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.
195 lines
8.1 KiB
195 lines
8.1 KiB
__author__ = 'Helium'
|
|
|
|
# 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 kingdom_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
|
|
|
|
# Finding Product Name
|
|
|
|
tag = soup.find('div', {"class": "col-md-9"})
|
|
|
|
desc = tag.find('div',{"class": "col-md-8"}).find('div', {"class": "box-cont"})
|
|
name = tag.find('div',{"class": "col-md-8"}).find('div', {"class": "box-head"}).text
|
|
name = cleanString(name).strip()
|
|
|
|
# Finding Prices
|
|
# Kingdom prices can be shown in a variety of currencies, not all in USD, so keeping currency
|
|
rows = desc.find_all('div', {"class", "row"}, recursive=False)
|
|
USD = rows[-1].find('div', {"class": "row"}).find('h3').text
|
|
USD = cleanNumbers(USD).strip()
|
|
BTC = rows[-1].find('div', {"class": "row"}).find_next_sibling('div').find('span').text
|
|
BTC = cleanNumbers(BTC).strip()
|
|
|
|
# Finding Vendor
|
|
vendor = rows[0].select_one('a[href^="/user"]').text
|
|
vendor = cleanString(vendor).strip()
|
|
|
|
# Finding Shipment Information (Origem)
|
|
descs = rows[0].find_all('div', {"class": "col-md-3 text-right"})
|
|
shipFrom = descs[2].text
|
|
shipFrom = cleanString(shipFrom).strip()
|
|
|
|
# Finding Shipment Information (Destiny)
|
|
shipTo = rows[-1].find('div', {"class": "col-md-6"}).text
|
|
shipTo = shipTo.replace("Ship to:","")
|
|
shipTo = cleanString(shipTo).strip()
|
|
if shipTo == '':
|
|
shipTo = "-1"
|
|
|
|
# Finding the Product Category
|
|
category = descs[0].text
|
|
category = cleanString(category).strip()
|
|
|
|
# Finding the Product Quantity Available
|
|
left = descs[1].text
|
|
left = cleanString(left).strip()
|
|
|
|
# Finding when the Product was Added
|
|
dt = descs[-1].text.strip()
|
|
addDate = datetime.strptime(dt, '%d.%m.%Y')
|
|
|
|
# Finding the Product description
|
|
describe = cleanString(soup.find('div', {"id": "descriptionContent"}).text).strip()
|
|
|
|
# Finding the Number of Product Reviews
|
|
reviews = str(len(soup.find('div', {"id": "feedbackContent"}).find_all(recursive=False)))
|
|
|
|
# Searching for CVE and MS categories
|
|
# no cve or ms in Kingdom
|
|
|
|
# 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
|
|
|
|
|
|
def kingdom_listing_parser(soup):
|
|
|
|
# Fields to be parsed
|
|
nm = 0 # *Total_Products (Should be Integer)
|
|
mktName = "Kingdom" # 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
|
|
image = [] # 20 Product_Image
|
|
image_vendor = [] # 21 Vendor_Image
|
|
href = [] # 22 Product_Links
|
|
|
|
listing = soup.find('div', {"id": "p0"}).find('div').find_all('div', {"class": "row"}, recursive=False)
|
|
|
|
# Populating the Number of Products
|
|
nm = len(listing)
|
|
|
|
for a in listing:
|
|
|
|
# Finding Prices
|
|
#in array USD, there may be prices not in USD, so includes currency as well
|
|
prices = a.find('div', {"class": "col-md-3"})
|
|
u = prices.find('h3').text
|
|
USD.append(cleanNumbers(u).strip())
|
|
bc = prices.find('div').find('span').text
|
|
BTC.append(cleanNumbers(bc).strip())
|
|
|
|
# Finding the Product
|
|
product = a.find('div', {"class": "col-md-7"}).select_one('a[href^="/offer/view?"]').text
|
|
name.append(cleanString(product).strip())
|
|
|
|
# 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.select_one('a[href^="/user"]').text
|
|
vendor_name = vendor_name.replace('/', '')
|
|
vendor.append(cleanString(vendor_name).strip())
|
|
|
|
# Finding Views
|
|
product_views = a.find('div', {"class": "col-md-7"}).find_all('p')[0].text
|
|
views.append(cleanNumbers(product_views).strip())
|
|
|
|
# Finding Sold
|
|
product_sold = a.find('div', {"class": "base-label label label-rounded label-success"})
|
|
if product_sold is not None:
|
|
sold.append(cleanNumbers(product_sold.text).strip())
|
|
else:
|
|
sold.append("-1")
|
|
|
|
# Adding the url to the list of urls
|
|
link = a.find('div', {"class": "col-md-7"}).select_one('a[href^="/offer/view?"]')['href']
|
|
href.append(link)
|
|
|
|
# Searching for CVE and MS categories
|
|
# cve and ms not in kingdom
|
|
|
|
# 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)
|
|
|
|
|
|
def kingdom_links_parser(soup):
|
|
|
|
# Returning all links that should be visited by the Crawler
|
|
|
|
href = []
|
|
|
|
listing = soup.findAll('div', {"class": "col-md-7"})
|
|
|
|
for a in listing:
|
|
link = a.select_one('a[href^="/offer/view?"]')
|
|
link = link['href']
|
|
href.append(link)
|
|
|
|
return href
|