dark_web_forums/MarketPlaces/CityMarket/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 city_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

    divmd7 = soup.find('div', {'class': "col-md-7"})

    # Finding Vendor
    vendor = divmd7.find('a').text.strip()

    # Finding Prices
    USD = soup.find('span', {'class': "total"}).text.strip()

    tempBTC = soup.find('div', {'class': "text-center"}).text.strip()
    BTC = tempBTC.replace("BTC", "").strip()

    # Finding Product Image
    image = soup.find('img', {'class': 'img-fluid'})
    image = image.get('src')
    image = image.split('base64,')[-1]

    # Finding the Product description
    describe = soup.find('div', {'class': "text-white"}).text
    describe = cleanString(describe.strip())

    '''# Finding the Number of Product Reviews
    tag = soup.findAll(text=re.compile('Reviews'))
    for index in tag:
        reviews = index
        par = reviews.find('(')
        if par >=0:
            reviews = reviews.replace("Reviews (","")
            reviews = reviews.replace(")","")
            reviews = reviews.split(",")
            review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
        else  :
            review = "-1"'''

    # 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 city_listing_parser(soup):

    # Fields to be parsed
    nm = 0                                    # *Total_Products (Should be Integer)
    mktName = "CityMarket"                     # 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": "p-4"})

    # 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)

        # Category
        tempCategory = soup.find('select', {"name": "category"})
        tempCategory = tempCategory.find('option', selected=True).text.strip()
        category.append(tempCategory)

        # Product Name
        product = a.find('h4', {"class": "text-center"}).text
        product = product.replace('\n', ' ')
        product = product.replace(",", "")
        product = product.replace("...", "")
        product = product.strip()
        name.append(product)

        # USD and BTC Price
        price = a.find('div', {"class": "price"}).text
        tempUSD = price.split("~")[0]
        tempUSD = tempUSD.replace("$", "")
        tempUSD = tempUSD.strip()
        USD.append(tempUSD)

        tempBTC = price.split("~")[1]
        tempBTC = tempBTC.replace("BTC", "")
        tempBTC = tempBTC.strip()
        BTC.append(tempBTC)

        # Img
        product_image = a.find('img')
        product_image = product_image.get('src')
        product_image = product_image.split('base64,')[-1]
        image.append(product_image)

        # 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 city_links_parser(soup):

    # Returning all links that should be visited by the Crawler

    href = []
    listing = soup.findAll('div', {"class": "p-4"})

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

    return href