this is based on calsyslab project
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.
 

182 lines
8.0 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, ResultSet, Tag
# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
def thedarkmarket_description_parser(soup: BeautifulSoup):
# 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"
image_vendor = "-1"
details: Tag = soup.find("div", {"class": "wc-content"})
vendor = details.find("div", {"class": "product_meta"}).find("a", {"class": "wcvendors_cart_sold_by_meta"}).text
name = details.find("h1", {"class": "product_title entry-title"}).text
describe_list = [
elem.text for elem in
details.find("div", {"id": "tab-description"}).find_all()
if elem.name != "h2"
]
describe = " ".join(describe_list)
categories_list: ResultSet[Tag] = details.find("span", {"class": "posted_in"}).find_all("a")
category = "Hacking"
reviews = details.find("div", {"class": "review-link"}).get("title")
rating_item = details.find("div", {"class": "star-rating"}).get('title')
price_container = details.find("p", {"class": "price"})
if not price_container.find("ins"):
USD = price_container.find("span", {"class": "woocommerce-Price-amount amount"}).text.replace("$", "")
else:
USD = price_container.find("ins").find("span", {"class": "woocommerce-Price-amount amount"}).text.replace("$", "")
# print(f"\n[desc] Product: {name}")
# print(f"[desc] Price: ${USD}\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, image_vendor)
# Sending the results
return row
# This is the method to parse the Listing Pages
def thedarkmarket_listing_parser(soup: BeautifulSoup):
# Fields to be parsed
nm = 0 # *Total_Products (Should be Integer)
mktName = "TheDarkMarket" # 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
image = []
image_vendor = []
href = [] # 20 Product_Links
products_list: ResultSet[Tag] = soup.find("ul", {"class": "products columns-3"}).find_all("li")
for product in products_list:
nm += 1
product_vendor = product.find("small", {"class": "wcvendors_sold_by_in_loop"}).find("a").text
vendor.append(cleanString(product_vendor))
# rating_vendor.append("-1")
# success.append("-1")
product_name = product.find("h2", {"class": "woocommerce-loop-product__title"}).text
name.append(cleanString(product_name))
# CVE.append("-1")
# MS.append("-1")
product_category = product.find("div", {"class": 'product-categories'}).text
category.append(cleanString(product_category))
# describe.append("-1")
# views.append("-1")
# reviews.append("-1")
product_rating = product.find("div", {"class": "star-rating"}).get("title")
rating_item.append(cleanString(product_rating))
# addDate.append(datetime.now().strftime("%m/%d/%Y "))
# BTC.append("-1")
price_container = product.find("span", {"class": "price"})
if not price_container.find("ins"):
product_price = price_container.find("span", {"class": "woocommerce-Price-amount amount"}).text.replace("$", "")
else:
product_price = price_container.find("ins").find("span", {"class": "woocommerce-Price-amount amount"}).text.replace("$", "")
USD.append(cleanNumbers(product_price))
# EURO.append("-1")
# sold.append("-1")
# qLeft.append("-1")
# shipTo.append("-1")
# shipFrom.append("-1")
product_href = product.find("a", {"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"}).get("href")
href.append(product_href)
# print(f"\n[list] Product: {product_name}")
# print(f"[list] Links: ${product_href}\n")
product_images_list = product.find("a", {"class": "tf-loop-product-thumbs-link"}).find("img").get("data-srcset").split(" ")
product_image = product_images_list[0]
image.append(product_image)
# 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)
def thedarkmarket_links_parser(soup: BeautifulSoup):
# Returning all links that should be visited by the Crawler
href = []
listing: ResultSet[Tag] = soup.find("ul", {"class": "products columns-3"}).find_all("li")
for li in listing:
a = li.find('a', {"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"})
link = a.get('href')
href.append(link)
print(f"Links: {href}")
return href