip()
|
|
views.append(view)
|
|
|
|
# Find where ships from
|
|
ships = a.find('div', {'class': "alert alert-info item_alert fs-12px p-1"})
|
|
ships = ships.findAll('b')
|
|
sFrom = ships[0].text.strips()
|
|
shipFrom.append(sFrom)
|
|
|
|
# Find where it ships to
|
|
sTo = ships[1].text.strips()
|
|
shipTo.append(sTo)
|
|
|
|
# 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 col-sm-4 col-xl-3 product_item_col p-1"})
|
|
|
|
for a in listing:
|
|
bae = a.find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|