''' Purpose: introduce web data acquisition -- print contents of
        word-of-the-day.txt from http://www.cs.virginia.edu/~cs1112/datasets/words/
'''

# need help to get web data - so import the capability
from urllib.request import urlopen
# We import urlopen so that we can use methods from the library
# urlopen to work with getting information from the web!
# When we import urlopen, we can use the functions and constants from
# that library! We can use those functions in our code!

# Today we are learning acquiring information from the web
# and how to work with datasets.

# IMPORTANT CONSTANTS
CS1112_WORDS_WEB_FOLDER = "http://www.cs.virginia.edu/~cs1112/datasets/words/"
# Usually our files for OUR datasets is in our datasets folder on the website^
FILE_NAME = "word-of-the-day" # this is the specific file we wanna
# go to after going into the folder and then going into what SPECIFICALLY
# we want from that folder

# get a link to file of interest
link = CS1112_WORDS_WEB_FOLDER + FILE_NAME
# You have the full link! ... datasets/ dataset-name(file name)
# Think about what urls/links look like in general with "/"s - same logic!
print( "Link=", link)
# get a connection to stream the web resource of interest
stream = urlopen( link ) # Program's connection to the web
print( "Stream= ", stream )
# read stream to gets its encoded contents
encoding = stream.read()
print( "Encoding=", encoding )

# decode contents into plain text form
text = encoding.decode( 'UTF-8' ) # UTF-8 is a particular encoding
# Basically makes your encoding into the traditional numerical/alphabetical
# encoding - translates your encoding into plain characters (numbers/letters)
# So it took your encoding and translated it into English we understand
# clean up text to get the word
word = text.strip() # We want to remove all leading and trailing whitespace

# So what did we do? Read the webpage, transform it so we can
# decode it, translate it into characters using UTF-8, and then print
# out whatever was on that webpage
# (the word ineffable in this case). So we got data from the web! Yay!

# print word of the day
print( word )