dark_web_forums/MarketPlaces/AnonMarket/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 AnonMarket_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

    name_of_product = soup.find("div", {"class": "heading"}).text
    name = cleanString(name_of_product.strip())

    description_div = soup.find("div", {"class": "tab1"})
    if description_div is None:
        describe = "-1"
    else:
        describe = cleanString(description_div.text.strip())

    info_div = soup.find('div', {'class': 'information'})
    table = info_div.find('table') if info_div else None

    # Find all table rows
    rows = table.find_all('tr')

    # Parse each row to get relevant data
    data = {}
    for row in rows:
        columns = row.find_all('td')
        if len(columns) == 3:
            key = columns[0].text.strip()
            value = columns[2].text.strip()
            data[key] = value

    # Extract specific data from the dictionary and assign them to individual variables
    vendor = data.get('Vendor', '-1')
    shipFrom = data.get('Location', '-1')
    shipTo = data.get('Ships to', '-1')
    category = data.get('Category', '-1')
    USD = data.get('Price', '-1').split()[0]
    left = data.get('Stock', '-1')

    # image
    image = soup.find('img', {"class": "bigthumbnail"})
    image = 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 AnonMarket_listing_parser(soup):

    # Fields to be parsed
    nm = 0  # *Total_Products (Should be Integer)
    mktName = "AnonMarket"                     # 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
    base_url = "http://2r7wa5og3ly4umqhmmqqytae6bufl5ql5kz7sorndpqtrkc2ri7tohad.onion"

    cat = soup.find("div", {'class': 'heading'}).text

    products_list = soup.find_all('div', {'class': 'item'})
    nm = 0
    for product in products_list:
        name_of_product = product.find("div", {"class": "title"}).text.strip()
        name.append(name_of_product)

        name_of_vendor = product.find("a", {'class': 'seller'}).text.strip()
        vendor.append(name_of_vendor)

        category.append(cat)

        tbody = product.find('div', {"class": "info"}).find('tbody')

        # rating_item
        width = tbody.find('div', {"class": "stars2"}).get('style')
        rating_item.append(cleanNumbers(width.strip()))

        tr = tbody.findAll('tr', recursive=False)
        td = tr[2].findAll('td')

        # sold
        sold.append(td[0].text.strip())

        # reviews
        reviews.append(td[1].text.strip())

        product_link_element = product.find("div", {"class": "title"}).find_parent('a')
        link = product_link_element['href']
        full_link = base_url + link
        href.append(full_link)

        # Append '-1' for unavailable data
        rating_vendor.append("-1")
        success.append("-1")
        CVE.append("-1")
        MS.append("-1")
        describe.append("-1")
        views.append("-1")
        addDate.append("-1")
        BTC.append("-1")
        USD.append("-1")
        EURO.append("-1")
        qLeft.append("-1")
        shipFrom.append("-1")
        shipTo.append("-1")

        nm += 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 AnonMarket_links_parser(soup):
    # Base URL to prepend to each product link
    base_url = "http://2r7wa5og3ly4umqhmmqqytae6bufl5ql5kz7sorndpqtrkc2ri7tohad.onion"

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

    # Using a shorter, but still unique, class name
    listing = soup.find('div', {'class': 'items'}).find_all('a', href=True, attrs={'href': lambda x: "/product/" in x})

    for a in listing:
        link = a.get('href')
        if link:  # Checks if 'href' attribute is not None
            # Prepending the base URL to the scraped link
            full_link = base_url + link
            href.append(full_link)

    # Filtering out any links that might not have '/product/' in them
    product_links = [link for link in href if '/product/' in link]

    return product_links