dark_web_forums/MarketPlaces/HiddenMarket/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


# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
def hiddenmarket_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

    bae = soup.find('div', {'class': "main"})

    # Finding Product Name
    name = bae.find('div', {'class': "heading"}).text
    name = name.replace('\n', ' ')
    name = name.replace(",", "")
    name = name.strip()

    mb = bae.find('div', {'class': "information"}).findAll('tr')

    # Finding Vendor
    vendor = mb[1].find('a').text
    vendor = vendor.replace(",", "")
    vendor = vendor.strip()

    # # Finding Vendor Rating
    # full_stars = bae[2].find_all('i', {'class': "fas fa-star"})
    # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"})
    # rating = len(full_stars) + (0.5 if half_star is not None else 0)

    # Finding Quantity Left
    temp = mb[-3].text
    left = temp.replace("Quantity in stock:", "")
    left = left.strip()

    # Finding USD
    USD = mb[0].text
    USD = USD.replace("Price:", "")
    USD = USD.replace("USD", "")
    USD = USD.strip()

    # Finding BTC
    # temp = bae.find('div', {"class": "small"}).text.split("BTC")

    # BTC = temp[0].strip()

    # Finding Shipment Information (Origin)
    shipFrom = mb[2].text
    shipFrom = shipFrom.replace("Seller location:", "")
    shipFrom = shipFrom.strip()

    # Finding Shipment Information (Destination)
    shipTo = mb[3].text
    shipTo = shipTo.replace("Ships to (seller):", "")
    shipTo = shipTo.strip()

    # Finding the Product description
    describe = bae.find('div', {"class": "twotabs"}).find('div', {'class': "tab1"}).text
    describe = describe.replace("\n", " ")
    describe = describe.replace("\r", " ")
    describe = describe.replace("-", " ")
    describe = describe.strip()

    # Finding Product Image
    image = soup.find('div', {"class": "thumbnails"}).find('img', {"class": "bigthumbnail"})
    image = image.get('src')

    # Finding the Product Category
    category = mb[-4].text
    category = category.replace("Category:", "")
    category = category.strip()

    #Finding the number of reviews
    reviews = bae.find_all('div', {'class': "heading"})
    reviews = reviews[-2].text
    reviews = reviews.replace("Comments (", "")
    reviews = reviews.replace(")", "")

    # 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


# This is the method to parse the Listing Pages
def hiddenmarket_listing_parser(soup):
    # Fields to be parsed
    nm = 0  # *Total_Products (Should be Integer)
    mktName = "HiddenMarket"  # 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

    listing = soup.findAll('div', {"class": "item"})

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

    # Finding Category
    # cat = soup.find("div", {'class': "heading"}).text
    # cat = cat.replace(",", "")
    # cat = cat.strip()

    for card in listing:
        # category.append(cat)


        # Adding the url to the list of urls
        link = card.find_all('a')
        link = link[1].get('href')

        href.append(link)

        # Finding Product Name
        product = card.next_sibling.find('div', {'class': "title"})
        product = product.text
        product = product.replace('\n', ' ')
        product = product.replace(",", "")
        product = product.strip()
        name.append(product)

        # Finding Product Image
        image.append("-1")

        # Finding Vendor
        vendor_name = card.text
        vendor_name = vendor_name.replace(",", "")
        vendor_name = vendor_name.strip()
        vendor.append(vendor_name)

        image_vendor.append("-1")

        # Finding USD
        usd = card.next_sibling.find('div', {"class": "buttons"}).find('div', {'class': "price"}).text
        usd = usd.replace("USD", "")
        usd = usd.strip()
        USD.append(usd)

        tb = card.next_sibling.find("div", {"class": "stats"})
        tb = tb.find_all('td')

        # Finding Reviews
        num = tb[-1].text
        num = num.strip()
        reviews.append(num)

        # Finding Views
        view = tb[-3].text.strip()
        views.append(view)

        # Finding Num of Sales
        sale = tb[-2].text.strip()
        sold.append(sale)

        # Finding Item Rating
        if num == '0':
            item_rating = '-1'
        else:
            item_rating = card.next_sibling.find('div', {'class': 'stats'}).find('div', {'class': "stars2"})
            item_rating = item_rating.get('style')
            item_rating = item_rating.replace("width:", "")
            item_rating = item_rating.replace("%", "")
            item_rating = (float(item_rating) * 5.0) / 100.0
            item_rating = "{:.{}f}".format(item_rating, 2)
        rating_item.append(item_rating)


        # Finding shipping info
        shipping = card.next_sibling.find('div', {'class': "shipping"}).text.split('>')
        # SHip from
        origin = shipping[0].strip()
        shipFrom.append(origin)
        #Ship to
        destination = shipping[1].strip()
        shipTo.append(destination)

        # Finding description (site only shows partial description on listing pages)
        # description = card.next_sibling.find('div', {'class': "description"}).text
        # description = description.replace("\n", " ")
        # description = description.replace("\r", " ")
        # description = description.replace("-", " ")
        # description = description.strip()
        # describe.append(description)

        # Searching for CVE and MS categories
        cve = card.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 = card.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)


def hiddenmarket_links_parser(soup):
    # Returning all links that should be visited by the Crawler
    href = []

    listing = soup.findAll('div', {"class": "item"})

    for div in listing:
        link = div.findAll('a')
        link = link[1]
        link = link['href']
        href.append(link)

    return href