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.
304 lines
12 KiB
304 lines
12 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 gofish_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
|
|
image = "-1" # 19 Product_Image
|
|
vendor_image = "-1" # 20 Vendor_Image
|
|
|
|
# Finding Product Name
|
|
|
|
divmb = soup.find('div', {'class': "p-3 mb-1 fs-3 fw-bold border border-2 bg-white rounded"})
|
|
if divmb is None:
|
|
divmb = soup.find('div', {'class': "p-3 mb-1 fs-4 fw-bold border border-2 bg-white rounded"})
|
|
|
|
name = divmb.text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace('\r', ' ')
|
|
name = name.replace('\t', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
# Finding Vendor
|
|
vendor = soup.find('div', {'class': 'my-1'}).find('a').text.strip()
|
|
|
|
# Finding Vendor Rating
|
|
# temp = soup.find('div', {'class': ""}).text
|
|
# temp = temp.split('(')
|
|
# rating = temp[0].replace("Vendor's Review : ", "")
|
|
# rating = rating.replace("%", "")
|
|
# rating_vendor = rating.strip()
|
|
|
|
# Finding the Product Rating and Number of Product Reviews
|
|
# reviews = temp[2].replace(" review)", "")
|
|
# reviews = reviews.strip()
|
|
|
|
# temp = temp[1].split(")")
|
|
# rating = temp[1].replace("Product Review : ", "")
|
|
# rating = rating.replace("%", "")
|
|
# rating_item = rating.strip()
|
|
|
|
# Finding Prices
|
|
precios = soup.findAll('td', {'class': "text-end text-nowrap"})
|
|
USD = precios[0].text.strip().replace('$', '')
|
|
|
|
# Finding the Product Category
|
|
# pmb = soup.findAll('p', {'class': "mb-1"})
|
|
|
|
# category = pmb[-1].text
|
|
# category = category.replace("Category: ", "").strip()
|
|
|
|
# Finding the Product Quantity Available
|
|
# left = divmb[-1].text
|
|
# left = left.split(",", 1)[1]
|
|
# left = left.replace("in stock", "")
|
|
# left = left.strip()
|
|
|
|
# Finding Number Sold
|
|
# sold = divmb[-1].text
|
|
# sold = sold.split(",", 1)[0]
|
|
# sold = sold.replace("sold", "")
|
|
# sold = sold.strip()
|
|
|
|
# Finding Shipment Information (Origin)
|
|
origin = soup.findAll('div', {'class': "p-3 mt-2 mb-3 border border-2 bg-white rounded"})
|
|
remove = origin[0].find('span').text.strip()
|
|
origin = origin[0].text.strip()
|
|
origin = origin.replace(remove, '')
|
|
|
|
shipFrom = origin.strip()
|
|
|
|
# Finding Shipment Information (Destination)
|
|
dest = soup.findAll('div', {'class': 'p-3 mb-3 overflow-auto border border-2 bg-white rounded'})
|
|
dest = dest[-1].text.strip()
|
|
dest = dest.replace('[', '')
|
|
dest = dest.replace(']', '')
|
|
|
|
shipTo = dest[1:].strip()
|
|
|
|
# Finding the Product description
|
|
cardbody = soup.findAll('div', {'class': "p-3 mb-3 overflow-auto border border-2 bg-white rounded"})
|
|
describe = cardbody[0].text
|
|
describe = describe.replace('\n', ' ')
|
|
describe = describe.strip()
|
|
|
|
# Finding Product Image
|
|
img = soup.findAll('figure', {'class': 'image-feature'})[0]
|
|
image = img.find('img', {'class': 'image-block rounded'})
|
|
image = image.get('src')
|
|
image = image.split('base64,')[-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 = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate,
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image)
|
|
|
|
# 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 gofish_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "GoFish" # 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) dont worry about this
|
|
MS = [] # 6 Product_MS_Classification (Microsoft Security) dont worry about this
|
|
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
|
|
image = [] # 20 Product_Image
|
|
image_vendor = [] # 21 Vendor_Image
|
|
href = [] # 22 Product_Links
|
|
|
|
listing = soup.find('tbody', {"class": "border border-2 align-middle"}).findAll('tr')
|
|
|
|
# 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')
|
|
href.append(link)
|
|
|
|
# Finding the Product
|
|
product = bae[1].text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding Product Image
|
|
product_image = bae[0].find('img')
|
|
product_image = product_image.get('src')
|
|
product_image = product_image.split('base64,')[-1]
|
|
image.append(product_image)
|
|
|
|
# Finding Prices
|
|
price = a.find('span', {"class": "fw-bold text-nowrap"}).text
|
|
price = price.replace("$","")
|
|
price = price.strip()
|
|
USD.append(price)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = bae[-1].text
|
|
vendor_name = vendor_name.replace(",", "")
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
image_vendor.append("-1")
|
|
|
|
# Finding the Category
|
|
# cat = lb[-1].find("span").text
|
|
# cat = cat.replace("class:", "")
|
|
# cat = cat.strip()
|
|
# category.append(cat)
|
|
|
|
# span = lb[0].findAll("span")
|
|
|
|
# Finding Number of Views
|
|
# num = span[0].text
|
|
# num = num.replace("views:", "")
|
|
# num = num.strip()
|
|
# sold.append(num)
|
|
|
|
# Finding Number Sold
|
|
# num = span[2].text
|
|
# num = num.replace("Sold:", "")
|
|
# num = num.strip()
|
|
# sold.append(num)
|
|
|
|
# Finding Quantity Left
|
|
# quant = span[1].text
|
|
# quant = quant.replace("stock:", "")
|
|
# quant = quant.strip()
|
|
# qLeft.append(quant)
|
|
|
|
# add shipping information
|
|
# ship = lb[2].findAll('small')[1].findAll('span')[1].text.split("->")
|
|
# shipFrom.append(ship[0].replace("Ship from ", "").strip())
|
|
# shipTo.append(ship[1].replace("to ", "").strip())
|
|
|
|
|
|
# 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, image, image_vendor)
|
|
|
|
|
|
# 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 gofish_links_parser(soup):
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.find('tbody', {'class': 'border border-2 align-middle'})
|
|
listing = soup.findAll('tr')
|
|
listing = listing[1:]
|
|
# for a in listing:
|
|
# bae = a.find('a', {"class": "text-info"}, href=True)
|
|
# link = bae['href']
|
|
# href.append(link)
|
|
|
|
for a in listing:
|
|
bae = a.findAll('a', href=True)
|
|
|
|
# Adding the url to the list of urls
|
|
link = bae[0].get('href')
|
|
href.append(link)
|
|
|
|
return href
|