updated utilities.py to fix bug with clean_html()

.idea/DW_Pipeline_Test.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="C:\Users\Helium\anaconda3" jdkType="Python SDK" />
+    <orderEntry type="inheritedJdk" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyNamespacePackagesService">

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\Helium\anaconda3" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\John Wick\anaconda3" project-jdk-type="Python SDK" />
 </project>

Forums/Utilities/utilities.py

@@ -292,7 +292,7 @@ def cleanHTML(html):
     clean_html = re.sub(r"<embed.*scriptable?>", "", clean_html)
 
     # image and JavaScript
-    clean_html = re.sub(r"<div.*background-image.*?>", "", clean_html)
+    clean_html = re.sub(r"<div[^>]*style=\"[^\"]*background-image.*?>", "", clean_html)
 
     return clean_html
 

MarketPlaces/Utilities/utilities.py

@@ -315,7 +315,7 @@ def cleanHTML(html):
     clean_html = re.sub(r"<embed.*scriptable?>", "", clean_html)
 
     # image and JavaScript
-    clean_html = re.sub(r"<div.*background-image.*?>", "", clean_html)
+    clean_html = re.sub(r"<div[^>]*style=\"[^\"]*background-image.*?>", "", clean_html)
 
     return clean_html
 

MarketPlaces/ViceCity/parser.py

@@ -0,0 +1,232 @@
+__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
+
+
+# This is the method to parse the Description Pages (one page to each Product in the Listing Pages)
+def tor2door_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
+
+    bae = soup.find('div', {'class': "col-9"})
+
+    # Finding Product Name
+    name = bae.find('h2').text
+    name = name.replace('\n', ' ')
+    name = name.replace(",", "")
+    name = name.strip()
+
+    mb = bae.findAll('div', {"class": "mb-1"})
+
+    # Finding Vendor
+    vendor = mb[0].text
+    vendor = vendor.replace(",", "")
+    vendor = vendor.replace("Sold by:", "")
+    vendor = vendor.strip()
+
+    # # Finding Vendor Rating
+    # full_stars = bae[2].find_all('i', {'class': "fas fa-star"})
+    # half_star = bae[2].find('i', {'class': "fas fa-star-half-alt"})
+    # rating = len(full_stars) + (0.5 if half_star is not None else 0)
+
+    # Finding Quantity Sold and Left
+    temp = mb[4].text.split(',')
+
+    sold = temp[0].replace("sold", "")
+    sold = sold.strip()
+
+    left = temp[1].replace("in stock", "")
+    left = left.strip()
+
+    # Finding USD
+    USD = bae.find('div', {"class": "h3 text-secondary"}).text
+    USD = USD.replace("$", "")
+    USD = USD.strip()
+
+    # Finding BTC
+    temp = bae.find('div', {"class": "small"}).text.split("BTC")
+
+    BTC = temp[0].strip()
+
+    # shipping_info = bae[4].text
+    # if "Digital" not in shipping_info:
+    #     shipping_info = shipping_info.split("  ")
+    #
+    #     # Finding Shipment Information (Origin)
+    #     shipFrom = shipping_info[0].strip()
+    #
+    #     # Finding Shipment Information (Destination)
+    #     shipTo = shipping_info[1].strip()
+
+    # Finding the Product description
+    describe = bae.find('div', {"class": "card border-top-0"}).text
+    describe = describe.replace("\n", " ")
+    describe = describe.replace("\r", " ")
+    describe = describe.strip()
+
+    # Searching for CVE and MS categories
+    cve = soup.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+    if cve:
+        CVE = " "
+        for idx in cve:
+            CVE += (idx)
+            CVE += "  "
+            CVE = CVE.replace(',', ' ')
+            CVE = CVE.replace('\n', '')
+    ms = soup.findAll(text=re.compile('MS\d{2}-\d{3}'))
+    if ms:
+        MS = " "
+        for im in ms:
+            MS += (im)
+            MS += " "
+            MS = MS.replace(',', ' ')
+            MS = MS.replace('\n', '')
+
+    # 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)
+
+    # Sending the results
+    return row
+
+
+# This is the method to parse the Listing Pages
+def tor2door_listing_parser(soup):
+    # Fields to be parsed
+    nm = 0  # *Total_Products (Should be Integer)
+    mktName = "Tor2door"  # 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
+    href = []  # 20 Product_Links
+
+    listing = soup.findAll('div', {"class": "card product-card mb-3"})
+
+    # Populating the Number of Products
+    nm = len(listing)
+
+    # Finding Category
+    cat = soup.find("div", {"class": "col-9"})
+    cat = cat.find("h2").text
+    cat = cat.replace("Category: ", "")
+    cat = cat.replace(",", "")
+    cat = cat.strip()
+
+    for card in listing:
+        category.append(cat)
+
+        bae = card.findAll('a')
+
+        # Adding the url to the list of urls
+        link = bae[0].get('href')
+        href.append(link)
+
+        # Finding Product Name
+        product = bae[1].text
+        product = product.replace('\n', ' ')
+        product = product.replace(",", "")
+        product = product.strip()
+        name.append(product)
+
+        # Finding Vendor
+        vendor_name = bae[2].text
+        vendor_name = vendor_name.replace(",", "")
+        vendor_name = vendor_name.strip()
+        vendor.append(vendor_name)
+
+        # Finding USD
+        usd = card.find('div', {"class": "mb-1"}).text
+        usd = usd.replace("$", "")
+        usd = usd.strip()
+        USD.append(usd)
+
+        # Finding Reviews
+        num = card.find("span", {"class": "rate-count"}).text
+        num = num.replace("(", "")
+        num = num.replace("review)", "")
+        num = num.replace("reviews)", "")
+        num = num.strip()
+        reviews.append(num)
+
+        # Searching for CVE and MS categories
+        cve = card.findAll(text=re.compile('CVE-\d{4}-\d{4}'))
+        if not cve:
+            cveValue = "-1"
+        else:
+            cee = " "
+            for idx in cve:
+                cee += (idx)
+                cee += "  "
+                cee = cee.replace(',', ' ')
+                cee = cee.replace('\n', '')
+            cveValue = cee
+        CVE.append(cveValue)
+
+        ms = card.findAll(text=re.compile('MS\d{2}-\d{3}'))
+        if not ms:
+            MSValue = "-1"
+        else:
+            me = " "
+            for im in ms:
+                me += (im)
+                me += " "
+                me = me.replace(',', ' ')
+                me = me.replace('\n', '')
+            MSValue = me
+        MS.append(MSValue)
+
+    # 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)
+
+
+def tor2door_links_parser(soup):
+    # Returning all links that should be visited by the Crawler
+    href = []
+
+    listing = soup.findAll('div', {"class": "card product-card mb-3"})
+
+    for div in listing:
+        link = div.find('a')['href']
+        href.append(link)
+
+    return href