1#! /bin/python3.10
  2import re
  3import requests
  4import os
  5from os.path import exists
  6from bs4 import BeautifulSoup
  7from colorama import Fore, Style
  8company_list = ['scythe','dragos']
  9company_url = {'scythe':'https://www.scythe.io/about/careers','dragos':'https://jobs.lever.co/dragos'}
 10
 11# Define formatting
 12reset = Style.RESET_ALL
 13green = Fore.GREEN
 14purple = Fore.MAGENTA
 15sep = Fore.BLUE + "---------------------------" + reset
 16
 17def get_format(response,company_name):
 18    '''Return the HTML attribute needed for each site'''
 19    match company_name:
 20       case "scythe":
 21            soup = BeautifulSoup(response.text, 'html.parser').findAll("h3",attrs={"id": "w-node-_6a3848d7-bd9c-4061-be22-05d0c32b7a82-c32b7a81"})
 22            return soup
 23       case "dragos":
 24            soup = BeautifulSoup(response.text, 'html.parser').findAll("h5",attrs={"data-qa": "posting-name"})
 25            return soup
 26
 27def parse(posting_location,company_name):
 28    '''Issue the HTML request for job posting page'''
 29    # Issue request to scyhte careers page 
 30    response = requests.get(posting_location,company_name)
 31
 32    # Get the format of the specific site to parse
 33    parsed_response = get_format(response,company_name)
 34
 35    return parsed_response 
 36
 37def parse_html(html_response):
 38    '''Takes list of HTML strings and parses them to contain just the job posting'''
 39    # for each job posting
 40    postings_list = []
 41    for i in html_response:
 42        # Remove HTML from job posting 
 43        postings_list.append(re.sub('<[^<]+?>', '', str(i)))
 44    return postings_list
 45
 46def get_new(postings_list,old_list,company_name):
 47    '''Get the difference in the new job postings and the old ones'''
 48    new_post = list(set(postings_list) - set(old_list)) + list(set(old_list) - set(postings_list)) 
 49    path = './data/'+company_name 
 50
 51    # Save job posting to file
 52    with open(path, 'w') as f:
 53        for listing in postings_list:
 54            f.write("%s \n" % listing)
 55    if new_post:
 56        return company_name,new_post 
 57
 58def get_old(company_name):
 59    '''Get the previous job postings and add them to a list'''
 60    # If data file does not exist, create it
 61    path = './data/'+company_name
 62    if not exists(path):
 63        open(path, 'a').close()
 64    with open(path) as file:
 65        lines = file.readlines()
 66        old_list = []
 67        for i in lines:
 68            # for each job posting, strip out the characters we don't need 
 69            old_list.append(i.rstrip())
 70    return old_list
 71
 72def print_results(company_name,new_post):
 73    '''print the job postings'''
 74    company_name = str(new_post[0]).upper()
 75    print(f"{green}{company_name} has new job postings!")
 76    print(sep)
 77    new_post = new_post[1:]
 78    job_postings = list(new_post)
 79    for i in job_postings:
 80        print(f"{purple}",*i,sep="\n")
 81    print(sep)
 82    pass
 83
 84def select_company():
 85    '''Select the company passed in list and then call the function required for that specific job'''
 86    # Get the company name from the index number passed in through the function
 87    for company in range(len(company_list)):
 88        company_name = list(company_url.keys())[company]
 89        posting_location = list(company_url.values())[company]
 90        html_response = parse(posting_location,company_name)
 91        old_list = get_old(company_name)
 92        postings_list = parse_html(html_response)
 93        new_post = get_new(postings_list,old_list,company_name)
 94        if new_post:
 95            print_results(company_name,new_post)
 96        else:
 97            print(f"{green}{company_name}{purple} has no new job postings")
 98
 99print(f"{green}Ear2Ground:{purple} A Program to help you keep tabs on the job postings of infosec companies")
100print(sep)
101def main():
102    path = './data/'
103    if not os.path.exists(path):
104        os.makedirs(path)
105    select_company()
106
107if __name__ == "__main__":
108    main()