__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 usd_to_brl_r = None #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 nexus_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 the name of the product name_of_product = soup.find("h1", {"class": "product_title entry-title"}).text name = cleanString(name_of_product.strip()) # Finding USD Price real = soup.find('span', {"class": "price"}).find('bdi').text real = real.split(',') whole = cleanNumbers(real[0]).replace('.', '') real = whole + '.' + real[1] usd = float(real) / usd_to_brl_r USD = str(round(usd, 2)) # Find the BTC Price prices = soup.find('p', {"class": "price"}).findAll('span', {"class": "cs"}) if len(prices) > 0: BTC = prices[0].text BTC = cleanNumbers(BTC.strip()) # finding the description of the product description_div = soup.find("div", {"class": "woocommerce-product-details__short-description"}) if description_div is None: describe = "-1" else: describe = cleanString(description_div.text.strip()) # Finding Product Image image = soup.find('div', {'class': 'woocommerce-product-gallery__wrapper'}).find('img') image = image.get('src') image = image.split('base64,')[-1] #find the category of the product name_of_category = soup.find("span", {"class": "posted_in"}).find("a").text category = cleanString(name_of_category.strip()) #finding the name of the vendor name_of_vendor = soup.find("div", {"class": "dokan-vendor-name"}).find("h5").text vendor = cleanString(name_of_vendor) #finding the vendor's rating vendorRating = soup.find("div", {"class": "dokan-vendor-rating"}).find("p").text rating_vendor = cleanString(vendorRating) #everything else gets a -1 because they are not found # 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 nexus_listing_parser(soup): global usd_to_brl_r while usd_to_brl_r is None: try: usd_to_brl_r = float(input("1 US Dollar = (Brazilian Real) ")) except ValueError: pass # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) mktName = "Nexus" # 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 main = soup.find('main', {'id': 'main'}) products_list = main.find('ul', recursive=False).find_all('li', recursive=False) nm = len(products_list) for product in products_list: # Finding the name of the product name_of_product = product.find("h2", {"class": "woocommerce-loop-product__title"}).find("a").text name_of_product_cleaned = cleanString(name_of_product.strip()) # print(name_of_product_cleaned) name.append(name_of_product_cleaned) #finding the URL try: url = product.find("a", class_="woocommerce-loop-product__link").get('href') href.append(url) except AttributeError as e: print("I can't find the link") raise e # Finding Product Image product_image = product.find('a', {'class': 'woocommerce-loop-image-link woocommerce-LoopProduct-link woocommerce-loop-product__link'}).find('img') product_image = product_image.get('src') product_image = product_image.split('base64,')[-1] image.append(product_image) # Finding USD Price real = product.find('span', {"class": "price"}).find('bdi').text real = real.split(',') whole = cleanNumbers(real[0]).replace('.', '') real = whole + '.' + real[1] usd = float(real) / usd_to_brl_r USD.append(str(round(usd, 2))) # Finding BTC Price prices = product.find('span', {"class": "price"}).findAll('span', {"class": "cs"}) if len(prices) > 0: price = prices[0].text BTC.append(cleanNumbers(price.strip())) #everything else appends a -1 rating_vendor.append("-1") vendor.append('-1') success.append("-1") CVE.append("-1") MS.append("-1") category.append("-1") describe.append("-1") views.append("-1") reviews.append("-1") addDate.append("-1") EURO.append("-1") sold.append("-1") qLeft.append("-1") shipFrom.append("-1") shipTo.append("-1") image_vendor.append("-1") # Populate the final variable (this should be a list with all fields scraped) return organizeProducts( marketplace = mktName, nm = nm, vendor = vendor, rating_vendor = rating_vendor, success_vendor = success, nombre = name, CVE = CVE, MS = MS, category = category, describe = describe, views = views, reviews = reviews, rating_item = rating_item, addDate = addDate, BTC = BTC, USD = USD, EURO = EURO, sold = sold, qLeft = qLeft, shipFrom = shipFrom, shipTo = shipTo, href = href, image = image, image_vendor = 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 nexus_links_parser(soup): # Returning all links that should be visited by the Crawler href = [] # Using a shorter, but still unique, class name listing = soup.find_all("a", class_="woocommerce-loop-product__link") for a in listing: link = a.get('href') if link: # Checks if 'href' attribute is not None href.append(link) return href