''' Purpose: practice getting data from a useful dataset
'''

# define the base folder for course csv datasets
CSV_WEB_FOLDER = "http://www.cs.virginia.edu/~cs1112/datasets/csv/"

import url

# get name of the dataset
reply = input( "Enter name of dataset: " )

print()

# clean up the reply to get file name
file_name = reply.strip()

# get url link for dataset
link = CSV_WEB_FOLDER + file_name

# get contents of web resource
text = url.get_contents( link )

# clean-up the text
text = text.strip() #this is the dataset, but we need to split it into lines

#print( 'text =', text )
###############  TURN CONTENTS INTO A LIST OF LINES  ###############

# turn the text into data; i.e., a list of lines
lines = text.split( "\n" )
#we can tell .split() to split on anything we want, in this case we telling it to split on new lines
#print('lines =', lines)
#we're almost ready to work with it
###############  TURN LINES INTO A DATASET -- LIST OF LISTS  ###############

# get csv rows into dataset from
dataset = []
#we will fill it below
for line in lines :
    # clean up the line
    line = line.strip()

    # split the line to cells
    cells = line.split(',')
    #print( 'cells =' , cells )
    #cell is individual number in each line
    #they're separated by commas so that is what we will split on
    row = []
    #we will use this to hold our cleaned up cells
    for cell in cells :
        # clean up the cell
        cell = cell.strip()

        # add the cell to the row
        row.append( cell )

        #now we will add it to row
    # add the row of data to our dataset
    dataset.append( row )
    #print('row =', row)

# decompose dataset into header and data
header = dataset[ 0 ]
data   = dataset[ 1 : ]

# print the header
print( "header:" )
print( header )

print()

# print the dataset data
print( "data:" )

for row in dataset :
    print( row )