minor naming fix and used cleanString and cleanNumbers

MarketPlaces/Initialization/prepare_parser.py

@@ -162,7 +162,7 @@ def parse_listing(marketPlace, listingFile, soup, createLog, logFile):
         elif marketPlace == "GoFish":
             rw = gofish_listing_parser(soup)
         elif marketPlace == "ZeroDay":
-            rw = zeroday_listing_parser()
+            rw = zeroday_listing_parser(soup)
         else:
             print("MISSING CALL TO LISTING PARSER IN PREPARE_PARSER.PY!")
             raise Exception

MarketPlaces/ZeroDay/parser.py

@@ -39,19 +39,22 @@ def zeroday_description_parser(soup):
 
     # Finding Vendor
     div_vendor = soup.find('div', {'class': "exploit_view_table_user_content"})
-    vendor = div_vendor.find('a').text.strip()
+    vendor = div_vendor.find('a').text
+    vendor = cleanString(vendor).strip()
 
     # Finding Vendor Rating (bug in their system shows standard rating)
     div_rating = div_vendor.find_next_sibling('div')
     rating_vendor = div_rating.find_all('div', {'class': "td"})[1].text
+    rating_vendor = cleanNumbers(rating_vendor).strip()
 
     # Finding Product Name
     div_name = soup.find('div', {'class': "exploit_title"})
     name = div_name.find('h1', {'class': "YellowText"}).text
-    name = name.strip()
+    name = cleanString(name).strip()
 
     # Finding Product description
     describe = soup.find('meta', attrs={'name': "description"}).get("content")
+    describe = cleanString(describe).strip()
 
     # Searching for CVE and MS categories
     cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
@@ -62,6 +65,7 @@ def zeroday_description_parser(soup):
             CVE += "  "
             CVE = CVE.replace(',', ' ')
             CVE = CVE.replace('\n', '')
+            CVE = CVE.replace('\t', '')
     ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
     if ms:
         MS = " "
@@ -73,7 +77,8 @@ def zeroday_description_parser(soup):
 
     # Finding category
     div_category = soup.find('div', {'class': "td"}, text="Category").find_next_sibling('div', {'class': "td"})
-    category = div_category.text.strip()
+    category = div_category.text
+    category = cleanString(category).strip()
 
     # Finding views
     div_views = soup.find('div', {'class': "td"}, text="Views").find_next_sibling('div', {'class': "td"})
@@ -82,6 +87,7 @@ def zeroday_description_parser(soup):
     # Finding added date
     div_date = soup.find('div', {'class': 'td'}, text='Date add').find_next_sibling('div', {'class': "td"})
     addDate = div_date.text.strip()
+    # addDate = datetime.strptime(addDate, "%d-%m-%Y")
 
     # Finding BTC and USD/GOLD
     div_price = soup.find('div', {'class': "td"}, text="Price")
@@ -111,7 +117,7 @@ def zeroday_description_parser(soup):
 def zeroday_listing_parser(soup):
     # Fields to be parsed
     nm = 0  # *Total_Products (Should be Integer)
-    mktName = "0Days"  # 0 *Marketplace_Name y
+    mktName = "ZeroDay"  # 0 *Marketplace_Name y
     vendor = []  # 1 *Vendor y
     rating_vendor = []  # 2 Vendor_Rating y
     success = []  # 3 Vendor_Successful_Transactions n
@@ -142,16 +148,19 @@ def zeroday_listing_parser(soup):
 
     for listing in listings:
         # Finding the vendor name
-        vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text.strip()
+        vendor_name = listing.find('a', href=lambda href: href and '/author/' in href).text
+        vendor_name = cleanString(vendor_name).strip()
         vendor.append(vendor_name)
 
         # Finding the vendor rating
         vendor_level_div = listing.find('div', {'class': "tips_bl"})
         vendor_level = vendor_level_div.find('div', {'class': "tips_value_big"}).text
+        vendor_level = cleanNumbers(vendor_level)
         rating_vendor.append(vendor_level)
 
         # Finding the product name
-        product_name = listing.find('h3').text.strip()
+        product_name = listing.find('h3').text
+        product_name = cleanString(product_name).strip()
         name.append(product_name)
 
         # Searching for CVE and MS categories
@@ -165,6 +174,7 @@ def zeroday_listing_parser(soup):
                 cee += "  "
                 cee = cee.replace(',', ' ')
                 cee = cee.replace('\n', '')
+                cee = cee.replace('\t', '')
             cveValue = cee
         CVE.append(cveValue)
 
@@ -182,7 +192,8 @@ def zeroday_listing_parser(soup):
         MS.append(MSValue)
 
         # Finding the category
-        category_text = listing.find_all('div', {'class': "td"})[2].text.strip()
+        category_text = listing.find_all('div', {'class': "td"})[2].text
+        category_text = cleanString(category_text).strip()
         category.append(category_text)
 
         # Finding the hrefs
@@ -190,11 +201,12 @@ def zeroday_listing_parser(soup):
         href.append(description_link)
 
         # Finding the views
-        views_text = listing.find_all('div', {'class': "td"})[3].text.strip()
+        views_text = listing.find_all('div', {'class': "td"})[3].text.replace(' ', '').strip()
         views.append(views_text)
 
         # Finding the date added
         date = listing.find('div', {'class': "td"}).find('a').text.strip()
+        # date = datetime.strptime(date, "%d-%m-%Y")
         addDate.append(date)
 
         # Finding the BTC and USD/GOLD