report_generator.py 文件源码

def scrape_kb_crt(self, url):
        ''' This method is used for parsing www.kb.cert.or'''
        data = self.get_html_data(url)
        lists = data.find(id="list-of-vuls").find_all("li") # Selecting list of valuns from https://www.kb.cert.org/vuls/
        for li in lists:
            temp_data = deepcopy(self.value)                # creating copy of self.value 
            temp_data['val_name'] = li.find("span", class_="vul-title truncate").text # parsing name using class name of span
            date = li.find("span", class_="vul-date").text  # parsing published using class name of span 
            temp_data['date'] = datetime.strptime(date, '%d %b %Y').date()
            page_link = "{}{}".format(url.strip('/vuls/'),li.a['href'])   # Creating link address
            temp_data['link'] = page_link
            new_data = self.get_html_data(page_link).find(id="vulnerability-note-content") # fetching link data and selecting a specific div using id 
            temp_data['description'] = new_data.p.text
            temp_data['solution'] = new_data.find_all("table")[2].find("tr").text # selecting solution part from html page using 'tr' tabs 
            self.data.append(temp_data) # appending temp data info to class variable called self.data
            temp_data['severity'] = "Medium" 
            temp_data['affected'] = "Please find description"