Extracts the vendor and product portions from the NVD dataset

extractor.py

import xml.etree.ElementTree as et
from collections import defaultdict
import json

data = []
path = "cpe-dictionary_v2.3.xml"

context = et.iterparse(path, events=("start", "end"))
context = iter(context)

ev, root = next(context)
vendors = defaultdict(set)

for ev, el in context:
    if ev == 'start' and el.tag == '{http://scap.nist.gov/schema/cpe-extension/2.3}cpe23-item':
        parts = el.attrib['name'].split(':')
        vendor = parts[3].replace('\\', '')
        product = parts[4].replace('\\', '')
        vendors[vendor].add(product)
        root.clear()

for k in vendors:
    vendors[k] = list(vendors[k])

with open('extract.json', 'w') as f:
   json.dump(vendors, f)