dark_web_forums/MarketPlaces/DarkBay/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 darkbay_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



    # vendor name
    vendor = soup.find('div', {'class', 'vendor'}).find('a').text

    # product name
    name = soup.find('h3').text

    # description
    describe = soup.find('div', {'class', 'description'}).text.replace('\n', ' ')

    # category
    category = soup.find('i', {'class', 'fas fa-folder'}).text

    # finding price
    money = soup.find('div', {'class', 'price'})
    BTC = money.find('span', {'class', 'btc'}).text.replace('$','')
    USD = money.find('span', {'class', 'usd'}).text.replace('₿','')

    if soup.find('div', {'class': 'instock many'}):
        left = soup.find('div', {'class': 'instock many'}).text
        if 'in stock' in left:
            left.replace('in stock', '').strip()
            if left == '':
                left = '-1'

    # ship to and ship from
    location = soup.find('dl', {'class': 'compact ships mb1'}).findAll('dd')
    shipFrom = location[0].text
    shipFrom = ''.join(c for c in shipFrom if c.isalnum())
    shipFrom = shipFrom.strip()
    shipFrom = cleanString(shipFrom)
    shipTo = location[1].text
    shipTo = ''.join(c for c in shipTo if c.isalnum())
    shipTo = shipTo.strip()

    # Finding Product Image
    if soup.find('div', {"class": 'product-photos'}):
        image = soup.find('div', {"class": 'product-photos'}).find('img')
        image = image.get('src')
        image = image.split('base64,')[-1]
    else:
        image = "-1"



    # 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 darkbay_listing_parser(soup):

    # Fields to be parsed
    nm = 0  # *Total_Products (Should be Integer)
    mktName = "DarkBay"                     # 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

    cat = soup.find('div', {'class': 'path'}).findAll('a')
    listing = soup.find('div', {"class": 'items'}).findAll('form', {"action": '/cart'})

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

    for a in listing:

        category.append(cat[1].text)

        # Adding the url to the list of urls
        link = a.find('a').get('href')
        link = cleanLink(link)
        href.append(link)

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

        # Finding Product Image
        product_image = a.find('img')
        if product_image is not None:
            product_image = product_image.get('src')
            product_image = product_image.split('base64,')[-1]
            image.append(product_image)
        else:
            image.append('-1')


        # vendor name
        ven = a.find('div', {'class', 'vendor'}).find('a').text
        ven = cleanString(ven)
        vendor.append(ven)

        # find price in usd
        usd = a.find('div', {'class': 'price'}).text
        usd = usd.replace('$','')
        USD.append(usd)

        rating_vendor.append('-1')
        success.append('-1')
        CVE.append('-1')
        MS.append('-1')
        describe.append('-1')
        views.append('-1')
        reviews.append('-1')
        rating_item.append('-1')
        addDate.append('-1')
        BTC.append('-1')
        EURO.append('-1')
        sold.append('-1')
        qLeft.append('-1')
        shipFrom.append('-1')
        shipTo.append('-1')
        image_vendor.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 darkbay_links_parser(soup):
    # Returning all links that should be visited by the Crawler

    href = []
    listing = soup.find('div', {"class": "items"}).findAll('form', {'class':'item'})

    for a in listing:
        bae = a.findAll('a', href=True)

        # Adding the url to the list of urls
        link = bae[0].get('href')
        href.append(link)

    return href