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

# need help to get web data - so import the capability
from urllib.request import urlopen

# IMPORTANT CONSTANTS
# this is our base url for the folder words on our class website
# it has several lists, dictionaries that we can access
CS1112_WORDS_WEB_FOLDER = 'http://www.cs.virginia.edu/~cs1112/datasets/words/'

# this is the file we want to access within our words folder
FILE_NAME = 'word-of-the-day'

# get a link to file of interest
# we can glue the base url and the file_name --> we have a link to a particular file on the web
# 'http://www.cs.virginia.edu/~cs1112/datasets/words/word-of-the-day'
link = CS1112_WORDS_WEB_FOLDER + FILE_NAME

# get a connection to stream the web resource of interest
stream = urlopen( link )   # use this function first! allows us to open the finished link to get the stream

# read stream to gets its encoded contents
page = stream.read()       # read in the stream from the website

# decode page into plain text form
text = page.decode()       # get the decoded version of the page --> give you back a string!

# clean up text to get the word - remove whitespace
word = text.strip()

# print word of the day
print( 'word of the day:', word )

print( 'text =', text )