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.
189 lines
8.9 KiB
189 lines
8.9 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
|
|
|
|
import re
|
|
|
|
#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 tormarket_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 the name of the product
|
|
name_of_product = soup.find("h1", {"class": "product_title entry-title"}).find("a").text
|
|
name = cleanString(name_of_product.strip())
|
|
|
|
#finding the description of the product
|
|
description_of_product = soup.find("div", {"class": "woocommerce-product-details__short-description"}).text
|
|
describe = cleanString(description_of_product.strip())
|
|
|
|
#finding the name of the vendor
|
|
name_of_vendor = soup.find("div", {"class": "wcfmmp_sold_by_store"})
|
|
if name_of_vendor is not None:
|
|
name_of_vendor = name_of_vendor.find("a").text
|
|
vendor = cleanString(name_of_vendor.strip())
|
|
else:
|
|
vendor = "TorMarket"
|
|
|
|
#finding the price of the item
|
|
price = soup.find("p", {"class": "price"}).find("bdi").text
|
|
price_cleaned = price[1:]
|
|
USD = price_cleaned.strip()
|
|
|
|
category = soup.find('span', {"class": "posted_in"}).text
|
|
category = category.split(':')[-1]
|
|
category = category.replace(',', '/')
|
|
category = cleanString(category.strip())
|
|
#everything else gets a -1 because they are not found
|
|
|
|
# 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 tormarket_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "TorMarket" # 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
|
|
|
|
products_list = soup.find('ul', {"class": "products columns-3 tablet-columns-2 mobile-columns-1"}).find_all('li')
|
|
nm = len(products_list)
|
|
|
|
for product in products_list:
|
|
# Finding the name of the product
|
|
name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text
|
|
name_of_product_cleaned = cleanString(name_of_product.strip())
|
|
# print(name_of_product_cleaned)
|
|
name.append(name_of_product_cleaned)
|
|
#finding the URL
|
|
try:
|
|
url = product.find("div", {"class": "product-loop-content text-center"}).find("a").get("href")
|
|
# print(url)
|
|
href.append(url)
|
|
except AttributeError as e:
|
|
print("I can't find the link")
|
|
raise e
|
|
|
|
#finding the rating of the product
|
|
rating_score_of_product = product.find("div", {"class": "product-loop-content text-center"}).find("div").find("span").text
|
|
rating_item.append(cleanString(rating_score_of_product.strip()))
|
|
# print("done")
|
|
#finding the rating of the vendors
|
|
rating_score_of_vendor = product.find("div", {"class": "wcfmmp-store-rating"})
|
|
if rating_score_of_vendor is not None:
|
|
rating_score_of_vendor = rating_score_of_vendor.find("strong").text
|
|
rating_vendor.append(cleanString(rating_score_of_vendor.strip()))
|
|
else:
|
|
rating_vendor.append('-1')
|
|
# print("done")
|
|
#finding the cost in USD
|
|
cost = product.find("span", {"class": "woocommerce-Price-amount amount"}).text
|
|
USD.append(cost)
|
|
# print("done")
|
|
#finding the name of the vendor
|
|
vendor_name = product.find("div", {"class": "wcfmmp_sold_by_wrapper"})
|
|
if vendor_name is not None:
|
|
vendor_name = vendor_name.find("a").text
|
|
vendor.append(cleanString(vendor_name.strip()))
|
|
else:
|
|
vendor.append(mktName)
|
|
# print("done")
|
|
#everything else appends a -1
|
|
success.append("-1")
|
|
CVE.append("-1")
|
|
MS.append("-1")
|
|
category.append("-1")
|
|
describe.append("-1")
|
|
views.append("-1")
|
|
reviews.append("-1")
|
|
addDate.append("-1")
|
|
BTC.append("-1")
|
|
EURO.append("-1")
|
|
sold.append("-1")
|
|
qLeft.append("-1")
|
|
shipFrom.append("-1")
|
|
shipTo.append("-1")
|
|
# print("Done! moving onto the next product!")
|
|
# print(len(shipTo))
|
|
|
|
|
|
# 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 tormarket_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.findAll('div', {"class": "product-loop-content text-center"})
|
|
|
|
for a in listing:
|
|
bae = a.find('h2', {"class": "woocommerce-loop-product__title"}).find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|