Extract and print technology tags from StackOverflow company page

extract-stackoverflow-tech-tags.py

#!/usr/bin/env python3

"""Extract and print technology tags from StackOverflow company page.

Given the final part of a StackOverflow company URL, extract the contents
from the technology stack links onthe corresponding company page and write
them to stdout, separated by spaces.

e.g. supplying "suse" as an argument will print the technologies listed
at https://stackoverflow.com/jobs/companies/suse .

By Pontus Lurcock, 2019. Released to the public domain.
"""

from bs4 import BeautifulSoup
import argparse
import urllib3


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("company_name")
    args = parser.parse_args()
    pool_manager = urllib3.PoolManager()
    response = pool_manager.request("GET",
        "https://stackoverflow.com/jobs/companies/" + args.company_name)
    content = response.data
    soup = BeautifulSoup(content, "html.parser")
    parent = soup.find("div", class_="mb16")
    elements = parent.find_all("a")
    print(" ".join([e.string for e in elements]))

    
if __name__ == "__main__":
    main()