|
|
@ -7,9 +7,11 @@ from MarketPlaces.Utilities.utilities import * |
|
|
from bs4 import BeautifulSoup |
|
|
from bs4 import BeautifulSoup |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# This is the method to parse the Description Pages (one page to each Product in the Listing Pages) |
|
|
|
|
|
|
|
|
# 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 quest_description_parser(soup): |
|
|
def quest_description_parser(soup): |
|
|
|
|
|
|
|
|
# Fields to be parsed |
|
|
# Fields to be parsed |
|
|
|
|
|
|
|
|
vendor = "-1" # 0 *Vendor_Name |
|
|
vendor = "-1" # 0 *Vendor_Name |
|
|
@ -31,111 +33,50 @@ def quest_description_parser(soup): |
|
|
left = "-1" # 16 Product_QuantityLeft |
|
|
left = "-1" # 16 Product_QuantityLeft |
|
|
shipFrom = "-1" # 17 Product_ShippedFrom |
|
|
shipFrom = "-1" # 17 Product_ShippedFrom |
|
|
shipTo = "-1" # 18 Product_ShippedTo |
|
|
shipTo = "-1" # 18 Product_ShippedTo |
|
|
|
|
|
|
|
|
row = soup.find_all('div', {'class': "row"}) |
|
|
|
|
|
|
|
|
image = "-1" # 19 Product_Image |
|
|
|
|
|
vendor_image = "-1" # 20 Vendor_Image |
|
|
|
|
|
|
|
|
# Finding Product Name |
|
|
# Finding Product Name |
|
|
name = row[1].text |
|
|
|
|
|
name = name.replace('\n', ' ') |
|
|
|
|
|
name = name.replace(",", "") |
|
|
|
|
|
name = name.strip() |
|
|
|
|
|
|
|
|
|
|
|
small = row[3].find_all('small') |
|
|
|
|
|
|
|
|
|
|
|
# Finding Vendor |
|
|
|
|
|
vendor = small[0].text |
|
|
|
|
|
vendor = vendor.replace("Vendor:", "") |
|
|
|
|
|
vendor = vendor.replace(",", "") |
|
|
|
|
|
vendor = vendor.strip() |
|
|
|
|
|
|
|
|
|
|
|
# Finding Vendor Rating |
|
|
|
|
|
full_stars = small[2].find_all('i', {'class': "fas fa-star"}) |
|
|
|
|
|
half_star = small[2].find('i', {'class': "fas fa-star-half-alt"}) |
|
|
|
|
|
rating_vendor = len(full_stars) + (0.5 if half_star is not None else 0) |
|
|
|
|
|
|
|
|
|
|
|
# Finding Successful Transactions |
|
|
|
|
|
success = small[4].text |
|
|
|
|
|
success = success.replace("Total Sales:", "") |
|
|
|
|
|
success = success.strip() |
|
|
|
|
|
|
|
|
|
|
|
small = row[2].find('p', {'class': "text-left"}).find_all('small') |
|
|
|
|
|
|
|
|
|
|
|
# Finding Prices |
|
|
|
|
|
USD = small[1].text |
|
|
|
|
|
USD = USD.replace("$", "") |
|
|
|
|
|
USD = USD.strip() |
|
|
|
|
|
|
|
|
|
|
|
shipping_info = row[2].find('p', {'class': "text-left"}).find('span').text.strip() |
|
|
|
|
|
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() |
|
|
|
|
|
|
|
|
|
|
|
textarea = row[2].find_all('textarea') |
|
|
|
|
|
|
|
|
|
|
|
# Finding the Product description |
|
|
|
|
|
describe = textarea[0].text |
|
|
|
|
|
describe = describe.replace("\n", " ") |
|
|
|
|
|
describe = describe.replace("\r", " ") |
|
|
|
|
|
describe = describe.strip() |
|
|
|
|
|
|
|
|
|
|
|
''' |
|
|
|
|
|
# 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 |
|
|
|
|
|
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', '') |
|
|
|
|
|
|
|
|
name = soup.find('div', class_='card-header bg-dark text-white rounded-0 text-center').text.strip() |
|
|
|
|
|
|
|
|
|
|
|
# USD Price |
|
|
|
|
|
USD = soup.find('small', text='Product Price:').find_next('small').text.strip().replace('$', '') |
|
|
|
|
|
|
|
|
|
|
|
# Product Description |
|
|
|
|
|
describe = soup.find('textarea').text.strip() |
|
|
|
|
|
|
|
|
|
|
|
# Finding Product Image |
|
|
|
|
|
image = soup.find('img', {'class': 'img-fluid'}) |
|
|
|
|
|
image = image.get('src').split('base64,')[-1] |
|
|
|
|
|
|
|
|
|
|
|
# Finding Vendor Image |
|
|
|
|
|
vendor_image = soup.select_one('.card-body.bg-mgray.css-selector.shadow img') |
|
|
|
|
|
vendor_image = vendor_image.get('src').split('base64,')[-1] |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Populating the final variable (this should be a list with all fields scraped) |
|
|
# 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, |
|
|
row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, |
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo) |
|
|
|
|
|
|
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image) |
|
|
|
|
|
|
|
|
# Sending the results |
|
|
# Sending the results |
|
|
return row |
|
|
return row |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# This is the method to parse the Listing Pages |
|
|
|
|
|
|
|
|
# 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 quest_listing_parser(soup): |
|
|
def quest_listing_parser(soup): |
|
|
|
|
|
|
|
|
# Fields to be parsed |
|
|
# Fields to be parsed |
|
|
nm = 0 # *Total_Products (Should be Integer) |
|
|
|
|
|
mktName = "Quest" # 0 *Marketplace_Name |
|
|
|
|
|
|
|
|
nm = 0 # *Total_Products (Should be Integer) |
|
|
|
|
|
mktName = "quest" # 0 *Marketplace_Name |
|
|
vendor = [] # 1 *Vendor y |
|
|
vendor = [] # 1 *Vendor y |
|
|
rating_vendor = [] # 2 Vendor_Rating |
|
|
rating_vendor = [] # 2 Vendor_Rating |
|
|
success = [] # 3 Vendor_Successful_Transactions |
|
|
success = [] # 3 Vendor_Successful_Transactions |
|
|
name = [] # 4 *Product_Name y |
|
|
name = [] # 4 *Product_Name y |
|
|
CVE = [] # 5 Product_CVE_Classification (Common Vulnerabilities and Exposures) |
|
|
|
|
|
MS = [] # 6 Product_MS_Classification (Microsoft Security) |
|
|
|
|
|
|
|
|
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 |
|
|
category = [] # 7 Product_Category y |
|
|
describe = [] # 8 Product_Description |
|
|
describe = [] # 8 Product_Description |
|
|
views = [] # 9 Product_Number_Of_Views |
|
|
views = [] # 9 Product_Number_Of_Views |
|
|
@ -146,87 +87,76 @@ def quest_listing_parser(soup): |
|
|
USD = [] # 14 Product_USD_SellingPrice y |
|
|
USD = [] # 14 Product_USD_SellingPrice y |
|
|
EURO = [] # 15 Product_EURO_SellingPrice |
|
|
EURO = [] # 15 Product_EURO_SellingPrice |
|
|
sold = [] # 16 Product_QuantitySold |
|
|
sold = [] # 16 Product_QuantitySold |
|
|
qLeft =[] # 17 Product_QuantityLeft |
|
|
|
|
|
|
|
|
qLeft = [] # 17 Product_QuantityLeft |
|
|
shipFrom = [] # 18 Product_ShippedFrom |
|
|
shipFrom = [] # 18 Product_ShippedFrom |
|
|
shipTo = [] # 19 Product_ShippedTo |
|
|
shipTo = [] # 19 Product_ShippedTo |
|
|
href = [] # 20 Product_Links |
|
|
|
|
|
|
|
|
|
|
|
# Finding category of listing page |
|
|
|
|
|
cat = soup.find('span', {'class': "btn btn-sm btn-outline-mgray active border-info"}).text |
|
|
|
|
|
cat = cat.replace("Digital -", "") |
|
|
|
|
|
cat = cat.strip() |
|
|
|
|
|
|
|
|
|
|
|
listing = soup.find_all('div', {"class": "col-md-2 my-md-0 col-12"}) |
|
|
|
|
|
|
|
|
image = [] # 20 Product_Image |
|
|
|
|
|
image_vendor = [] # 21 Vendor_Image |
|
|
|
|
|
href = [] # 22 Product_Links |
|
|
|
|
|
|
|
|
|
|
|
# Extract all product listings |
|
|
|
|
|
listing = soup.findAll('div', class_='col-md-2 my-md-0 col-12') |
|
|
# Populating the Number of Products |
|
|
# Populating the Number of Products |
|
|
nm = len(listing) |
|
|
nm = len(listing) |
|
|
|
|
|
|
|
|
for a in listing: |
|
|
for a in listing: |
|
|
bae = a.find_all('a', href=True) |
|
|
|
|
|
|
|
|
|
|
|
# Adding the category |
|
|
|
|
|
category.append(cat) |
|
|
|
|
|
|
|
|
|
|
|
# Adding the url to the list of urls |
|
|
|
|
|
link = bae[0].get('href') |
|
|
|
|
|
link = cleanLink(link) |
|
|
|
|
|
href.append(link) |
|
|
|
|
|
|
|
|
|
|
|
# Finding the Vendor |
|
|
|
|
|
vendor_name = bae[2].text |
|
|
|
|
|
vendor_name = vendor_name.replace(",", "") |
|
|
|
|
|
vendor_name = vendor_name.strip() |
|
|
|
|
|
vendor.append(vendor_name) |
|
|
|
|
|
|
|
|
|
|
|
# Finding the Product |
|
|
|
|
|
product = bae[1].find('img').get('alt') |
|
|
|
|
|
product = product.replace('\n', ' ') |
|
|
|
|
|
product = product.replace(",", "") |
|
|
|
|
|
product = product.strip() |
|
|
|
|
|
name.append(product) |
|
|
|
|
|
|
|
|
|
|
|
# Searching for CVE and MS categories |
|
|
|
|
|
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) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Extracting Product URL & Name |
|
|
|
|
|
product_link_tags = a.find_all('a', class_='badge-info') |
|
|
|
|
|
if product_link_tags: |
|
|
|
|
|
# Using the first tag as default |
|
|
|
|
|
product_link_tag = product_link_tags[0] |
|
|
|
|
|
href.append(product_link_tag['href']) |
|
|
|
|
|
name.append(product_link_tag.text.strip()) |
|
|
|
|
|
|
|
|
|
|
|
# Extracting Product Image |
|
|
|
|
|
img_tag = a.find('img') |
|
|
|
|
|
if img_tag: |
|
|
|
|
|
image_data = img_tag['src'].split('base64,')[-1] |
|
|
|
|
|
image.append(image_data) |
|
|
|
|
|
|
|
|
|
|
|
# Extracting Vendor Name |
|
|
|
|
|
vendor_tag = a.find('a', class_='badge-dark') |
|
|
|
|
|
if vendor_tag: |
|
|
|
|
|
vendor.append(vendor_tag.text.replace('👤', '').strip()) |
|
|
|
|
|
|
|
|
|
|
|
# Extracting Product Price in USD |
|
|
|
|
|
price_tag = a.find('a', class_='text') |
|
|
|
|
|
if price_tag: |
|
|
|
|
|
USD.append(price_tag.text.replace("$", "").strip()) |
|
|
|
|
|
|
|
|
|
|
|
category_tag = soup.find('span', class_= 'btn btn-sm btn-outline-mgray active border-info') |
|
|
|
|
|
if category_tag: |
|
|
|
|
|
category.append(category_tag.text.strip()) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Populate the final variable (this should be a list with all fields scraped) |
|
|
# 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, |
|
|
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) |
|
|
|
|
|
|
|
|
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 quest_links_parser(soup): |
|
|
def quest_links_parser(soup): |
|
|
|
|
|
# Returning all product links |
|
|
|
|
|
|
|
|
# Returning all links that should be visited by the Crawler |
|
|
|
|
|
href = [] |
|
|
href = [] |
|
|
|
|
|
|
|
|
listing = soup.findAll('div', {"class": "col-md-2 my-md-0 col-12"}) |
|
|
|
|
|
|
|
|
# Locate all divs with class 'row' |
|
|
|
|
|
row_divs = soup.findAll('div', class_='row') |
|
|
|
|
|
|
|
|
|
|
|
for row_div in row_divs: |
|
|
|
|
|
# Locate all product divs within the current 'row' div |
|
|
|
|
|
product_divs = row_div.findAll('div', class_='col-md-2 my-md-0 col-12') |
|
|
|
|
|
|
|
|
|
|
|
for product_div in product_divs: |
|
|
|
|
|
# Locate the anchor tag containing the product link within each product div |
|
|
|
|
|
product_link_tag = product_div.find('a', class_='badge-info') |
|
|
|
|
|
|
|
|
for div in listing: |
|
|
|
|
|
|
|
|
if product_link_tag and product_link_tag.has_attr('href'): |
|
|
|
|
|
href.append(product_link_tag['href']) |
|
|
|
|
|
|
|
|
link = div.find('a')["href"] |
|
|
|
|
|
href.append(link) |
|
|
|
|
|
|
|
|
print(len(href)) |
|
|
|
|
|
|
|
|
return href |
|
|
return href |
unknown
1 year ago