gistfile1.txt

from bs4 import BeautifulSoup
import requests
import sys
import uuid
import json

data = {
        'url':sys.argv[1],
        'links': [],
        'images': []
       }

req = requests.get(data['url'])
soup = BeautifulSoup(req.content,'html5lib')

for a in soup.find_all('a'):
    if a.attrs.get('href',None):
        data['links'].append(a.get('href'))

for img in soup.find_all('img'):
    if img.attrs.get('src',None):
        data['images'].append(img.get('src'))

json.dump(data,open(uuid.uuid5(uuid.NAMESPACE_URL, data['url']).hex+'.json','w'))