cvrf_parser.py

import requests
import xml.etree.ElementTree as ET
from bs4 import BeautifulSoup


class CVRFParser:

    def __init__(self, xml_doc: ET.ElementTree):

        self.cvrf_doc = xml_doc.getroot()
        self.product_tree = None
        self.vulnerabilities = []
        for i in self.cvrf_doc : 
            if i.tag.endswith('ProductTree'):
                self.product_tree = i
            if i.tag.endswith('Vulnerability'):
                self.vulnerabilities.append(i)
    
    def get_products(self):
        products  = set()
        for child in  self.product_tree : 
            if child.attrib.get('Name') and child.attrib.get('Type'):
                if child.attrib['Type'] == 'Product Version' :
                    products.add(child.attrib['Name'])
        return products

    def get_vulnerablities(self):
        vulnerabilities = []
        for vulnerability in  self.vulnerabilities: 
            vuln_entry = {
                'cve_id':None,
                'reference_urls': [],
                }
            for details in  vulnerability : 
                if details.tag.endswith('CVE'):
                    vuln_entry['cve_id'] = details.text
                
                if details.tag.endswith('References'):
                    for child in  details.iter() : 
                        if child.tag.endswith('URL'):
                            vuln_entry['reference_urls'].append(child.text)
            vulnerabilities.append(vuln_entry)
        
        return vulnerabilities

    def get_data(self):

        return {"packages":self.get_products(),
        "vulnerabilities":self.get_vulnerablities(),
        }


            
def get_urls_of_xmls_from_page(base_url):
    r = requests.get(base_url)
    soup = BeautifulSoup(r.content, 'lxml')
    for a_tag in soup.find_all('a', href=True):
        if a_tag['href'].endswith('.xml'):
            yield base_url + a_tag['href']

for url in  get_urls_of_xmls_from_page("http://ftp.suse.com/pub/projects/security/cvrf/"):
    resp = requests.get(url).content
    z = ET.ElementTree(ET.fromstring(resp.decode('utf-8')))
    vb = CVRFParser(z)
    print(vb.get_products())