You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
249 lines
9.5 KiB
249 lines
9.5 KiB
__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 wethenorth_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
|
|
|
|
# Finding Product Name
|
|
listDes = soup.find('div', {'class': "listDes"})
|
|
name = listDes.find('h2').text
|
|
name = name.replace('\n', ' ')
|
|
name = name.replace(",", "")
|
|
name = name.strip()
|
|
|
|
# Finding Vendor
|
|
vendor = listDes.find('b').text
|
|
vendor = vendor.replace(",", "")
|
|
vendor = vendor.replace("...", "")
|
|
vendor = vendor.replace("-", "")
|
|
vendor = vendor.strip()
|
|
|
|
# Finding Vendor Rating
|
|
rating = listDes.find('span',{'class':'levelSet'})
|
|
rating = rating.text
|
|
rating = rating.replace('\n', ' ')
|
|
rating = rating.replace(",", "")
|
|
rating = rating.strip()
|
|
|
|
# Finding Successful Transactions
|
|
success = listDes.find_all('p')[1]
|
|
success = success.find('span').text
|
|
success = success.split()
|
|
success = success[0].strip()
|
|
|
|
# Finding Prices - all prices in We The North are in CAD, I left the CAD in the resulting String so that it would show CAD for all prices
|
|
padp = listDes.find('p',{'class':'padp'})
|
|
USD = padp.find('span').text
|
|
USD = USD.strip()
|
|
|
|
# Finding Escrow - no escrow on WTN market
|
|
|
|
shipping_info = listDes.find('tbody')
|
|
if "Digital" not in shipping_info:
|
|
shipping_info = shipping_info.find_all('tr')
|
|
row1 = shipping_info[0].find_all('td')
|
|
|
|
# Finding Shipment Information (Origin)
|
|
shipFrom = row1[-1].text
|
|
shipFrom=shipFrom.strip()
|
|
if shipFrom=="":
|
|
shipFrom="-1"
|
|
|
|
row2 = shipping_info[1].find_all('td')
|
|
|
|
# Finding Shipment Information (Destination)
|
|
shipTo = row2[-1].text
|
|
shipTo= shipTo.strip()
|
|
if shipTo == "":
|
|
shipTo = "-1"
|
|
|
|
# Finding the Product description
|
|
describe = soup.find("div",{'class':'tabcontent'})
|
|
describe = describe.find('p').text
|
|
describe = describe.replace("\n", " ")
|
|
describe = describe.replace("\r", " ")
|
|
describe = describe.strip()
|
|
|
|
# cannot find any tag for these
|
|
'''
|
|
# Finding the Number of Product Reviews
|
|
tag = soup.findAll(text=re.compile('Reviews'))
|
|
for index in tag:
|
|
reviews = index
|
|
par = reviews.find('(')
|
|
if par >=0:
|
|
reviews = reviews.replace("Reviews (","")
|
|
reviews = reviews.replace(")","")
|
|
reviews = reviews.split(",")
|
|
review = str(abs(int(reviews[0])) + abs(int(reviews[1])))
|
|
else :
|
|
review = "-1"
|
|
'''
|
|
|
|
# Searching for CVE and MS categories
|
|
# no CVE or MS for WTN market
|
|
|
|
# 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 wethenorth_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "WeTheNorth" # 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
|
|
|
|
right_content = soup.find('div', {"class": "right-content"})
|
|
listing = right_content.findAll('div', {"class": "col-1search"})
|
|
listing = listing[3:]
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
for a in listing:
|
|
bae = a.findAll('a', href=True)
|
|
|
|
# Adding the url to the list of urls
|
|
link = bae[0].get('href')
|
|
link = cleanLink(link)
|
|
href.append(link)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = a.find('p', {'class': 'padp'})
|
|
vendor_name = vendor_name.find('a').text
|
|
vendor_name = vendor_name.replace(",", "")
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# Finding the Product
|
|
product = bae[0].text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding the Category
|
|
category_name = a.find('p', {'class': 'padp'}).text
|
|
first_dash = category_name.find('-')
|
|
second_dash = category_name[first_dash+1:].find('-')
|
|
category_name = category_name[first_dash+1:second_dash]
|
|
category_name=category_name.strip()
|
|
category.append(category_name)
|
|
|
|
# Finding Views
|
|
view_count = a.text
|
|
view_count = view_count[view_count.find('Views:'): view_count.find('Sales:')]
|
|
view_count = view_count.replace('Views:', ' ')
|
|
view_count = view_count.replace('/', ' ')
|
|
view_count = view_count.strip()
|
|
views.append(view_count)
|
|
|
|
# Finding success sales
|
|
sold_count = a.text
|
|
sold_count = sold_count[sold_count.find('Sales:'): sold_count.find('Short')]
|
|
sold_count = sold_count.replace('Sales:', ' ')
|
|
sold_count = sold_count.replace('/', ' ')
|
|
sold_count = sold_count.strip()
|
|
success.append(sold_count)
|
|
|
|
# Searching for CVE and MS categories
|
|
# no CVE or MS in WTN market
|
|
cve = a.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 = a.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 wethenorth_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
href = []
|
|
right_content = soup.find('div',{"class": "right-content"})
|
|
listing = right_content.findAll('div', {"class": "col-1search"})
|
|
#cut out the irrelevant products that are in blue, the first three products of each page usually unrelated
|
|
listing = listing[3:]
|
|
for a in listing:
|
|
|
|
link = a.find('a')
|
|
link = link['href']
|
|
href.append(link)
|
|
|
|
return href
|