import re
import urllib.request


def name_to_url(name):
    if ',' in name:
        x = name.index(',')
        last = name[0:x]
        first = name[x + 2:]
        full = first + '-' + last
        full = full.lower()
        return full

    if ',' not in name and '-' not in name and ' ' in name:
        full = name.replace(' ', '-')
        full = full.lower()
        return full

    if ',' not in name and ' ' not in name:
        full = name
        full = full.lower()
        return full


def report(name):
    full = name_to_url(name)
    key = 'http://cs1110.cs.virginia.edu/files/uva2016/' + full
    try:
        page = urllib.request.urlopen(key)
    except:
        return None, 0, 0

    jobregex = re.compile('Job title: ([A-Za-z 0-9-&]*)')
    moneyregex = re.compile('gross pay: \$([0-9\,]*)')
    rankregex = re.compile('rank</td><td>([0-9,]+) of [0-9,]*')
    rank = 0

    for line in page:
        text = line.decode('utf-8').strip()
        text = text.replace("&amp;", '&')
        text = text.replace("&lt","<")
        text = text.replace("&gt",">")
        for a in jobregex.finditer(text):
            job = (a.group(1))
        for b in moneyregex.finditer(text):
            money = b.group(1)
            money = money.replace(',', '')
            money = float(money)
        if ' rank' in text:
            for c in rankregex.finditer(text):
                rank = c.group(1)
                rank = rank.replace(',', '')
                rank = int(rank)
    return job, money, rank