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.
282 lines
9.8 KiB
282 lines
9.8 KiB
__author__ = 'DarkWeb'
|
|
|
|
import re
|
|
|
|
# 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 vicecity_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('div', {'class': "listing_info"}).find('div', {'class': "listing_right"})
|
|
name = name.find('span', {'style': "font-size:18px;font-weight: bold;color: #fff"}).text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
# Finding Vendor
|
|
vendor = soup.find('div', {'class': "listing_info"})
|
|
vendor = vendor.find('div', {'class': "listing_right"})
|
|
numbers = vendor.find('a').find('span').text
|
|
vendor = vendor.find('a').text
|
|
vendor = vendor.replace(numbers, "").strip() # removes numbers at the end of vendor name
|
|
|
|
# Finding Vendor Rating
|
|
rating = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title')
|
|
rating = re.search(r"\d+%", rating)
|
|
rating_vendor = rating.group(0).strip()
|
|
|
|
# Finding Quantity Sold and Left
|
|
# temp = mb[4].text.split(',')
|
|
#
|
|
# sold = temp[0].replace("sold", "")
|
|
# sold = sold.strip()
|
|
#
|
|
# left = temp[1].replace("in stock", "")
|
|
# left = left.strip()
|
|
|
|
# Finding Successful Transactions
|
|
success = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"}).find('a').get('title')
|
|
success = re.search(r"\d+(?= sales)", success)
|
|
success = success.group(0).strip()
|
|
|
|
|
|
bae = soup.find('pre')
|
|
|
|
# Finding USD
|
|
USD = bae.find('span').text
|
|
USD = re.search(r"\$\d+(?:\.\d+)?", USD).group(0)
|
|
USD = USD.replace("$", "").strip()
|
|
|
|
# Finding BTC
|
|
BTC = bae.find_all('span')
|
|
BTC = re.search(r"\d+(?:\.\d+)?", BTC[1].text).group(0)
|
|
BTC = BTC.strip()
|
|
|
|
# Finding the Product Category
|
|
category = soup.find('div', {'class': "listing_info"}).find('div', {'class': "listing_right"})
|
|
category = category.find('span', {'style': "font-size:15px;color: #a1a1a1"}).text
|
|
category = category.replace("Category:", "").strip()
|
|
|
|
li = bae.find_all('span')
|
|
|
|
# Finding Shipment Information (Origin)
|
|
shipFrom = li[-4].text.strip()
|
|
|
|
# Finding Shipment Information (Destination)
|
|
shipTo = li[-2].text.strip()
|
|
|
|
# Finding the Product description
|
|
describe = soup.find('p', {
|
|
'style': "width:705px;margin-left:-305px;background-color: #242424;border-radius: 3px;border: 1px solid #373737;padding: 5px;"}).text
|
|
describe = describe.replace("\n", " ")
|
|
describe = describe.strip()
|
|
|
|
# Finding the Number of Product Reviews
|
|
li = soup.find_all('label', {'class': "tc_label threetabs"})
|
|
review = li[1].text
|
|
review = re.search(r"\d+", review)
|
|
if review:
|
|
reviews = review.group(0).strip()
|
|
else:
|
|
reviews = '0'
|
|
|
|
# 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 vicecity_listing_parser(soup):
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "ViceCity" # 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
|
|
|
|
listing = soup.findAll('div', {"class": "wLf"}) # should be 30
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
# # Finding Category
|
|
# cat = soup.find("div", {"class": "col-9"})
|
|
# cat = cat.find("h2").text
|
|
# cat = cat.replace("Category: ", "")
|
|
# cat = cat.replace(",", "")
|
|
# cat = cat.strip()
|
|
|
|
for a in listing:
|
|
# category.append(cat)
|
|
|
|
# bae = card.findAll('a')
|
|
|
|
# Adding the url to the list of urls
|
|
link = a.find('div', {"class": "wLfLeft"}).find('a', href=True).get('href')
|
|
link = cleanLink(link)
|
|
href.append(link)
|
|
|
|
# Finding the Product Name
|
|
product = a.find('div', {"class": "wLfName"}).find('a').text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = a.find('div', {"class": "wLfVendor"}).find('a').text
|
|
addedNums = a.find('div', {"class": "wLfVendor"}).find('a').find('span').text # finds numbers added at end
|
|
vendor_name = vendor_name.replace(",", "")
|
|
vendor_name = vendor_name.replace(addedNums, "") # removes numbers added at end
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# Finding Prices
|
|
price = a.find('div', {"class": "wLfPrice"}).find_all('span')
|
|
ud = price[0].text.replace(" USD", " ")
|
|
# u = ud.replace("$","")
|
|
ud = ud.replace(",", "")
|
|
u = ud.replace(price[1].text, "")
|
|
u = u.strip()
|
|
USD.append(u)
|
|
bc = price[1].text
|
|
bc = re.search(r"\d+(?:\.\d+)?", bc).group(0).strip()
|
|
BTC.append(bc)
|
|
|
|
# # Finding Reviews
|
|
# num = card.find("span", {"class": "rate-count"}).text
|
|
# num = num.replace("(", "")
|
|
# num = num.replace("review)", "")
|
|
# num = num.replace("reviews)", "")
|
|
# num = num.strip()
|
|
# reviews.append(num)
|
|
|
|
# Finding Successful Transactions
|
|
freq = a.find('div', {"class": "wLfVendor"}).find('a').get('title')
|
|
freq = re.search(r'\d+(?= sales)', freq).group(0)
|
|
freq = freq.strip()
|
|
success.append(freq)
|
|
|
|
# Finding Ship from and ship to
|
|
place = a.find('div', {"class": "wLfPrice"})
|
|
place = place.find('span', {'style': "font-size: 12px;"}).text
|
|
place = place.split('⟶')
|
|
varFrom = place[0].strip()
|
|
varTo = place[1].strip()
|
|
if varFrom == "WW":
|
|
varFrom = "Worldwide"
|
|
if varTo == "WW":
|
|
varTo = "Worldwide"
|
|
shipFrom.append(varFrom)
|
|
shipTo.append(varTo)
|
|
|
|
# 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 vicecity_links_parser(soup):
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.findAll('div', {"class": "wLf"})
|
|
|
|
for a in listing:
|
|
bae = a.find('div', {"class": "wLfLeft"}).find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|