# import a library for openning URL
import urllib.request
# We'll work with a dataset from the Internet. This dataset contains history temperature
#
# http://www.wunderground.com/history/airport/KCHO/2012/03/17/DailyHistory.html?format=1"
#
# Typically, we'd want to be able to access multiple day-month-year of this history file,
# put day-month-year in variables and form a URL
# Or, sometimes we'd want to let the user specify what date to load data
#
# prepare URL to be opened
year = "2012"
month = "03"
day = "17"
url = "http://www.wunderground.com/history/airport/KCHO/" + year + "/" + month +"/" + day + "/DailyHistory.html?format=1"
# how about yesterday's weather
# open the specified URL to read
# store the response object received from the server in a variable
stream = urllib.request.urlopen(url)
print(stream) # http.client.HTTPResponse object
print("processing data")
is_header = True
# read each line from the response object
for line in stream:
# decode the string using the standard encoding scheme (UTF-8)
# then, strip leading and tailing spaces, and split the string using ","
decoded = line.decode("UTF-8").strip().split(",")
print(decoded) # there is "
" at the end of each line
## what can we do with this dataset?
# Count how many days the weather was clear
# Compute the average temperatureF
# Find patterns and estimate likelihood
print("processing data")
is_header = True
# read each line from the response object
for line in stream:
# decode the string using the standard encoding scheme (UTF-8)
# then, strip leading and tailing spaces, and split the string using ","
decoded = line.decode("UTF-8").strip().split(",")
print(decoded) # there is "
" at the end of each line
## what can we do with this dataset?
# Count how many days the weather was clear
# Compute the average temperatureF
# Find patterns and estimate likelihood