import urllib.request, urllib.parse
from bs4 import BeautifulSoup
import re, getopt, sys
import numpy as np


def avgsalary(query, location):
    query = urllib.parse.quote_plus(query)
    location = urllib.parse.quote_plus(location)
    url = "https://jp.indeed.com/%E6%B1%82%E4%BA%BA?q={}&l={}&radius=0".format(query, location)
            
    request = urllib.request.urlopen(url);
    soup = BeautifulSoup(request.read(), 'html.parser')
    result = soup.find(id="SALARY_rbo")
    results = result.find_all("li")
    salaries = []
    num_salaries = []
    for result in results:
        tmp  = result.a["title"]
        tmp = re.sub(',','', tmp)
        tmp = re.sub(r'([0-9]+)[^\d]+([0-9]+).*$', r'\1,\2', tmp);
        tmp = tmp.split(",")
        salaries.append(tmp[0])
        num_salaries.append(tmp[1])
    salaries = np.array(salaries).astype(np.float)
    salaries *= 10000
    num_salaries = np.array(num_salaries).astype(np.float)
    return(np.sum(salaries * num_salaries)/np.sum(num_salaries))

def main():

    try:  
        opts, args = getopt.getopt(sys.argv[1:],"q:l:", ["query", "location"]);
    except getout.GetoptError as err:
        #usage()
        sys.exit(2)

    query = ""
    location = ""
    for o, a in opts:
        if o == "-q":
            query = a
        elif o == "-l":
            location = a

    print(avgsalary(query, location))

if __name__ == "__main__":
    main()

$ python avgsalary.py -l Gotemba
2312722.94887

$ python avgsalary.py -q programmer
4469298.24561
$ python avgsalary.py -q programmer
3116876.47306

Recommended Posts