indeed.py

import urllib
import urllib2

from prettytable import PrettyTable
import BeautifulSoup


def format_data(item):
    text = item.text
    price, users = text.split('+')
    price = price.strip('$').replace(',', '')
    users = users.strip('(').strip(')')
    return int(price), int(users)


def generate_stats(url):
    soup = BeautifulSoup.BeautifulSoup(urllib2.urlopen(url))
    response = soup.find(id='SALARY_rbo').findNext()
    data = filter(lambda x: x != '\n', response.contents)
    return map(format_data, data)


def main():
    dev_list = ['Python', 'Java', 'C#', 'C++', 'Ruby', 'PHP', 'HTML5', 'Objective C', 'Android', 'IOS']
    base_url = 'http://www.indeed.com/jobs'
    display_table = PrettyTable(['Title', '#Jobs', 'Avg.Sal'])
    for dev in dev_list:
        query = "{dev}".format(dev=urllib.quote(dev))
        full_url = '{baseurl}?q={query}'.format(baseurl=base_url, query=query.replace(' ', '+'))
        stats = list(generate_stats(full_url))
        
        jobs = [users for price, users in stats]
        total = sum(jobs)
        salaries = [price * users / total for price, users in stats]

        display_table.add_row(["{dev} Developer".format(dev=dev), sum(jobs), sum(salaries)])

    print display_table


if __name__ == '__main__':
    main()

output.txt

+-----------------------+--------+---------+
|         Title         | #Jobs  | Avg.Sal |
+-----------------------+--------+---------+
|    Python Developer   | 95448  |  82562  |
|     Java Developer    | 203378 |  82673  |
|      C# Developer     | 88558  |  80501  |
|     C++ Developer     | 84019  |  82570  |
|     Ruby Developer    | 44259  |  82842  |
|     PHP Developer     | 51878  |  64146  |
|    HTML5 Developer    | 37813  |  81441  |
| Objective C Developer | 47869  |  66358  |
|   Android Developer   | 49783  |  66979  |
|     IOS Developer     | 57419  |  74844  |
+-----------------------+--------+---------+