this is based on calsyslab project
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.
 

328 lines
12 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
#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 torzon_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) dont worry about that much
MS = "-1" # 6 Product_MS_Classification (Microsoft Security) dont worry about that much
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
#vendor name
try:
temp = soup.find('div', {'class': 'box rounded mb-0'}).find('a').text
vendor = (cleanString(temp.strip()))
except:
vendor = "-1"
#successful transaction
try:
temp = soup.findAll('div', {'class','text-center text-truncate column-flex ml-1 mr-1'}) #card sidebar-menu mb-4 card sidebar-menu mb-4
temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
temp = temp2[1].text
success = (temp.strip())
except:
print("success")
#vendor rating 5
try:
temp = soup.findAll('div', {'class', 'text-center text-truncate column-flex ml-1 mr-1'}) # card sidebar-menu mb-4 card sidebar-menu mb-4
temp2 = temp[1].findAll('span', {'class', 'float-right font-weight-bold'})
temp = temp2[5].text
rating_vendor = (cleanString(temp.strip()))
except:
print("product")
# product name
try:
temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').text
name = (cleanString(temp.strip()))
except:
temp = soup.find('h3', {'class', 'h3 rounded card-title'}).find('span').find("div").text
name = (cleanString(temp.strip()))
# product description
describe = soup.find('div', {'class': "box rounded flex-fill"}).find('pre').text
if "\n" in describe:
describe = describe.replace("\n", " ")
describe = describe.replace("\r", " ")
describe = cleanString(describe.strip())
CVE = "-1" # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) dont worry about that much
MS = "-1" # 6 Product_MS_Classification (Microsoft Security) dont worry about that much
# product category
try:
temp = soup.findAll('table', {'class', 'table table-hover'})
temp2 = temp[1].find('tr').findAll('td')
temp = temp2[1].text
category = cleanString(temp.strip())
except:
temp = soup.find('table', {'class', 'table table-hover'})
temp2 = temp.find('tbody').find('tr').findAll('td')
temp = temp2[1].text
category = cleanString(temp.strip())
# product number of view
try:
temp = soup.find('div', {'class', 'box rounded mb-0'})
temp2 = temp.findAll('i')
temp = temp2[2].text
views = cleanString((temp.strip()))
except:
print('Product number of view')
reviews = "-1" # 9 Product_Number_Of_Reviews
rating_item = "-1" # 10 Product_Rating
addDate = "-1" # 11 Product_AddedDate
#BTC selling price box box-rounded mt-2
try:
temp = soup.find('div', {'class', 'box box-rounded mt-2'})
temp2 = temp.findAll('i', {'class', 'float-right color-prices'})
temp = temp2[1].text
BTC = cleanString((temp.strip()))
except:
try:
temp = soup.find('div', {'class', 'box box-rounded'})
temp2 = temp.findAll('span', {'class', 'float-right color-prices'})
temp = temp2[1].text
BTC = cleanString((temp.strip()))
except:
print("BTC")
# USD selling price
try:
temp = soup.find('div', {'class', 'box box-rounded mt-2'})
temp2 = temp.findAll('center')
temp = temp2[1].find('i').text
if "$" in temp:
temp = temp.replace("$", "")
USD = cleanString((temp.strip()))
except:
try:
temp = soup.find('div', {'class', 'box box-rounded'})
temp2 = temp.findAll('center')
temp = temp2[1].find('span').text
if "$" in temp:
temp = temp.replace("$", "")
USD = cleanString((temp.strip()))
except:
print("USD")
EURO = "-1" # 14 Product_EURO_SellingPrice
# product sold
try:
temp = soup.find('div', {'class', 'box rounded mb-0'}) # card sidebar-menu mb-4 card sidebar-menu mb-4
temp2 = temp.find('i')
temp = temp2.text
sold = (cleanString(temp.strip()))
# sold = "-1"
except:
print("product sold")
# product quantatiy left ###ERRROR
try:
temp = soup.findAll('table', {'class', 'table table-hover'})
temp2 = temp[1].findAll('tr')
temp3 = temp2[1].findAll('td')
temp = temp3[1].text
left = cleanString(temp.strip())
except:
temp = soup.find('table', {'class', 'table table-hover'})
temp2 = temp.findAll('tr')
temp3 = temp2[1].findAll('td')
temp = temp3[1].text
left = cleanString(temp.strip())
shipFrom = "-1" # 17 Product_ShippedFrom
shipTo = "-1" # 18 Product_ShippedTo
# 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
#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 torzon_listing_parser(soup):
# Fields to be parsed
nm = 0 # *Total_Products (Should be Integer)
mktName = "Torzon" # 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
href = [] # 20 Product_Links
listing = soup.findAll('div', {"class": "card mt-1"})
# Populating the Number of Products
nm = len(listing)
for a in listing:
# vendor
try:
temp = a.find('div', {'class','col-5 justify-content-between mx-auto'}).find('a').text
vendor.append(cleanString(temp.strip()))
except:
print('vendor')
#vendor rating
#successful transactions CHECK AGAIN HERE
try:
success.append("-1")
except:
print('successful transactions')
# product name
try:
temp = a.find('h5', {'class','card-title rounded text-truncate'}).find('a').text
name.append(cleanString(temp.strip()))
except:
print('product name')
CVE.append('-1')
MS.append('-1')
rating_vendor.append('-1')
# product category
try:
temp = soup.find('div', {'class', 'card-sidebar-menu box mb-2 flex-column'}).find('h3').find('span').text
if "Search Results for: " in temp:
temp = temp.replace("Search Results for: ", "")
category.append(cleanString(temp.strip()))
except:
print("Error in product category")
describe.append('-1')
# product views
try:
temp = a.find('h6',{'class', 'card-subtitle mb-1 text-muted text-truncate'})
temp2 = temp.find('i').text
views.append(cleanString(temp2.strip()))
except:
print("Error in views")
reviews.append('-1') # 10 Product_Number_Of_Reviews
rating_item.append('-1') # 11 Product_Rating
addDate.append('-1') # 12 Product_AddDate
# BTC
try:
temp = a.find('div', {'class', 'col-3 justify-content-between mx-auto'})
temp2 = temp.findAll('p')
temp = temp2[1].text
BTC.append(cleanString(temp.strip()))
except:
print("BTC")
#USD ERROR get rid of $
try:
temp = a.find('div', {'class', 'col-12 justify-content-between mx-auto'}).find('i').text
if '$' in temp:
temp = temp.replace("$", "")
USD.append(cleanString(temp.strip())) # 14 Product_USD_SellingPrice
except:
print("USD")
EURO.append("-1") # 15 Product_EURO_SellingPrice
#product sold
try:
temp = a.find('div', {'class', 'col-12 mx-auto text-truncate text-center flex-fill'}).findAll('p', {'class', 'card-text mb-0'})
temp2 = temp[1].find('i').text
sold.append(cleanString(temp2.strip()))
except:
print("product sold")
qLeft.append('-1') # 17 Product_QuantityLeft
shipFrom.append('-1') # 18 Product_ShippedFrom
shipTo.append('-1') # 19 Product_ShippedTo
#href
try:
temp = a.find('h5', {'class', 'card-title rounded text-truncate'}).find('a').get('href')
href.append(temp) # 20 Product_Links
except:
print("href")
# 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)
#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 torzon_links_parser(soup):
# Returning all links that should be visited by the Crawler
href = []
# listing = soup.findAll('div', {"class": "card mt-1"})
listing = soup.find('td', {"valign": "top"}).find("table", {"border": "0"}).findAll('td', {'width': '50%'})
for a in listing:
bae = a.find('a', href=True)#card-title rounded text-truncate
link = bae['href']
href.append(link)
return href