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.
259 lines
11 KiB
259 lines
11 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 MikesGrandStore_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
|
|
name = soup.find('h1', {'class': 'product-title product_title entry-title'}).text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
divmb = soup.findAll('div', {'class': "mb-1"})
|
|
|
|
# Finding Vendor
|
|
# no vendor
|
|
vendor = "MikesGrandStore"
|
|
|
|
# Finding the Product Rating
|
|
rating_item = soup.find('strong', {'class', 'rating'}).text
|
|
rating_item = rating_item.replace('\n', ' ')
|
|
rating_item = rating_item.replace(",", "")
|
|
rating_item = rating_item.strip()
|
|
|
|
# Finding Number of Product Reviews
|
|
review_container = soup.find('li', {'id': 'tab-title-reviews'})
|
|
reviews = review_container.find('a').text
|
|
reviews = reviews.replace('Reviews', '')
|
|
reviews = reviews.replace('(', '')
|
|
reviews = reviews.replace(')', '')
|
|
reviews = reviews.replace('\n', ' ')
|
|
reviews = reviews.replace(",", "")
|
|
reviews = reviews.strip()
|
|
|
|
# Finding Prices
|
|
USD = soup.find('span', {'class': 'woocommerce-Price-currencySymbol'}).next_sibling
|
|
USD = USD.replace('\n', ' ')
|
|
USD = USD.replace(",", "")
|
|
USD = USD.strip()
|
|
|
|
# Finding the Product Category
|
|
cat_container = soup.find('span', {'class': 'posted_in'})
|
|
cat = cat_container.findAll('a')
|
|
category = ""
|
|
for name in cat:
|
|
category = category + " " + name.text
|
|
|
|
# Finding the Product Quantity Available
|
|
stock = soup.find('p', {'class': 'stock in-stock'})
|
|
if stock is not None:
|
|
left = stock.text
|
|
left = left.replace("in stock", "")
|
|
left = left.strip()
|
|
|
|
# Finding the Product description
|
|
desc_cont = soup.find('div', {'class': 'product-short-description'})
|
|
describe = desc_cont.find('p').text.strip()
|
|
|
|
# Finding Product Image
|
|
image = soup.find('img', {'class': 'wp-post-image skip-lazy'})
|
|
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 MikesGrandStore_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "MikesGrandStore" # 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_container = soup.find('div', {'class': 'products row row-small large-columns-3 medium-columns-3 small-columns-2 equalize-box'})
|
|
listing = listing_container.findAll('div', recursive=False)
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
for a in listing:
|
|
bae = a.findAll('a', href=True)
|
|
lb = a.findAll('div', {"id": "littlebox"})
|
|
|
|
# Adding the url to the list of urls
|
|
link = a.find('a', {'class': 'woocommerce-LoopProduct-link woocommerce-loop-product__link'}).get('href')
|
|
href.append(link)
|
|
|
|
# Finding the Product
|
|
product = a.find('a', {'class': 'woocommerce-LoopProduct-link woocommerce-loop-product__link'}).text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding Product Image
|
|
product_image = a.find('img', {'class': 'attachment-woocommerce_thumbnail size-woocommerce_thumbnail'})
|
|
product_image = product_image.get('src')
|
|
product_image = product_image.split('base64,')[-1]
|
|
image.append(product_image)
|
|
|
|
# Finding Prices
|
|
price = a.find('span', {'class': 'woocommerce-Price-currencySymbol'}).next_sibling
|
|
price = price.strip()
|
|
USD.append(price)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = "MikesGrandStore"
|
|
vendor.append(vendor_name)
|
|
|
|
image_vendor.append("-1")
|
|
|
|
# Finding the Category
|
|
cat = a.find('p', {'class': 'category uppercase is-smaller no-text-overflow product-cat op-7'}).text
|
|
cat = cat.replace("class:", "")
|
|
cat = cat.strip()
|
|
category.append(cat)
|
|
|
|
# Finding product rating
|
|
rating = a.find('strong', {'class': 'rating'}).text
|
|
rating = rating.strip()
|
|
rating_item.append(rating)
|
|
|
|
|
|
# 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 MikesGrandStore_links_parser(soup):
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
container = soup.find('div', {"class": "products row row-small large-columns-3 medium-columns-3 small-columns-2 equalize-box"})
|
|
listing = container.findAll('div', recursive=False)
|
|
|
|
# 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
|