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.
240 lines
8.6 KiB
240 lines
8.6 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
|
|
|
|
|
|
# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
|
|
def royal_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
|
|
name = soup.find('h5', {'class': "bold"}).text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
bae = soup.find('div', {'class': "card-header bg-light"})
|
|
|
|
# Finding Vendor
|
|
vendor = bae.find('a').text
|
|
vendor = vendor.replace(",", "")
|
|
vendor = vendor.strip()
|
|
|
|
# # Finding Vendor Rating
|
|
# full_stars = bae[2].find_all('i', {'class': "fas fa-star"})
|
|
# half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"})
|
|
# rating = len(full_stars) + (0.5 if half_star is not None else 0)
|
|
|
|
# Finding Successful Transactions
|
|
success = bae.find('b').text
|
|
success = success.replace("(", "")
|
|
success = success.replace(")", "")
|
|
success = success.strip()
|
|
|
|
form = soup.find_all('form', {'method': "POST"})
|
|
bae = form[1].find_all('div', {'class': "row"})
|
|
|
|
# Finding Quantity Sold
|
|
div = bae[2].find_all('div', {'class': "col"})
|
|
temp = div[1].text
|
|
temp = temp.split()
|
|
if len(temp) > 0:
|
|
sold = temp[0].strip()
|
|
sold = re.sub(r'[^0-9.]', "", sold)
|
|
if sold == "":
|
|
sold = -1
|
|
else:
|
|
sold = -1
|
|
|
|
# Finding Quantity Left
|
|
div = bae[3].find_all('div', {'class': "col"})
|
|
temp = div[1].text
|
|
temp = temp.split()
|
|
if len(temp) > 0:
|
|
left = temp[0].strip()
|
|
left = re.sub(r'[^0-9.]', "", left)
|
|
if left == "":
|
|
left = -1
|
|
else:
|
|
left = -1
|
|
|
|
# Finding Prices
|
|
temp = bae[-2].find('strong').text
|
|
temp = temp.replace("Price:", "")
|
|
temp = temp.split()
|
|
USD = temp[0].strip()
|
|
USD = re.sub(r'[^0-9.]', "", USD)
|
|
|
|
# shipping_info = bae[4].text
|
|
# if "Digital" not in shipping_info:
|
|
# shipping_info = shipping_info.split(" ")
|
|
#
|
|
# # Finding Shipment Information (Origin)
|
|
# shipFrom = shipping_info[0].strip()
|
|
#
|
|
# # Finding Shipment Information (Destination)
|
|
# shipTo = shipping_info[1].strip()
|
|
|
|
# Finding the Product description
|
|
describe = soup.find('xmp').text
|
|
describe = describe.replace("\n", " ")
|
|
describe = describe.replace("\r", " ")
|
|
describe = describe.strip()
|
|
|
|
# Searching for CVE and MS categories
|
|
cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
|
|
if cve:
|
|
CVE = " "
|
|
for idx in cve:
|
|
CVE += (idx)
|
|
CVE += " "
|
|
CVE = CVE.replace(',', ' ')
|
|
CVE = CVE.replace('\n', '')
|
|
ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
|
|
if ms:
|
|
MS = " "
|
|
for im in ms:
|
|
MS += (im)
|
|
MS += " "
|
|
MS = MS.replace(',', ' ')
|
|
MS = MS.replace('\n', '')
|
|
|
|
# Populating the final variable (this should be a list with all fields scraped)
|
|
row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate,
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo)
|
|
|
|
# Sending the results
|
|
return row
|
|
|
|
|
|
# This is the method to parse the Listing Pages
|
|
def royal_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "Royal" # 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)
|
|
MS = [] # 6 Product_MS_Classification (Microsoft Security)
|
|
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
|
|
|
|
# Finding category of listing page
|
|
cat = soup.find('li', {'class': "breadcrumb-item active"}).text
|
|
cat = cat.strip()
|
|
|
|
listing = soup.findAll('div', {'class': "card search border shadow-sm mb-3"})
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
for a in listing:
|
|
bae = a.findAll('a', href=True)
|
|
|
|
# Adding the category
|
|
category.append(cat)
|
|
|
|
# Adding the url to the list of urls
|
|
link = bae[1].get('href')
|
|
link = cleanLink(link)
|
|
href.append(link)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = bae[0].text
|
|
vendor_name = vendor_name.replace(",", "")
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# Finding the Product
|
|
product = bae[2].get('title')
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# 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)
|
|
|
|
|
|
def royal_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
href = []
|
|
|
|
listing = soup.findAll('div', {"class": "card search border shadow-sm mb-3"})
|
|
|
|
for div in listing:
|
|
|
|
a = div.find_all('a')
|
|
link = a[1].get('href')
|
|
href.append(link)
|
|
|
|
return href
|