edb_advanced_proxy.py

#/usr/bin/python3

import atoma, requests, re, pandas as pd
feed_name = "Exploit-DB.com RSS Feed"
url = "https://www.exploit-db.com/rss.xml"

proxies = {
      "http": "http://proxy.com:8080", # Change this
      "https": "https://proxy.com:8080", # Change this
      }

response = requests.get(url, proxies=proxies)
feed = atoma.parse_rss_bytes(response.content)

date1 = feed.pub_date.strftime('(%Y-%m-%d)')
print ("Feed: " + feed.title)
print ("Description: " + feed.description)
print ("Link: " + feed.link)
print ("Feed Update: " + date1)

new_items = []
bad_chars = [';', ':', '!', "*", "'", "[", "]","(",")","-"]

for exploit in feed.items:
    new_item = {}
    new_item['Published'] = exploit.pub_date.strftime('%Y-%m-%d')
    new_item['Title'] = re.findall(r"(.*)\-",exploit.description)
    new_item['Link'] = exploit.link
    new_item['Attack Vector'] = re.findall(r'\[(.*?)\]',exploit.title)
    new_item['Attack Description'] = re.findall(r'\-(.*?)\(',exploit.description)
    new_item['Attack Type'] = re.findall(r'\((.*?)\)',exploit.description)
    new_items.append(new_item)
    print (new_items)

df = pd.DataFrame(new_items,columns=['Published','Title','Attack Vector','Attack Description','Attack Type','Link'])
#Convert dtype to str
df["Published"]= df["Published"].astype(str)
df["Title"]= df["Title"].astype(str)
df["Attack Vector"]= df["Attack Vector"].astype(str)
df["Attack Description"]= df["Attack Description"].astype(str)
df["Attack Type"]= df["Attack Type"].astype(str)
df["Link"]= df["Link"].astype(str)

#Replace special characters
df1 = pd.DataFrame(columns=['PUBLISHED','TITLE','ATTACK VECTOR','ATTACK DESCRIPTION','ATTACK TYPE','LINK'])
df1['PUBLISHED']  = df['Published']
df1['TITLE']  = df['Title'].str.replace("\[|\]|\'", "")
df1['ATTACK VECTOR']  = df['Attack Vector'].str.replace("\[|\]|\'", "")
df1['ATTACK DESCRIPTION']  = df['Attack Description'].str.replace("\[|\]|\'", "")
df1['ATTACK TYPE']  = df['Attack Type'].str.replace("\[|\]|\'", "")
df1['LINK']  = df['Link']
df1.head()

#Export to CSV file and as HTML page
df1.to_csv('/var/www/exploitdb/EDB.csv',index=False, encoding = 'utf-8')
df1.to_html('/var/www/exploitdb/EDB.html')