khangtran
/
dark_web_forums
0
0
Fork 0
Code Issues 0 Pull Requests 0 Projects 0 Releases 0 Wiki Activity
Browse Source

setup configs for gofish crawling and parsing

main
Joshua 1 year ago
parent
cfcff093e4
commit
1a2d29d94f
2 changed files with 284 additions and 339 deletions
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +38
    -54
      MarketPlaces/GoFish/crawler_selenium.py
  2. +246
    -285
      MarketPlaces/GoFish/parser.py

+ 38
- 54
MarketPlaces/GoFish/crawler_selenium.py View File

@ -1,8 +1,7 @@
__author__ = 'DarkWeb' __author__ = 'DarkWeb'
''' '''
Go Fish market Crawler (Selenium)
- this is a new marketplace and was up for only a few days, crawler has not been finished
GoFish Marketplace Crawler (Selenium)
''' '''
from selenium import webdriver from selenium import webdriver
@ -11,6 +10,7 @@ from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
from selenium.webdriver.firefox.firefox_binary import FirefoxBinary from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
from selenium.webdriver.firefox.service import Service from selenium.webdriver.firefox.service import Service
from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.ui import Select
from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By from selenium.webdriver.common.by import By
@ -28,8 +28,7 @@ from MarketPlaces.Utilities.utilities import cleanHTML
counter = 1 counter = 1
baseURL = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/' baseURL = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/'
# Opens Tor Browser, crawls the website, then parses, then closes tor
#acts like the main method for the crawler, another function at the end of this code calls this function later
def startCrawling(): def startCrawling():
mktName = getMKTName() mktName = getMKTName()
driver = getAccess() driver = getAccess()
@ -46,21 +45,18 @@ def startCrawling():
# Returns the name of the website # Returns the name of the website
#return: name of site in string type
def getMKTName(): def getMKTName():
name = 'GoFish' name = 'GoFish'
return name return name
# Return the base link of the website # Return the base link of the website
#return: url of base site in string type
def getFixedURL(): def getFixedURL():
url = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/' url = 'http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/'
return url return url
# Closes Tor Browser # Closes Tor Browser
#@param: current selenium driver
def closeDriver(driver): def closeDriver(driver):
# global pid # global pid
# os.system("taskkill /pid " + str(pro.pid)) # os.system("taskkill /pid " + str(pro.pid))
@ -110,7 +106,6 @@ def createFFDriver():
#the driver 'gets' the url, attempting to get on the site, if it can't access return 'down' #the driver 'gets' the url, attempting to get on the site, if it can't access return 'down'
#return: return the selenium driver or string 'down'
def getAccess(): def getAccess():
url = getFixedURL() url = getFixedURL()
driver = createFFDriver() driver = createFFDriver()
@ -122,31 +117,27 @@ def getAccess():
return 'down' return 'down'
# Manual captcha solver, waits fora specific element so that the whole page loads, finds the input box, gets screenshot of captcha
# then allows for manual solving of captcha in the terminal
#@param: current selenium web driver
def login(driver): def login(driver):
# wait for page to show up (This Xpath may need to change based on different seed url)
WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, '//*[@id="username"]')))
input("Press ENTER when CAPTCHA is complete and login page has loaded\n")
# entering username and password into input boxes # entering username and password into input boxes
usernameBox = driver.find_element(by=By.XPATH, value='//*[@id="username"]')
usernameBox = driver.find_element(by=By.XPATH, value='//input[@name="username"]')
# Username here # Username here
usernameBox.send_keys('itsmedio')
passwordBox = driver.find_element(by=By.XPATH, value='//*[@id="password"]')
usernameBox.send_keys('aliciamykeys')
passwordBox = driver.find_element(by=By.XPATH, value='//input[@name="password"]')
# Password here # Password here
passwordBox.send_keys('DementedBed123-')
passwordBox.send_keys('aliciawherearemykey$')
# session time
session_select = Select(driver.find_element(by=By.XPATH, value='/html/body/main/div/div/div/div/div/form/div[4]/div/div[2]/select'))
session_select.select_by_visible_text('Session 60min')
input("Press ENTER when CAPTCHA is completed and logged in\n")
input("Press ENTER when CAPTCHA is completed and you exit the newsletter\n")
# wait for listing page show up (This Xpath may need to change based on different seed url) # wait for listing page show up (This Xpath may need to change based on different seed url)
WebDriverWait(driver, 100).until(EC.visibility_of_element_located( WebDriverWait(driver, 100).until(EC.visibility_of_element_located(
(By.XPATH, "/html/body/div[1]/div[3]/div[1]/div[3]/ul/div")))
(By.XPATH, '//*[@id="submit"]')))
# Saves the crawled html page, makes the directory path for html pages if not made
def savePage(driver, page, url): def savePage(driver, page, url):
cleanPage = cleanHTML(driver, page) cleanPage = cleanHTML(driver, page)
filePath = getFullPathName(url) filePath = getFullPathName(url)
@ -155,8 +146,6 @@ def savePage(driver, page, url):
return return
# Gets the full path of the page to be saved along with its appropriate file name
#@param: raw url as crawler crawls through every site
def getFullPathName(url): def getFullPathName(url):
from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE from MarketPlaces.Initialization.markets_mining import config, CURRENT_DATE
@ -169,38 +158,41 @@ def getFullPathName(url):
return fullPath return fullPath
# Creates the file name from passed URL, gives distinct name if can't be made unique after cleaned
#@param: raw url as crawler crawls through every site
def getMKTName() -> str:
name = 'GoFish'
return name
def getNameFromURL(url): def getNameFromURL(url):
global counter global counter
name = ''.join(e for e in url if e.isalnum()) name = ''.join(e for e in url if e.isalnum())
if (name == ''):
if name == '':
name = str(counter) name = str(counter)
counter = counter + 1 counter = counter + 1
return name return name
# returns list of urls, here is where you can list the different urls of interest, the crawler runs through this list
#in this example, there are a couple of categories some threads fall under such as
# Guides and Tutorials, Digital Products, and Software and Malware
#as you can see they are categories of products
def getInterestedLinks(): def getInterestedLinks():
links = [] links = []
# Hacking
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=129')
# Malware
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=97')
# Exploits
# Hosting and Security
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=84')
# Exploits and Kits
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=107') links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=107')
# Botnets and Malware
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=97')
# Other Software
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=108')
# Hacking Guide
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=129')
# Fraud (mostly carding)
links.append('http://gofishbybookb4a2kvviuygmwjqfxx7nqsovweogs2cxvqvexhe7edyd.onion/?c=128')
return links return links
# gets links of interest to crawl through, iterates through list, where each link is clicked and crawled through
#topic and description pages are crawled through here, where both types of pages are saved
#@param: selenium driver
def crawlForum(driver): def crawlForum(driver):
print("Crawling the GoFish market") print("Crawling the GoFish market")
linksToCrawl = getInterestedLinks() linksToCrawl = getInterestedLinks()
@ -222,6 +214,7 @@ def crawlForum(driver):
savePage(driver, html, link) savePage(driver, html, link)
list = productPages(html) list = productPages(html)
for item in list: for item in list:
itemURL = urlparse.urljoin(baseURL, str(item)) itemURL = urlparse.urljoin(baseURL, str(item))
try: try:
@ -229,7 +222,6 @@ def crawlForum(driver):
except: except:
driver.refresh() driver.refresh()
savePage(driver, driver.page_source, item) savePage(driver, driver.page_source, item)
time.sleep(3)
driver.back() driver.back()
# comment out # comment out
@ -240,7 +232,7 @@ def crawlForum(driver):
break break
try: try:
link = driver.find_element(by=By.LINK_TEXT, value='Next ›').get_attribute('href')
link = driver.find_element(by=By.XPATH, value='//a[contains(text(), "Next")]').get_attribute('href')
if link == "": if link == "":
raise NoSuchElementException raise NoSuchElementException
count += 1 count += 1
@ -252,30 +244,23 @@ def crawlForum(driver):
print(link, e) print(link, e)
i += 1 i += 1
print("Crawling the GoFishMarket done.")
print("Crawling the GoFish market done.")
# Returns 'True' if the link is a description link
#@param: url of any url crawled
#return: true if is a description page, false if not
# Returns 'True' if the link is Topic link, may need to change for every website
def isDescriptionLink(url): def isDescriptionLink(url):
if 'c' in url:
if 'item' in url:
return True return True
return False return False
# Returns True if the link is a listingPage link
#@param: url of any url crawled
#return: true if is a Listing page, false if not
# Returns True if the link is a listingPage link, may need to change for every website
def isListingLink(url): def isListingLink(url):
if 'a' in url:
if 'category=' in url:
return True return True
return False return False
# calling the parser to define the links, the html is the url of a link from the list of interested link list
#@param: link from interested link list ie. getInterestingLinks()
#return: list of description links that should be crawled through
def productPages(html): def productPages(html):
soup = BeautifulSoup(html, "html.parser") soup = BeautifulSoup(html, "html.parser")
return gofish_links_parser(soup) return gofish_links_parser(soup)
@ -283,4 +268,3 @@ def productPages(html):
def crawler(): def crawler():
startCrawling() startCrawling()
# print("Crawling and Parsing BestCardingWorld .... DONE!")

+ 246
- 285
MarketPlaces/GoFish/parser.py View File

@ -7,321 +7,282 @@ from MarketPlaces.Utilities.utilities import *
from bs4 import BeautifulSoup 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
# 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): def gofish_description_parser(soup):
# Fields to be parsed # 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
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
divmb = soup.findAll('div', {'class': "mb-1"})
name = divmb[0].text
name = name.replace('\n', ' ')
name = name.replace(",", "")
name = name.strip()
# Finding Vendor
vendor = divmb[1].find('a').text.strip()
# Finding Vendor Rating
temp = soup.find('div', {'class': ""}).text
temp = temp.split('(')
rating = temp[0].replace("Vendor's Review : ", "")
rating = rating.replace("%", "")
rating_vendor = rating.strip()
# Finding the Product Rating and Number of Product Reviews
reviews = temp[2].replace(" review)", "")
reviews = reviews.strip()
temp = temp[1].split(")")
rating = temp[1].replace("Product Review : ", "")
rating = rating.replace("%", "")
rating_item = rating.strip()
# Finding Prices
USD = soup.find('div', {'class': "h3 text-primary"}).text.strip()
# Finding the Product Category
pmb = soup.findAll('p', {'class': "mb-1"})
category = pmb[-1].text
category = category.replace("Category: ", "").strip()
# Finding the Product Quantity Available
left = divmb[-1].text
left = left.split(",", 1)[1]
left = left.replace("in stock", "")
left = left.strip()
# Finding Number Sold
sold = divmb[-1].text
sold = sold.split(",", 1)[0]
sold = sold.replace("sold", "")
sold = sold.strip()
# Finding Shipment Information (Origin)
pmb[0].text
shipFrom = shipFrom.replace("Ships from: ", "").strip()
# Finding Shipment Information (Destination)
pmb[1].text
shipTo = shipTo.replace("Ships to: ", "").strip()
# Finding the Product description
cardbody = soup.findAll('div', {'class': "card-body"})
describe = cardbody[1].text.strip()
# Finding Product Image
image = soup.find('div', {'class': 'product-primary'}).find('img')
image = image.get('src')
image = image.split('base64,')[-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', '')
# 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
#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
# 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): def gofish_listing_parser(soup):
# Fields to be parsed # Fields to be parsed
nm = 0 # *Total_Products (Should be Integer) 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
href = [] # 20 Product_Links
listing = soup.findAll('div', {"class": "card mt-1"})
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
listing = soup.findAll('div', {"id": "itembox"})
# 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.findAll('a', href=True)
lb = a.findAll('div', {"id": "littlebox"})
# 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")
# Adding the url to the list of urls
link = bae[0].get('href')
href.append(link)
# Finding the Product
product = lb[1].find('a').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 Prices
price = lb[-1].find('div', {"class": "mb-1"}).text
price = price.replace("$","")
price = price.strip()
USD.append(price)
# Finding the Vendor
vendor_name = lb[-1].find("a").text
vendor_name = vendor_name.replace(",", "")
vendor_name = vendor_name.strip()
vendor.append(vendor_name)
image_vendor.append("-1")
# Finding the Category
cat = lb[-1].find("span").text
cat = cat.replace("class:", "")
cat = cat.strip()
category.append(cat)
span = lb[0].findAll("span")
# Finding Number of Views
num = span[0].text
num = num.replace("views:", "")
num = num.strip()
sold.append(num)
# Finding Number Sold
num = span[2].text
num = num.replace("Sold:", "")
num = num.strip()
sold.append(num)
# Finding Quantity Left
quant = span[1].text
quant = quant.replace("stock:", "")
quant = quant.strip()
qLeft.append(quant)
# add shipping information
ship = lb[2].findAll('small')[1].findAll('span')[1].text.split("->")
shipFrom.append(ship[0].replace("Ship from ", "").strip())
shipTo.append(ship[1].replace("to ", "").strip())
# 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)
# 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 gofish_links_parser(soup):
# 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 # Returning all links that should be visited by the Crawler
href = [] href = []
listing = soup.findAll('div', {"class": "card mt-1"})
listing = soup.findAll('div', {"id": "itembox"})
# for a in listing:
# bae = a.find('a', {"class": "text-info"}, href=True)
# link = bae['href']
# href.append(link)
for a in listing: for a in listing:
bae = a.find('a', href=True)#card-title rounded text-truncate
link = bae['href']
bae = a.findAll('a', href=True)
# Adding the url to the list of urls
link = bae[0].get('href')
href.append(link) href.append(link)
return href return href

Write Preview
Loading…
Cancel
Save