azjobsearch.py

from bs4 import BeautifulSoup
import requests


url = "https://www.azjobconnection.gov/ada/r/search/jobs?utf8=%E2%9C%93&per_page=50&keywords=Python&refiners=%7B%7D&is_subsequent_search=false&status=Active"


r = requests.get(url)
soup = BeautifulSoup(r.content, features="html.parser")
jobs_to_look_at = []
for link in soup.findAll('a'):
    if "/jobs/" in str(link):
        jobs_to_look_at.append("https://www.azjobconnection.gov" + link.get('href'))


good_kw = [' python ', ' sql ', ' qa ', ' quality assurance ']

bad_kw = [' nurse ', ' military ', ' loud ', 'data scientist']


keepers = []
for job in jobs_to_look_at:
    r = str(requests.get(url).content).lower()
    if any([kw in r for kw in bad_kw]):
        print('bad')
        continue

    results = [kw in r for kw in good_kw]
    if any(results):
        print('good', job, len([x for x in results if x]))



from pprint import pprint
pprint(keepers)