__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 # 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 quest_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('div', class_='card-header bg-dark text-white rounded-0 text-center').text name = cleanString(name).strip() # USD Price USD = soup.find('small', text='Product Price:').find_next('small').text.replace('$', '').strip() # Product Description describe = soup.find('textarea').text describe = cleanString(describe).strip() # Finding Product Image image = soup.find('img', {'class': 'img-fluid'}) image = image.get('src').split('base64,')[-1] # Finding Vendor Image vendor_image = soup.select_one('.card-body.bg-mgray.css-selector.shadow img') vendor_image = vendor_image.get('src').split('base64,')[-1] # Finding Successful Transactions success = soup.find('strong', text='Total Sales:').parent.text success = cleanNumbers(success).strip() # Finding Vendor Rating temp = soup.find('strong', text='Rating:').parent rating_vendor = len(temp.findAll('i', {"class": "fas fa-star"})) half_stars = len(temp.findAll('i', {'class': "fas fa-star-half-alt"})) if half_stars > 0: rating_vendor += 0.5 # Finding Item Rating temp = soup.find('small', text='Average Product Score:').find_next('small') rating_item = len(temp.findAll('i', {"class": "fas fa-star"})) half_stars = len(temp.findAll('i', {'class': "fas fa-star-half-alt"})) if half_stars > 0: rating_item += 0.5 # 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 quest_listing_parser(soup): # Fields to be parsed nm = 0 # *Total_Products (Should be Integer) mktName = "quest" # 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 # Extract all product listings listing = soup.findAll('div', class_='col-md-2 my-md-0 col-12') # Populating the Number of Products nm = len(listing) for a in listing: # Extracting Product URL & Name product_link_tags = a.find_all('a', class_='badge-info') if product_link_tags: # Using the first tag as default product_link_tag = product_link_tags[0] href.append(product_link_tag['href']) name.append(cleanString(product_link_tag.text).strip()) # Extracting Product Image img_tag = a.find('img') if img_tag: image_data = img_tag['src'].split('base64,')[-1] image.append(image_data) # Extracting Vendor Name vendor_tag = a.find('a', class_='badge-dark') if vendor_tag: vendor.append(cleanString(vendor_tag.text.replace('👤', '')).strip()) # Extracting Product Price in USD price_tag = a.find('a', class_='text') if price_tag: USD.append(price_tag.text.replace("$", "").strip()) category_tag = soup.find('span', class_= 'btn btn-sm btn-outline-mgray active border-info') if category_tag: category.append(cleanString(category_tag.text).strip()) # 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 quest_links_parser(soup): # Returning all product links href = [] # Locate all divs with class 'row' row_divs = soup.findAll('div', class_='row') for row_div in row_divs: # Locate all product divs within the current 'row' div product_divs = row_div.findAll('div', class_='col-md-2 my-md-0 col-12') for product_div in product_divs: # Locate the anchor tag containing the product link within each product div product_link_tag = product_div.find('a', class_='badge-info') if product_link_tag and product_link_tag.has_attr('href'): href.append(product_link_tag['href']) return href