dark_web_forums/MarketPlaces/DarkRoad/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
import re


# 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 darkroad_description_parser(soup):
    # Fields to be parsed

    vendor = "-1"  # 0 *Vendor_Name n
    success = "-1"  # 1 Vendor_Successful_Transactions n
    rating_vendor = "-1"  # 2 Vendor_Rating n
    name = "-1"  # 3 *Product_Name y
    describe = "-1"  # 4 Product_Description y
    CVE = "-1"  # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures)
    MS = "-1"  # 6 Product_MS_Classification (Microsoft Security)
    category = "-1"  # 7 Product_Category y
    views = "-1"  # 8 Product_Number_Of_Views n
    reviews = "-1"  # 9 Product_Number_Of_Reviews y
    rating_item = "-1"  # 10 Product_Rating y
    addDate = "-1"  # 11 Product_AddedDate n
    BTC = "-1"  # 12 Product_BTC_SellingPrice n
    USD = "-1"  # 13 Product_USD_SellingPrice y
    EURO = "-1"  # 14 Product_EURO_SellingPrice n
    sold = "-1"  # 15 Product_QuantitySold n
    left = "-1"  # 16 Product_QuantityLeft n
    shipFrom = "-1"  # 17 Product_ShippedFrom n
    shipTo = "-1"  # 18 Product_ShippedTo n
    image = "-1"  # 19 Product_Image y
    vendor_image = "-1"  # 20 Vendor_Image n

    # Finding Product Name
    name = soup.find('h1').text
    name = cleanString(name).strip()

    # Finding Product description
    describe_div = soup.find('div', {'class': "woocommerce-product-details__short-description"})
    describe = describe_div.get_text()
    describe = cleanString(describe).strip()

    # Finding category
    div_category = soup.find('div', {'class': "product_meta"})
    category = div_category.find('span', {"class": 'posted_in'}).get_text()
    category = cleanString(category).strip()

    # Finding Number of Reviews
    div_review_count = soup.find('a', {'class': "woocommerce-review-link"})
    reviews = div_review_count.find('span', {'class': 'count'}).text

    # Finding Review Rating
    div_rating_item = soup.find('div', {'class': "star-rating"})
    rating_item = div_rating_item.find('strong', {'class', "rating"}).text

    # Finding BTC and USD/GOLD
    div_price = soup.find('span', {'class': "woocommerce-Price-amount amount"})
    USD = div_price.text

    div_image = soup.find('div', {'class': "woocommerce-product-gallery woocommerce-product-gallery--with-images woocommerce-product-gallery--columns-4 images"})
    div_image = div_image.find('img')
    image = div_image.get('src').split('base64,')[-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 darkroad_listing_parser(soup):
    # Fields to be parsed
    nm = 0  # *Total_Products (Should be Integer)
    mktName = "DarkRoad"  # 0 *Marketplace_Name y
    vendor = []  # 1 *Vendor n
    rating_vendor = []  # 2 Vendor_Rating n
    success = []  # 3 Vendor_Successful_Transactions n
    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 n
    views = []  # 9 Product_Number_Of_Views n
    reviews = []  # 10 Product_Number_Of_Reviews n
    rating_item = []  # 11 Product_Rating y
    addDate = []  # 12 Product_AddDate n
    BTC = []  # 13 Product_BTC_SellingPrice n
    USD = []  # 14 Product_USD_SellingPrice y
    EURO = []  # 15 Product_EURO_SellingPrice n
    sold = []  # 16 Product_QuantitySold n
    qLeft = []  # 17 Product_QuantityLeft n
    shipFrom = []  # 18 Product_ShippedFrom n
    shipTo = []  # 19 Product_ShippedTo n
    image = []  # 20 Product_Image y
    image_vendor = []  # 21 Vendor_Image n
    href = []  # 22 Product_Links y

    listings = soup.findAll('a', {"class": "woocommerce-LoopProduct-link woocommerce-loop-product__link"})

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

    for listing in listings:
        # Finding the product name
        product_name = listing.find('h2', {"class": "woocommerce-loop-product__title"}).text
        product_name = cleanString(product_name).strip()
        name.append(product_name)

        # Finding the category
        category_name = soup.find('h1', {"class": "page-title"}).get_text()
        category_name = cleanString(category_name).strip()
        category.append(category_name)

        # Finding the BTC and USD/GOLD
        USD_price = listing.find('span', {"class": "woocommerce-Price-amount amount"}).get_text()
        USD_price = cleanString(USD_price).strip()
        USD.append(USD_price)

        # Finding the item rating
        rating_div = listing.find('div', {"class": "star-rating"})
        rating = rating_div.find('strong').text
        rating = cleanString(rating).strip()
        rating_item.append(rating)

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

        # Finding the hrefs
        description_link = listing["href"]
        href.append(description_link)
    # 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 darkroad_links_parser(soup):

    href = []
    listings = soup.findAll('li')

    for listing in listings:
        # Adding the url to the list of urls
        try:
            description_link = listing.find('a', class_="woocommerce-LoopProduct-link woocommerce-loop-product__link")['href']
            href.append(description_link)
        except:
            pass

    return href