dark_web_forums/MarketPlaces/MetaVerseMarket/parser.py

__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 metaversemarket_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('div', {'class': "panel-heading"}).text
    name = cleanString(name.strip())

    temp = soup.findAll('div', {'class': "col-xs-12 col-sm-6 mt-5"})

    # Finding Product Image
    image = temp[0].find('img')
    image = image.get('src')
    image = image.split('base64,')[-1]

    # Finding Vendor
    temp = temp[1].findAll('span')
    vendor = temp[1].find('b').text
    vendor = cleanString(vendor.strip())

    # Finding Vendor Rating
    pos = soup.find('span', {'class': "badge bg-success fs-12px"}).text
    pos = int(cleanNumbers(pos).strip())
    neg = soup.find('span', {'class': "badge bg-danger fs-12px"}).text
    neg = int(cleanNumbers(neg).strip())
    total = pos + neg
    if total > 0:
        rating_vendor = str(pos / total)

    # Finding Prices
    USD = soup.find('h3', {'class': "mb-2"}).text
    USD = cleanNumbers(USD).strip()

    # Finding the Product Category
    temp = soup.select('div[class="mt-2"]')[1].text
    temp = temp.replace("Category:", "")
    category = temp.strip()

    # Finding Number of Views
    views = soup.find('button', {"class": "btn btn-secondary text-center w-33 fw-bold"}).text
    views = views.strip()

    # Finding the Product Quantity Available
    temp = soup.find('button', {"class": "btn btn-success text-center w-33 fw-bold"}).text
    temp = temp.split("/")
    left = temp[1].strip()

    # Finding Number Sold
    sold = temp[0].strip()

    # Finding Shipment Information (Origin)
    temp = soup.find('div', {'class': "alert alert-info"}).text
    temp = temp.split("to")
    shipFrom = temp[0].replace("Shipping from ", "").strip()

    # Finding Shipment Information (Destination)
    shipTo = temp[1].split("for")
    shipTo = shipTo[0].strip()

    # Finding the Product description
    describe = soup.find('p', {'class': "card-text"}).text
    describe = cleanString(describe.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 = (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 metaversemarket_listing_parser(soup):
    # Fields to be parsed
    nm = 0                                    # *Total_Products (Should be Integer)
    mktName = "MetaVerseMarket"                     # 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 = soup.findAll('div', {"class": "col-12 col-sm-4 col-xl-3 product_item_col p-1"})

    # Populating the Number of Products
    nm = len(listing)

    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)

        # Finding the Product
        product = bae[1].find('span', {"class": "text-primary"}).text
        name.append(cleanString(product.strip()))

        # Finding Prices
        price = a.find('strong').text
        USD.append(cleanNumbers(price).strip())

        # Finding the Vendor
        temp = a.find('div', {'class': "mt-1 fs-12px"})
        temp = temp.findAll('span')
        vendor_name = temp[1].find('b').text
        vendor.append(cleanString(vendor_name.strip()))

        # Finding the Category
        cat = a.select_one('div[class="fs-12px"]')
        cat = cat.findAll('span')[1].text
        cat = cat.strip()
        category.append(cat)

        ul = a.find('ul', {"class": "product-actions"})

        # Finding Number Sold and Quantity Left
        temp = ul.find('span', {'class': "badge bg-success"}).text
        temp = temp.split("/")
        num = temp[0]
        num = num.replace('k', '000')
        sold.append(cleanNumbers(num).strip())

        quant = temp[1]
        quant = quant.replace('k', '000')
        qLeft.append(cleanNumbers(quant).strip())

        # Finding Descrption
        # description = a.find('p', {'class': "alert alert-light text-ssbold p-1"}).text
        # description = description.replace("\n", " ")
        # description = description.strip()
        # describe.append(cleanString(description))

        # Finding Number of Views
        view = ul.find('span', {'class': "badge bg-primary"}).text
        view = view.replace('.', '')
        view = view.replace('K', '000')
        views.append(view.strip())

        # Find where ships from
        ships = a.find('div', {'class': "alert alert-info item_alert fs-12px p-1"})
        ships = ships.findAll('b')
        sFrom = ships[0].text.strip()
        shipFrom.append(sFrom)

        # Find where it ships to
        sTo = ships[1].text.strip()
        shipTo.append(sTo)

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

    href = []
    listing = soup.findAll('div', {"class": "col-12 col-sm-4 col-xl-3 product_item_col p-1"})

    for a in listing:
        bae = a.find('a', href=True)
        link = bae['href']
        href.append(link)

    return href