Finished with description parser for MikesGrandStore

Forums/OnniForums/parser.py

@@ -13,7 +13,7 @@ from bs4 import BeautifulSoup
 
 # This is the method to parse the Description Pages (one page to each topic in the Listing Pages)
 
-def onniForums_description_parser(soup: BeautifulSoup):
+def onniForums_description_parser(soup: BeautifulSoup) -> tuple:
     
     topicName: str = "-1"    # 0 *topic name
     users       : List[str] = []  # 1 *all users of each post

MarketPlaces/MikesGrandStore/crawler_selenium.py

@@ -33,19 +33,19 @@ baseURL = 'http://4yx2akutmkhwfgzlpdxiah7cknurw6vlddlq24fxa3r3ebophwgpvhyd.onion
 # Opens Tor Browser, crawls the website, then parses, then closes tor
 #acts like the main method for the crawler, another function at the end of this code calls this function later
 def startCrawling():
-    opentor()
-    # mktName = getMKTName()
-    driver = getAccess()
-
-    if driver != 'down':
-        try:
-            login(driver)
-            crawlForum(driver)
-        except Exception as e:
-            print(driver.current_url, e)
-        closetor(driver)
-
-    # new_parse(mktName, baseURL, False)
+    # opentor()
+    mktName = getMKTName()
+    # driver = getAccess()
+
+    # if driver != 'down':
+    #     try:
+    #         login(driver)
+    #         crawlForum(driver)
+    #     except Exception as e:
+    #         print(driver.current_url, e)
+    #     closetor(driver)
+
+    new_parse(mktName, baseURL, False)
 
 
 # Opens Tor Browser

MarketPlaces/MikesGrandStore/parser.py

@@ -1,14 +1,88 @@
 __author__ = 'DarkWeb'
 
 # Here, we are importing the auxiliary functions to clean or convert data
+from typing import List, Tuple
 from MarketPlaces.Utilities.utilities import *
 
 # Here, we are importing BeautifulSoup to search through the HTML tree
 from bs4 import BeautifulSoup
 
 
-def mikesGrandStore_description_parser(soup: BeautifulSoup):
-    pass
+def mikesGrandStore_description_parser(soup: BeautifulSoup) -> Tuple:
+    
+    name = "-1"                         # 0 Product_Name
+    describe = "-1"                     # 1 Product_Description
+    lastSeen = "-1"                     # 2 Product_LastViewDate
+    rules = "-1"                        # 3 NOT USED ...
+    CVE = "-1"                          # 4 Product_CVE_Classification (Common Vulnerabilities and Exposures)
+    MS = "-1"                           # 5 Product_MS_Classification (Microsoft Security)
+    review = "-1"                       # 6 Product_Number_Of_Reviews
+    category = "-1"                     # 7 Product_Category
+    shipFrom = "-1"                     # 8 Product_ShippedFrom
+    shipTo = "-1"                       # 9 Product_ShippedTo
+    left = "-1"                         # 10 Product_QuantityLeft
+    escrow = "-1"                       # 11 Vendor_Warranty
+    terms = "-1"                        # 12 Vendor_TermsAndConditions
+    vendor = "-1"                       # 13 Vendor_Name
+    sold = "-1"                         # 14 Product_QuantitySold
+    addDate = "-1"                      # 15 Product_AddedDate
+    available = "-1"                    # 16 NOT USED ...
+    endDate = "-1"                      # 17 NOT USED ...
+    BTC = "-1"                          # 18 Product_BTC_SellingPrice
+    USD = "-1"                          # 19 Product_USD_SellingPrice
+    rating = "-1"                       # 20 Vendor_Rating
+    success = "-1"                      # 21 Vendor_Successful_Transactions
+    EURO = "-1"                         # 22 Product_EURO_SellingPrice
+    
+    
+    name: str = soup.find("h1", {"class": "product-title product_title entry-title"}).text
+    
+    describe = soup.find("div", {"id": "tab-description"}).text
+    
+    commentsList: List[BeautifulSoup] = soup.find("ol", {"class": "commentlist"}).find_all("li")
+    
+    if len(commentsList) > 0:
+        lastReview: BeautifulSoup = commentsList[0]
+        lastSeen = lastReview.find("time").get("datetime").text
+    
+    reviewTab: str = soup.find('a', {'href': '#tab-reivews'}).text
+    review = reviewTab.split('(')[1].split(')')[0]
+    
+    navbarBreadcrumbs: List[BeautifulSoup] = soup.find('nav', {'class': 'woocommerce-breadcrumb breadcrumbs '}).find_all('a')
+    category = navbarBreadcrumbs[1].text
+    
+    USD = soup.find("div", {"class": "price-wrapper"}).text
+    
+    reviewStats: str = soup.find("div", {"class": "star-rating"}).text
+    rating = reviewStats.split(' ')[1]
+    
+    row = (
+        name,
+        describe,
+        lastSeen,
+        rules,
+        CVE,
+        MS,
+        review,
+        category,
+        shipFrom,
+        shipTo,
+        left,
+        escrow,
+        terms,
+        vendor,
+        sold,
+        addDate,
+        available,
+        endDate,
+        BTC,
+        USD,
+        rating,
+        success,
+        EURO
+    )
+    
+    return row
 
 
 def mikesGtrandStore_listing_parser(soup: BeautifulSoup):