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.
289 lines
12 KiB
289 lines
12 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
|
|
|
|
|
|
# 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 bohemia_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('h1', {"style": "margin: 0; margin-bottom: 0.5em;"}).text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
# Finding Vendor
|
|
vendor = soup.find('div', {"class": "user-photo"}).find_next_sibling('a').text
|
|
vendor = vendor.strip()
|
|
|
|
# Finding Vendor Rating
|
|
rating_vendor = soup.find('span', {'class': "user-percent"}).text.strip()
|
|
|
|
# Finding Users' Successful Transactions
|
|
temp = ''
|
|
success = soup.find('span', {'class': "smalltext shadow-text"}).text
|
|
temp = success.split("|")
|
|
success = str(temp[1])
|
|
success = success.strip()
|
|
|
|
# Finding Prices
|
|
prices = soup.find('div', {'class': "col-md-3 sidebar-navigation user-details"}
|
|
).find('div', {'class': "container text-left"})
|
|
USD = prices.find('h1').text.strip()
|
|
BTC = prices.find('h1').find_next_sibling('h3').text
|
|
BTC = BTC.replace("BTC", "")
|
|
BTC = BTC.strip()
|
|
|
|
detail_row = soup.find('div', {'class': "detail-container text-left"}).find_all('strong')
|
|
|
|
# Finding the Product Category (there isnt a thing for it on the page
|
|
# category = li[1].find('span', {'class': "tag is-dark"}).text.strip()
|
|
|
|
# Finding the Product Quantity Available
|
|
left = soup.find('div', {'class': "container detail-container text-left"})
|
|
left = left.find('div', {'class': "detail-row"}).text.replace('\n', '')
|
|
left = left.split("Available Stock:")
|
|
left = left[1].strip()
|
|
|
|
# Finding Number Sold
|
|
sold = detail_row[0].find_parent()
|
|
sold = sold.text
|
|
sold = sold.replace("Total Sold:", "")
|
|
sold = sold.strip()
|
|
|
|
# Finding Shipment Information (Origin) (There is no shipping information)
|
|
'''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) (No shipping info
|
|
'''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': "container feedback-container"})
|
|
describe = describe.find_next_sibling('div', {'class': "container"}).find('p').text
|
|
describe = describe.replace("\n", " ")
|
|
describe = describe.strip()
|
|
|
|
# Finding the Number of Product Reviews
|
|
review = detail_row[2].find_parent().text
|
|
review = review.split("Based on")
|
|
review = review[1].replace("ratings)", "").strip()
|
|
|
|
# Searching for CVE and MS categories (cant find it)
|
|
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 bohemia_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "Bohemia" # 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": "product-link"})
|
|
|
|
# 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[0].text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
bae = a.find('div', {'class': "container"})
|
|
|
|
# Finding Prices
|
|
price = bae.find('div', {'class': "product-price"}).find('h2').text
|
|
ud = price.replace("USD", " ")
|
|
# u = ud.replace("$","")
|
|
ud = ud.replace(",", "")
|
|
ud = ud.strip()
|
|
USD.append(ud)
|
|
bc = bae.find('div', {'class': "product-price"}).find('span', {'class': "shadow-text smalltext boldtext"}).text
|
|
bc = bc.replace("\n", "")
|
|
bc = bc.split()
|
|
bc = bc[0].replace("BTC", "").strip()
|
|
BTC.append(bc)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = bae.find('b').find('a').text
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# Finding the Category
|
|
cat = bae.find('span', {'class': "shadow-text smalltext"}).find('strong').text
|
|
cat = cat.strip()
|
|
category.append(cat)
|
|
|
|
# Finding Number Sold and Quantity Left
|
|
num = bae.find('div', {'class': "product-details-bottom"}).find('span').text
|
|
num = num.replace("Sold", "")
|
|
num = num.replace("times in total", "")
|
|
num = num.strip()
|
|
sold.append(num)
|
|
|
|
quant = bae.find('div', {'class': "product-price"}).text
|
|
quant = quant.replace("\n", "")
|
|
quant = quant.split("Available")
|
|
quant = quant[0].replace("Autoship", "").strip()
|
|
qLeft.append(quant)
|
|
|
|
# Finding Successful Transactions
|
|
freq = bae.find('div', {'title': "Total Sales"}).find_parent().text.replace("\n", "")
|
|
freq = freq.strip().split()
|
|
freq = freq[-1].strip()
|
|
success.append(freq)
|
|
|
|
# find vendor rating
|
|
rate = bae.find('b').find('strong').text.strip()
|
|
rating_vendor.append(rate)
|
|
|
|
# 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 bohemia_links_parser(soup):
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
|
|
temp = soup.find('div', {"class": "col-md-9 sidebar-content-right listing-content"})
|
|
temp = temp.find('div', {"class": "product-listing"})
|
|
listing = temp.findAll('div', {"class": "product-heading"})
|
|
|
|
for a in listing:
|
|
bae = a.find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|