dark_web_forums/MarketPlaces/DarkBazar/parser.py

# 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 darkbazar_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

    # Finding Product Name
    divmb = soup.findAll('div', {'class': "mb-1"})

    name = divmb[0].text
    name = name.replace('\n', ' ')
    name = name.replace(",", "")
    name = name.strip()

    # Finding Vendor
    vendor = divmb[1].find('a').text.strip()

    # Finding Vendor Rating
    rating = soup.find('div', {'class': ""}).text
    rating = rating.replace("Vendor's Review : ", "")
    rating = rating.strip()

    # Finding Successful Transactions
    success = divmb[3].text
    success = success.replace("Level:", "")
    success = success.strip()

    # Finding Prices
    USD = soup.find('div', {'class': "h3 text - primary"}).text.strip()


    # Finding Escrow
    escrow = divmb[5].find('span', {'class': "badge badge-danger"}).text.strip()

    # 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)
    pmb[0].text
    shipFrom = shipFrom.replace("Ships from: ", "").strip()

    # Finding Shipment Information (Destination)
    pmb[1].text
    shipTo = shipTo.replace("Ships to: ", "").strip()

    # Finding the Product description
    cardbody = soup.findAll('div', {'class': "card-body"})
    describe = cardbody[1].text.strip()

    # Finding the Number of Product Reviews
    reviews = reviews.find('div', {'class': "product-rating"}).text
    reviews = reviews.replace("(", "")
    reviews = reviews.replace(" review)", "")
    reviews = reviews.strip()


    # 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 = (name, describe, CVE, MS, review, category, shipFrom, shipTo, left, escrow, vendor,
           sold, addDate, BTC, USD, rating, success, EURO)

    # 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 darkbazar_listing_parser(soup):
    # Fields to be parsed
    nm = 0  # Total_Products (Should be Integer)
    mktName = "DarkBazar"  # 0 Marketplace_Name
    name = []  # 1 Product_Name
    CVE = []  # 2 Product_CVE_Classification (Common Vulnerabilities and Exposures)
    MS = []  # 3 Product_MS_Classification (Microsoft Security)
    category = []  # 4 Product_Category
    describe = []  # 5 Product_Description
    escrow = []  # 6 Vendor_Warranty
    views = []  # 7 Product_Number_Of_Views
    reviews = []  # 8 Product_Number_Of_Reviews
    addDate = []  # 9 Product_AddDate
    lastSeen = []  # 10 Product_LastViewDate
    BTC = []  # 11 Product_BTC_SellingPrice
    USD = []  # 12 Product_USD_SellingPrice
    EURO = []  # 13 Product_EURO_SellingPrice
    sold = []  # 14 Product_QuantitySold
    qLeft = []  # 15 Product_QuantityLeft
    shipFrom = []  # 16 Product_ShippedFrom
    shipTo = []  # 17 Product_ShippedTo
    vendor = []  # 18 Vendor
    rating = []  # 19 Vendor_Rating
    success = []  # 20 Vendor_Successful_Transactions
    href = []  # 23 Product_Links (Urls)

    listing = soup.findAll('div', {"id": "itembox"})

    # 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 = bae[0].get('href')
        link = cleanLink(link)
        href.append(link)

        # Finding the Product
        product = lb[1].find('a').text
        product = product.replace('\n', ' ')
        product = product.replace(",", "")
        product = product.replace("...", "")
        product = product.strip()
        name.append(product)

        # Finding Prices
        price = lb[-1].find('div', {"class": "mb-1"}).text
        price = price.replace("$","")
        price = price.strip()
        USD.append(price)

        # Finding the Vendor
        vendor_name = lb[-1].find("a").text
        vendor_name = vendor_name.replace(",", "")
        vendor_name = vendor_name.strip()
        vendor.append(vendor_name)

        # Finding the Category
        cat = lb[-1].find("span").text
        cat = cat.replace("class:", "")
        cat = cat.strip()
        category.append(cat)

        # Finding Number Sold and Quantity Left
        span = lb[1].findAll("span")
        num = span[-1].text
        num = num.replace("Sold:", "")
        num = num.strip()
        category.append(num)

        quant = span[1].text
        quant = quant.replace("stock:", "")
        quant = quant.strip()
        qLeft.append(quant)


        # 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, name, CVE, MS, category, describe, escrow, views, reviews, addDate, lastSeen,
                            BTC, USD, EURO, qLeft, shipFrom, shipTo, vendor, rating, success, sold, href)


# 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 darkbazar_links_parser(soup):
    # Returning all links that should be visited by the Crawler

    href = []
    listing = soup.findAll('div', {"id": "itembox"})

    # 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')
        link = cleanLink(link)
        href.append(link)

    return href