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.
217 lines
8.8 KiB
217 lines
8.8 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
|
|
|
|
|
|
# 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 gofish_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
|
|
|
|
temp = soup.find('div', {'class': 'col-lg-5'})
|
|
|
|
# find vendor name
|
|
vendor = temp.find('a', {'class': 'text-decoration-none fw-bold'}).text.strip()
|
|
if vendor is None:
|
|
print('vendor')
|
|
|
|
# find product name
|
|
temp2 = soup.find('nav', {'aria-label': 'breadcrumb'}).findAll('li', {'class': 'breadcrumb-item'})
|
|
name = soup.find('li', {'class': 'breadcrumb-item active text-truncate'}).text.strip()
|
|
if name is None:
|
|
print('name')
|
|
|
|
describe = soup.find('div', {'class': 'p-3 mb-3 overflow-auto border border-2 bg-white rounded'}).text
|
|
describe = cleanString(describe)
|
|
if describe is None:
|
|
print('describe')
|
|
|
|
category = temp2[2].text
|
|
if category is None:
|
|
print('category')
|
|
|
|
USD = soup.find('td', {'class': 'text-end text-nowrap'}).text
|
|
if USD is None:
|
|
print('USD')
|
|
|
|
shipFrom = soup.find('span', {'class': 'lh-1 me-2 fs-4'}).text
|
|
print(shipFrom)
|
|
|
|
shipTo = soup.find('span', {'class': 'lh-1 me-2 fs-4'}).text
|
|
if shipTo.isalnum():
|
|
shipTo = shipTo
|
|
else:
|
|
shipTo = 'Worldwide'
|
|
|
|
# Finding Product Image
|
|
image = soup.find('figure', {"class": 'image-feature'}).find('img')
|
|
if image is not None:
|
|
image = image.get('src')
|
|
image = image.split('base64,')[-1]
|
|
else:
|
|
print('img')
|
|
image = "-1"
|
|
|
|
|
|
# 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 gofish_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "GoFish" # 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
|
|
|
|
temp = soup.find('div', {"class": "col-9"})
|
|
cat = temp.find('nav', {'aria-label': 'breadcrumb'}).find('li', {'class': 'breadcrumb-item active'}).text.strip()
|
|
cat = cleanString(cat)
|
|
|
|
listing = temp.find('tbody', {"class": 'border border-2 align-middle'}).findAll('tr')
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
for a in listing:
|
|
|
|
category.append(cat)
|
|
|
|
# Adding the url to the list of urls
|
|
link = a.find('a').get('href')
|
|
link = cleanLink(link)
|
|
href.append(link)
|
|
|
|
# Finding the Product name
|
|
product = a.find('a', {"class": 'text-decoration-none'}).text
|
|
product = product.replace('\n', ' ')
|
|
product = product.replace(",", "")
|
|
product = product.replace("...", "")
|
|
product = product.strip()
|
|
name.append(product)
|
|
|
|
# Finding Product Image
|
|
product_image = a.find('img')
|
|
product_image = product_image.get('src')
|
|
product_image = product_image.split('base64,')[-1]
|
|
image.append(product_image)
|
|
|
|
# Finding the Vendor
|
|
vendor_name = a.find('a', {"class": 'text-decoration-none fw-bold'}).text
|
|
vendor_name = vendor_name.replace(",", "")
|
|
vendor_name = vendor_name.strip()
|
|
vendor.append(vendor_name)
|
|
|
|
# image vendor
|
|
image_vendor.append("-1")
|
|
|
|
# USD
|
|
usd = a.find('div', {'class': 'text-nowrap'}). find('span', {'class': 'fw-bold text-nowrap'}).text.strip()
|
|
USD.append(usd)
|
|
|
|
temp = a.findAll('span', {'class': 'fs-4 lh-1'})
|
|
shipF = temp[0].text
|
|
shipFrom.append(shipF)
|
|
|
|
shipT = temp[1].text
|
|
|
|
if shipT.isalnum():
|
|
shipTo.append(shipT)
|
|
else:
|
|
shipTo.append('Worldwide')
|
|
|
|
|
|
|
|
rating_vendor.append('-1')
|
|
success.append('-1')
|
|
CVE.append('-1')
|
|
MS.append('-1')
|
|
describe.append('-1')
|
|
views.append('-1')
|
|
reviews.append('-1')
|
|
rating_item.append('-1')
|
|
addDate.append('-1')
|
|
BTC.append('-1')
|
|
EURO.append('-1')
|
|
sold.append('-1')
|
|
qLeft.append('-1')
|
|
|
|
# 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 gofish_links_parser(soup):
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
listing = soup.find('div', {"class": "col-9"}).find('tbody', {'class': 'border border-2 align-middle'}).findAll('tr')
|
|
|
|
for a in listing:
|
|
bae = a.findAll('a', href=True)
|
|
|
|
# Adding the url to the list of urls
|
|
link = bae[0].get('href')
|
|
href.append(link)
|
|
|
|
return href
|