dark_web_forums/MarketPlaces/RobinhoodMarket/parser.py

__author__ = 'chris'

import re
import traceback

# 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

# Import for test run
import glob
import os
import codecs
import shutil

# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
def Robinhood_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('h1').text
    name = name.replace('\n', ' ')
    name = name.replace(",", "")
    name = name.strip()

    # Finding description
    desc = ''
    tab = soup.find('div', {"id": "tab-description"})
    for p in tab.findAll('p'):
        desc += p.text
    if desc == '':
        desc = soup.find('div', {"class": "woocommerce-product-details__short-description"}).text
    describe = cleanString(desc.strip())

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

    # Finding Vendor
    vendor = soup.find('a', {'class': 'wcfm_dashboard_item_title'}).text
    vendor = vendor.replace(",", "")
    vendor = vendor.replace("Sold by:", "")
    vendor = vendor.strip()

    # Finding Vendor Image
    vendor_image = soup.find('div', {'class': 'wcfmmp_sold_by_container_left'}).find('img')
    vendor_image = vendor_image.get('src')
    vendor_image = vendor_image.split('base64,')[-1]

    # Finding Category
    catSpan = soup.find('span', {'class': 'posted_in'})
    category = catSpan.find('a').text

    # Finding USD
    priceText = soup.find('p', {'class': 'price'}).text
    USD = str(priceText).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


# This is the method to parse the Listing Pages
def Robinhood_listing_parser(soup):

    # Fields to be parsed
    nm = 0                                    # *Total_Products (Should be Integer)
    mktName = "Robinhood Market"              # 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.find('ul', {"class": "products columns-4"})
    items = listing.findAll('li')

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

    for card in items:
        # Finding Category
        cat = soup.find("h1").text
        cat = cat.replace('\n', ' ')
        cat = cat.replace(",", "")
        cat = cat.strip()
        category.append(cat)

        bae = card.findAll('a')

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

        # Finding Product Name
        product = card.find("h2").text
        product = product.replace('\n', ' ')
        product = product.replace(",", "")
        product = product.strip()
        name.append(product)

        # Finding Product Image
        product_image = card.find('img', {'class': 'attachment-woocommerce_thumbnail size-woocommerce_thumbnail'})
        product_image = product_image.get('src')
        product_image = product_image.split('base64,')[-1]
        image.append(product_image)

        info = card.find('div', {'class': 'wcfmmp_sold_by_container'})

        # Finding Vendor
        vendor_name = info.find('a', {'class', 'wcfm_dashboard_item_title'}).text
        vendor_name = vendor_name.replace(",", "")
        vendor_name = vendor_name.strip()
        vendor.append(vendor_name)

        # Finding Vendor Image
        vendor_icon = info.find('img', {'class', 'wcfmmp_sold_by_logo'})
        vendor_icon = vendor_icon.get('src')
        vendor_icon = vendor_icon.split('base64,')[-1]
        image_vendor.append(vendor_icon)

        # Finding USD
        span = card.find('span', {'class': 'price'})
        if span is not None:
            bdi = span.find('bdi')
            usdText = bdi.find('span').next_sibling
            usdVal = usdText.text
        else:
            usdVal = "0"
        USD.append(usdVal)

        # 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)

    #print(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views,
    #                        reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href)

    # 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 Robinhood_links_parser(soup):

    # Returning all links that should be visited by the Crawler
    href = []

    #list = soup.findAll('div', {"class": "woocommerce columns-4"})
    listing = soup.find('ul', {"class": "products columns-4"}).findAll('li')

    for item in listing:

        link = item.find('a')['href']
        href.append(link)

    return href


if __name__ == '__main__':
    nError = 0
    marketPlace = 'RobinhoodMarket'

    lines = []  # listing pages
    lns = []  # description pages
    detPage = {}

    '''
    # reading description pages
    count = 0
    for fileDescription in glob.glob(os.path.join("..\\" + marketPlace + "\\HTML_Pages\\08082023\\Description", '*.html')):
        count += 1
        lns.append(fileDescription)
        # if count > 5:
        #     break

    for index, line2 in enumerate(lns):

        print("Reading description folder of '" + marketPlace + "', file '" + os.path.basename(line2) + "', index= " + str(index + 1) + " ... " + str(len(lns)))

        try:
            html = codecs.open(line2.strip('\n'), encoding='utf8')
            soup = BeautifulSoup(html, "html.parser")
            html.close()
        except:

            try:
                html = open(line2.strip('\n'))
                soup = BeautifulSoup(html, "html.parser")
                html.close()
            except:

                nError += 1
                print("There was a problem to read the file " + line2 + " in the Description section!")
                # if createLog:
                #     logFile.write(str(nError) + ". There was a problem to read the file " + line2 + " in the Description section.\n")
                continue

        try:
            print(Robinhood_description_parser(soup))
        except:
            traceback.print_exc()
            print("There was a problem to parse the file " + line2 + " in the Description section!")
    '''
    
    # reading listing pages
    count = 0
    for fileListing in glob.glob(os.path.join("..\\" + marketPlace + "\\HTML_Pages\\08082023\\Listing", '*.html')):
        count += 1
        lines.append(fileListing)
        #if count > 1:
        #    break

    for index, line1 in enumerate(lines):

        print("Reading listing folder of '" + marketPlace + "', file '" + os.path.basename(line1) + "', index= " + str(index + 1) + " ... " + str(len(lines)))

        readError = False
        try:
            html = codecs.open(line1.strip('\n'), encoding='utf8')
            soup = BeautifulSoup(html, "html.parser")
            html.close()
        except:
            try:
                html = open(line1.strip('\n'))
                soup = BeautifulSoup(html, "html.parser")
                html.close()
            except:
                print("There was a problem to read the file " + line1 + " in the Listing section!")
                readError = True

        if not readError:

            parseError = False
            try:
                test = Robinhood_listing_parser(soup)
                print(Robinhood_listing_parser(soup))
            except:
                traceback.print_exc()
                print("There was a problem to parse the file " + line1 + " in the listing section!")
                parseError = True
                

    print("DONE")