__author__ = 'DarkWeb'
|
|
|
|
# Here, we are importing the auxiliary functions to clean or convert data
|
|
from typing import List, Tuple
|
|
from MarketPlaces.Utilities.utilities import *
|
|
|
|
# Here, we are importing BeautifulSoup to search through the HTML tree
|
|
from bs4 import BeautifulSoup, ResultSet, Tag
|
|
|
|
|
|
def thiefWorld_description_parser(soup: BeautifulSoup) -> Tuple:
|
|
|
|
# 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
|
|
|
|
name = soup.find("h1", {'class': 'title'}).text
|
|
name = cleanString(name.strip())
|
|
|
|
describe = soup.find('div', {'id': 'descriptionContent'}).text
|
|
describe = cleanString(describe.strip())
|
|
|
|
# Finding Product Image
|
|
image = soup.find('div', {'class': 'product_img_big'}).find('img')
|
|
image = image.get('src')
|
|
image = image.split('base64,')[-1]
|
|
|
|
commentListTag: Tag = soup.find('ul', {'class': 'comment_list scrollbar'})
|
|
commentList = commentListTag.find_all('li')
|
|
review = str(len(commentList))
|
|
|
|
citySelection: str = soup.find('ul', {'class': 'meta text-muted i_location'}).text
|
|
shipFrom = cleanString(citySelection.strip())
|
|
|
|
vendor = soup.find('h1', {'class': 'title over'}).text
|
|
vendor = cleanString(vendor.strip())
|
|
|
|
usdTag: Tag = soup.find('div', {'class': 'product_price__big'}).find('span')
|
|
usdText = usdTag.text.strip('/')[0]
|
|
# usdText format: "<value> USD " (i.e., "70 000 USD ")
|
|
USD = cleanString(usdText.replace("USD", "").strip())
|
|
|
|
ratingDiv = soup.find('div', {'class': 'rating_star'})
|
|
rating_vendor = ratingDiv.get('title').split(' ')[1]
|
|
|
|
rating_item = soup.find('div', {'class': 'product_rate'}).text
|
|
rating_item = rating_item.replace("rating", "")
|
|
rating_item = cleanString(rating_item.strip())
|
|
|
|
# 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
|
|
|
|
|
|
def thiefWorld_listing_parser(soup: BeautifulSoup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # Total_Products (Should be Integer)
|
|
mktName = "ThiefWorld" # 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 = [] # 20 Product_Image
|
|
image_vendor = [] # 21 Vendor_Image
|
|
href = [] # 22 Product_Links
|
|
|
|
productList: ResultSet[Tag] = soup.find_all('div', {'class': 'catalog_item'})
|
|
|
|
nm = len(productList)
|
|
|
|
for product in productList:
|
|
|
|
productTitle: Tag = product.find('div', {'class': 'title'}).find('a')
|
|
|
|
productName = cleanString(productTitle.text.strip())
|
|
name.append(productName)
|
|
|
|
# Finding Product Image
|
|
product_image = product.find('noscript').find('img')
|
|
product_image = product_image.get('src')
|
|
product_image = product_image.split('base64,')[-1]
|
|
image.append(product_image)
|
|
|
|
productHref = productTitle.get('href')
|
|
href.append(productHref)
|
|
|
|
CVE.append('-1')
|
|
MS.append('-1')
|
|
|
|
cat = soup.find('calsys-cat').text
|
|
category.append(cat.strip())
|
|
|
|
productDescription = product.find('div', {'class': 'text'}).text
|
|
productDescription = cleanString(productDescription.strip())
|
|
describe.append(productDescription)
|
|
|
|
views.append('-1')
|
|
reviews.append('-1')
|
|
addDate.append('-1')
|
|
BTC.append('-1')
|
|
|
|
priceText = product.find('span', {'class': 'price'}).find('span').text
|
|
priceText = priceText.split('USD')[0]
|
|
priceText = cleanString(priceText.strip())
|
|
USD.append(priceText)
|
|
|
|
EURO.append('-1')
|
|
sold.append('-1')
|
|
qLeft.append('-1')
|
|
shipFrom.append('-1')
|
|
shipTo.append('-1')
|
|
|
|
productVendor = product.find('div', {'class': 'market over'}).find('a').text
|
|
productVendor = cleanString(productVendor.strip())
|
|
vendor.append(productVendor)
|
|
|
|
image_vendor.append('-1')
|
|
|
|
rating_vendor.append('-1')
|
|
#rating_item.append('-1')
|
|
|
|
rating = product.find('div', {'class': 'rating_star_yellow'}).attrs.get('style')
|
|
rating = rating.replace("width: ", "")
|
|
rating_item.append(cleanString(rating))
|
|
|
|
success.append('-1')
|
|
|
|
|
|
# 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 thiefworld_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.find('div', {"class": "row tile__list tileitems_filter pad15 tileproduct__list"}).findAll('div', {"class": "desc"})
|
|
|
|
for a in listing:
|
|
bae = a.find('div', {"class": "title"}).find('a', href=True)
|
|
link = bae['href']
|
|
href.append(link)
|
|
|
|
return href
|