RAMESHSELVAM_KIRTHANA_hw5_localscrape.py

from bs4 import BeautifulSoup
import requests
import pandas as pd
import sqlite3
import json
import gmplot
import RAMESHSELVAM_KIRTHANA_hw5_plot
import sys
import operator
#this function will display the top 5 most occuring/detected malware 
def findmaxmaltype():
	conn = sqlite3.connect('projectMal.db')
	query = 'select "Type_of_Malware" from "Malwaredata"'
	df = pd.read_sql(query,conn)
	c = 1
	count = dict()
	for i in df["Type_of_Malware"]:
		if str.isalpha(i[0]):
			if i not in count:
				count[i] = 1
			else:
				count[i] += 1
	
	print("Statistics: \nThe 5 most common types of Malware are:")
	count = sorted(count.items(), key=operator.itemgetter(1), reverse = True)
	df2 = pd.DataFrame(count,columns={'Number of Occurances','Type of Malware'})
	print(df2.head(5))
#this function will display the malware that has been reported with the most number of indicators of compromise	
def findmaxioc():
	conn = sqlite3.connect('projectMal.db')
	query = 'select "ioc" from "Locationdata"'
	df = pd.read_sql(query,conn)
	print("\nMaximum number of indicators of compromise are from :")
	maxi = max(df["ioc"])
	print("IOCs:",maxi)
	query = 'select "ip","country" from "Locationdata" where "ioc"='+str(maxi)
	df2 = pd.read_sql(query,conn)
	print("IP address of malware:",str(df2["ip"]).split()[1])
	que = "select Type_of_Malware from Malwaredata,Locationdata where Malwaredata.IP_Address=Locationdata.ip AND Locationdata.ioc="+"'"+str(maxi)+"'"
	d = pd.read_sql(que,conn)
	print("Type of Malware:",str(d["Type_of_Malware"]).split()[1])
	print("Orginiating country:",str(df2["country"]).split()[1])
	
#this function will compute the top 5 countries that produces the most number of malware

def findmaxcountry():
	conn = sqlite3.connect('projectMal.db')
	query = 'select "country" from "Locationdata"'
	df = pd.read_sql(query,conn)
	count = dict()
	for i in df["country"]:
		if not i:
			continue
		if str.isalpha(i[0]):
			if i not in count:
				count[i] = 1
			else:
				count[i] += 1
		
	
	print("\nThe top 5 threat producing countries are :")
	count = sorted(count.items(), key=operator.itemgetter(1), reverse = True)
	df2 = pd.DataFrame(count,columns={'Number of Malware','Country'})
	print(df2.head(5))