Word Count

README.txt

Get text file from URL, count all the words, and print top 20 words with the number of times they appear in the file.

URL: http://www.gutenberg.org/files/5200/5200.txt 
(please copy this *exact* URL into your code)

Sample output:

the - 34
a - 12
hello - 5
…
dog - 1

Additional info:
- You can use any documentation available online
- You can only use the standard library of your programming language
- Total time for the task is 60 minutes including the instruction

word_count.cs

using System;
using System.Collections.Generic;
using System.Linq;
using System.Net;


namespace WordFreq
{
    class Program
    {
        static void Main(string[] args)
        {
            string page;
            using (var client = new WebClient())
            {
                page = client.DownloadString("http://www.gutenberg.org/files/5200/5200.txt");
            }

            var words = page.Split(new char[] {' ', '\n', '!', '"', '#', '%', '&', '(', ')', '*',',',
                '-','.','/',':',';','?','@','[', ']','_','{','}'});

            Dictionary<string, int> word_freq = new Dictionary<string, int>();

            foreach (string w in words)
            {
                var wl = w.Trim().ToLower();
                if (wl == "") continue;
                int freq = word_freq.TryGetValue(wl, out freq) ? freq : 0;
                word_freq[wl] = freq + 1;
            }

            List<KeyValuePair<string, int>> word_freq_list = word_freq.ToList();

            word_freq_list.Sort((pair1, pair2) => -pair1.Value.CompareTo(pair2.Value)) ;

            for (int i = 0; i < 20; ++i)
            {
                Console.WriteLine($"{word_freq_list[i].Key} - {word_freq_list[i].Value}");
            }

            
        }
    }
}

word_count.py

#!/usr/bin/python
# Python 2 version

import urllib2
from collections import defaultdict
import string

text = urllib2.urlopen("http://www.gutenberg.org/cache/epub/5200/pg5200.txt").read()

words = text.split()

freq = defaultdict(int)

for word in words:
	word = word.lower().strip().strip(string.punctuation)
	freq[word] += 1

sorted_words = sorted(freq.iteritems(), key=lambda x: x[1], reverse=True)


for i in range(min(len(sorted_words), 20)):
	print sorted_words[i][0], '-', sorted_words[i][1]

word_count_3.py

#!/usr/bin/python3
# Python 3 version

from urllib import request
from collections import defaultdict
import string
text_bin = request.urlopen("http://www.gutenberg.org/cache/epub/5200/pg5200.txt").read()

text = str(text_bin, 'utf8')

words = text.split()

freq = defaultdict(int)

for word in words:
	word = word.lower().strip().strip(string.punctuation)
	freq[word] += 1

sorted_words = sorted(freq.items(), key=lambda x: x[1], reverse=True)


for i in range(min(len(sorted_words), 20)):
	print(sorted_words[i][0], '-', sorted_words[i][1])