dark_web_forums/MarketPlaces/Utilities/utilities.py

__author__ = 'DarkWeb'

import string
import time
import re
import hashlib
import base64
import io
import configparser
from datetime import datetime, timedelta
from lxml import html as lxml
from selenium.webdriver.common.by import By
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad, unpad
from PIL import Image
from urllib.parse import urlsplit, urljoin


def generate_aes_key():
    config = configparser.ConfigParser()
    config.read('../../setup.ini')

    secret = config.get('Encryption', 'secret')
    secret_bytes = bytes(secret, encoding="utf-8")

    # Derive a key from the seed using PBKDF2
    key = hashlib.pbkdf2_hmac(hash_name='sha256', password=secret_bytes, salt=bytes(), iterations=1)

    # Use the first 16 bytes of the derived key as the AES key
    aes_key = key[:16]

    # print("key: ", aes_key)
    return aes_key


BLOCK_SIZE = 32
aes_key = generate_aes_key()
encryptCipher = AES.new(aes_key, AES.MODE_ECB)
decryptCipher = AES.new(aes_key, AES.MODE_ECB)


def convertDate(sdate, language, crawlerDate):

    if language == "english":

       today = crawlerDate.strftime("%m/%d/%Y")
       yesterday = (crawlerDate - timedelta(1)).strftime("%m/%d/%Y")

       sdate = sdate.replace(u"January","01")
       sdate = sdate.replace(u"February","02")
       sdate = sdate.replace(u"March","03")
       sdate = sdate.replace(u"April","04")
       sdate = sdate.replace(u"May","05")
       sdate = sdate.replace(u"June","06")
       sdate = sdate.replace(u"July","07")
       sdate = sdate.replace(u"August","08")
       sdate = sdate.replace(u"September","09")
       sdate = sdate.replace(u"October","10")
       sdate = sdate.replace(u"November","11")
       sdate = sdate.replace(u"December","12")
       sdate = sdate.replace(u"Jan","01")
       sdate = sdate.replace(u"Feb","02")
       sdate = sdate.replace(u"Mar","03")
       sdate = sdate.replace(u"Apr","04")
       sdate = sdate.replace(u"May","05")
       sdate = sdate.replace(u"Jun","06")
       sdate = sdate.replace(u"Jul","07")
       sdate = sdate.replace(u"Aug","08")
       sdate = sdate.replace(u"Sep","09")
       sdate = sdate.replace(u"Oct","10")
       sdate = sdate.replace(u"Nov","11")
       sdate = sdate.replace(u"Dec","12")
       sdate = sdate.replace(u".","")

       if "Today" in sdate:
          sdate = datetime.strptime(str(today), '%m/%d/%Y').strftime('%m %d %Y')
       elif "Yesterday" in sdate:
          sdate = datetime.strptime(str(yesterday), '%m/%d/%Y').strftime('%m %d %Y')

       sdate = datetime.strptime(str(sdate), '%m %d %Y').strftime('%m/%d/%Y')

    elif language == "british":

       sdate = datetime.strptime(str(sdate), '%d %m %Y').strftime('%m/%d/%Y')

    elif language == "french":

       todaysday = crawlerDate.strftime("%m/%d/%Y")

       sdate = sdate.replace(u"janvier","01")
       sdate = sdate.replace(u"jan","01")
       sdate = sdate.replace(u"février","02")
       sdate = sdate.replace(u"juin","06")
       sdate = sdate.replace(u"juillet","07")
       sdate = sdate.replace(u"juil","07")
       sdate = sdate.replace(u"août","08")
       sdate = sdate.replace(u"septembre","09")
       sdate = sdate.replace(u"sept","09")
       sdate = sdate.replace(u"octobre","10")
       sdate = sdate.replace(u"oct","10")
       sdate = sdate.replace(u"novembre","11")
       sdate = sdate.replace(u"nov","11")
       sdate = sdate.replace(u"décembre","12")
       sdate = sdate.replace(u"déc","12")
       sdate = sdate.replace(u".","")

       if sdate == u"Aujourd'hui" or "Today" in sdate:
          sdate = datetime.strptime(str(todaysday), '%m/%d/%Y').strftime('%d %m %Y')

       if "mar" in sdate:
           print ("Add March to the IBM Black Market")
           raise SystemExit
       elif "avr" in sdate:
           print ("Add April to the IBM Black Market")
           raise SystemExit
       elif "mai" in sdate:
           print ("Add May to the IBM Black Market")
           raise SystemExit

       sdate = datetime.strptime(str(sdate), '%d %m %Y').strftime('%m/%d/%Y')

    elif language == "swedish":

       sdate = sdate.replace(u"jan","01")
       sdate = sdate.replace(u"feb","02")
       sdate = sdate.replace(u"mar","03")
       sdate = sdate.replace(u"apr","04")
       sdate = sdate.replace(u"maj","05")
       sdate = sdate.replace(u"jun","06")
       sdate = sdate.replace(u"jul","07")
       sdate = sdate.replace(u"aug","08")
       sdate = sdate.replace(u"sep","09")
       sdate = sdate.replace(u"okt","10")
       sdate = sdate.replace(u"nov","11")
       sdate = sdate.replace(u"dec","12")
       sdate = sdate.replace(u".","")

       if sdate == u"Ig\xe5r" or sdate == u"Idag" or "minuter sedan" in sdate:
          sdate = crawlerDate
          sdate = datetime.strptime(str(sdate), '%Y-%m-%d').strftime('%d %m %Y')

       sdate = datetime.strptime(str(sdate), '%d %m %Y').strftime('%m/%d/%Y')

    elif language == "russian":

       if sdate == u'\u0412\u0447\u0435\u0440\u0430' or u"Вчера" in sdate:
          sdate = crawlerDate - timedelta(1)
          sdate = datetime.strptime(str(sdate), '%Y-%m-%d').strftime('%d %m %Y')
       elif sdate == u'\u0421\u0435\u0433\u043e\u0434\u043d\u044f':
          sdate = crawlerDate
          sdate = datetime.strptime(str(sdate), '%Y-%m-%d').strftime('%d %m %Y')
       elif u'\xd1\xee\xe7\xe4\xe0\xed\xee' in sdate:
          return ""

       sdate = sdate.replace(u"Январь","01")
       sdate = sdate.replace(u"января","01")
       sdate = sdate.replace(u"янв","01")
       sdate = sdate.replace(u"January","01")
       sdate = sdate.replace(u"Jan","01")
       sdate = sdate.replace(u"фев","02")
       sdate = sdate.replace(u"февраля","02")
       sdate = sdate.replace(u"Февраль", "02")
       sdate = sdate.replace(u"February", "02")
       sdate = sdate.replace(u"Feb", "02")
       sdate = sdate.replace(u"Март","03")
       sdate = sdate.replace(u"марта","03")
       sdate = sdate.replace(u"March","03")
       sdate = sdate.replace(u"Mar","03")
       sdate = sdate.replace(u"Апрель","04")
       sdate = sdate.replace(u"апреля","04")
       sdate = sdate.replace(u"апр","04")
       sdate = sdate.replace(u"April","04")
       sdate = sdate.replace(u"Apr","04")
       sdate = sdate.replace(u"май","05")
       sdate = sdate.replace(u"Май","05")
       sdate = sdate.replace(u"мар","05")
       sdate = sdate.replace(u"май","05")
       sdate = sdate.replace(u"мая","05")
       sdate = sdate.replace(u"May","05")
       sdate = sdate.replace(u"Июнь","06")
       sdate = sdate.replace(u"июня","06")
       sdate = sdate.replace(u"июн","06")
       sdate = sdate.replace(u"June","06")
       sdate = sdate.replace(u"Jun","06")
       sdate = sdate.replace(u"Июль","07")
       sdate = sdate.replace(u"июля","07")
       sdate = sdate.replace(u"июл","07")
       sdate = sdate.replace(u"July","07")
       sdate = sdate.replace(u"Jul","07")
       sdate = sdate.replace(u"августа","08")
       sdate = sdate.replace(u"Август","08")
       sdate = sdate.replace(u"авг","08")
       sdate = sdate.replace(u"August","08")
       sdate = sdate.replace(u"Aug","08")
       sdate = sdate.replace(u"Сентябрь","09")
       sdate = sdate.replace(u"сентября","09")
       sdate = sdate.replace(u"сен","09")
       sdate = sdate.replace(u"September","09")
       sdate = sdate.replace(u"Sep","09")
       sdate = sdate.replace(u"октября","10")
       sdate = sdate.replace(u"Октябрь","10")
       sdate = sdate.replace(u"October","10")
       sdate = sdate.replace(u"Oct","10")
       sdate = sdate.replace(u"окт","10")
       sdate = sdate.replace(u"Ноябрь","11")
       sdate = sdate.replace(u"ноября","11")
       sdate = sdate.replace(u"ноя","11")
       sdate = sdate.replace(u"November","11")
       sdate = sdate.replace(u"Nov","11")
       sdate = sdate.replace(u"Декабрь","12")
       sdate = sdate.replace(u"декабря","12")
       sdate = sdate.replace(u"дек","12")
       sdate = sdate.replace(u"December","12")
       sdate = sdate.replace(u"Dec","12")
       sdate = sdate.replace(u".","")

       sdate = datetime.strptime(str(sdate), '%d %m %Y').strftime('%m/%d/%Y')

    return sdate


def cleanText(originalText):

    safe_chars = string.ascii_letters + string.digits + " " + "_" + "/" + "&" + "$" + "#" "@" + "+" + "-" + "*" + "=" \
                     ":" + ";" + "." "," + "?" + "!" + "{" + "}" + "[" + "]" + "(" + ")" + "%" + "`" + "~" + "^" + "|" + "<" + ">"

    for index, text in enumerate(originalText):

        originalText[index] = ''.join([char if char in safe_chars else '' for char in text])

    return originalText


def cleanLink(originalLink):

    safe_chars = string.ascii_letters + string.digits

    originalLink = ''.join([char if char in safe_chars else '' for char in originalLink])

    return originalLink


def organizeProducts(marketplace, nm, vendor, rating_vendor, success_vendor, nombre, CVE, MS, category, describe,
                     views, reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image, image_vendor):

    rw = []

    current_time = datetime.now()
    day = current_time.strftime("%m/%d/%Y")
    ahora = current_time.strftime("%I:%M:%S")

    for n in range(nm):

        lne = marketplace                                                       # 0
        lne += ","
        lne += "-1" if len(vendor) == 0 else vendor[n]                          # 1
        lne += ","
        lne += "-1" if len(rating_vendor) == 0 else rating_vendor[n]            # 2
        lne += ","
        lne += "-1" if len(success_vendor) == 0 else success_vendor[n]          # 3
        lne += ","
        lne += nombre[n]                                                        # 4
        lne += ','
        lne += "-1" if len(describe) == 0 else describe[n]                      # 5
        lne += ","
        lne += "-1" if len(CVE) == 0 else CVE[n]                                # 6
        lne += ","
        lne += "-1" if len(MS) == 0 else MS[n]                                  # 7
        lne += ","
        lne += "-1" if len(category) == 0 else category[n]                      # 8
        lne += ","
        lne += "-1" if len(views) == 0 else views[n]                            # 9
        lne += ","
        lne += "-1" if len(reviews) == 0 else reviews[n]                        # 10
        lne += ","
        lne += "-1" if len(rating_item) == 0 else rating_item[n]                # 11
        lne += ","
        lne += "-1" if len(addDate) == 0 else addDate[n]                        # 12
        lne += ","
        lne += "-1" if len(BTC) == 0 else BTC[n]                                # 13
        lne += ","
        lne += "-1" if len(USD) == 0 else USD[n]                                # 14
        lne += ","
        lne += "-1" if len(EURO) == 0 else EURO[n]                              # 15
        lne += ","
        lne += "-1" if len(sold) == 0 else sold[n]                              # 16
        lne += ","
        lne += "-1" if len(qLeft) == 0 else qLeft[n]                            # 17
        lne += ","
        lne += "-1" if len(shipFrom) == 0 else shipFrom[n]                      # 18
        lne += ","
        lne += "-1" if len(shipTo) == 0 else shipTo[n]                          # 19
        lne += ","
        lne += "-1" if len(image) == 0 else image[n]                            # 20
        lne += ","
        lne += "-1" if len(image_vendor) == 0 else image_vendor[n]              # 21
        lne += ","
        lne += "-1" if len(href) == 0 else href[n]                              # 22
        lne += ","
        lne += day + " " + ahora                                                # 23

        rw.append(lne)

    return rw


def cleanString(originalString):
    updated_string = originalString.replace(",", "")    #replace all commas
    updated_string = updated_string.replace("\n", "")   #replace all newlines
    updated_string = updated_string.replace("\t", "")   #replace all tabs
    updated_string = updated_string.replace("\r", "")   #replace all carriage returns
    updated_string = updated_string.replace("'", "^")   #replace all semicolons
    updated_string = updated_string.replace(u"»", '')   #replace all arrows
    updated_string = updated_string.replace("!", "")    #replace all exclamation points
    updated_string = updated_string.replace(";", "")    #replace all exclamations

    return updated_string


def checkDateFormat(myString):
    isDate = re.match('[0-1][0-9]\/[0-3][0-9]\/[1-2][0-9]{3}', myString)
    return isDate


def cleanNumbers(inputString):

    reg_ex = re.compile(r'[^\d.]+')
    updated_string = reg_ex.sub('', inputString)

    return updated_string


def aes_encryption(item):

    to_bytes = bytes(item)

    encrypted_bytes = encryptCipher.encrypt(pad(to_bytes, BLOCK_SIZE))

    return encrypted_bytes


def aes_decryption(item):

    to_bytes = bytes(item)

    decrypted_bytes = decryptCipher.decrypt(to_bytes)

    return unpad(decrypted_bytes, BLOCK_SIZE)


def encrypt_encode_image_to_base64(driver, xpath):

    try:

        img_element = driver.find_element(by=By.XPATH, value=xpath)
        image_data = img_element.screenshot_as_png

        encrypted_image = aes_encryption(image_data)
        base64_image = base64.b64encode(encrypted_image)
        string_image = base64_image.decode('utf-8')

        return string_image

    except:
        pass

    return None


def decode_decrypt_image_in_base64(string_image):

    try:

        base64_image = bytes(string_image, encoding='utf-8')
        encrypted_image = base64.b64decode(base64_image)
        decrypted_image = aes_decryption(encrypted_image)

        im = Image.open(io.BytesIO(decrypted_image))
        im.show()

        return decrypted_image

    except Exception as e:
        print(e)
        pass

    return None


def replace_image_sources(driver, html_content):

    tree = lxml.fromstring(html_content)

    for picture_tag in tree.findall('.//picture'):
        for source_tag in picture_tag.findall('.//source'):
            picture_tag.remove(source_tag)

    for img_tag in tree.findall('.//img'):

        img_xpath = tree.getroottree().getpath(img_tag)

        string_image = encrypt_encode_image_to_base64(driver, img_xpath)

        if string_image:
            img_tag.set('src', f'data:image/png;base64,{string_image}')
        else:
            img_tag.getparent().remove(img_tag)

    modified_html = lxml.tostring(tree, encoding='utf-8').decode('utf-8')

    return modified_html


def cleanHTML(driver, html):

    clean_html = replace_image_sources(driver, html)

    formats = [
        "jpg", "jpeg", "jfif", "pjpeg", "pjp",
        "png", "apng", "svg", "bmp", "gif",
        "avif", "webp", "ico", "cur", "tiff"
    ]

    # remove images
    clean_html = re.sub(r"<svg[\s\S]*?svg>", "", clean_html)
    for fmat in formats:
        clean_html = re.sub(r"<object.*" + fmat + "[\s\S]*?object>", "", clean_html)
    clean_html = re.sub(r"<canvas[\s\S]*?canvas>", "", clean_html)

    # remove JavaScript
    clean_html = re.sub(r"<script[\s\S]*?script>", "", clean_html)
    clean_html = re.sub(r"<iframe[\s\S]*?iframe>", "", clean_html)
    clean_html = re.sub(r"<object.*javascript[\s\S]*?object>", "", clean_html)
    clean_html = re.sub(r"<aplet.*mayscript[\s\S]*?aplet>", "", clean_html)
    clean_html = re.sub(r"<embed.*scriptable[\s\S]*?embed>", "", clean_html)

    # image and JavaScript
    clean_html = re.sub(r"<div[^>]*style=\"[^\"]*background-image[\s\S]*?div>", "", clean_html)

    return clean_html


def get_relative_url(target_url):
    # Use a dummy base URL to handle both absolute and relative URLs
    base_url = "http://dummybaseurl.com/"
    absolute_url = urljoin(base_url, target_url)

    # Parse the absolute URL
    parsed_absolute_url = urlsplit(absolute_url)

    # Extract the path and query from the absolute URL as the relative URL
    return parsed_absolute_url.path + '?' + parsed_absolute_url.query \
        if parsed_absolute_url.query else parsed_absolute_url.path