#Demonstrating reading a webpage, and then finding the information we
#are interested in using regular expressions.
#

import urllib.request
from re import findall

#Read the webpage:
response = urllib.request.urlopen("http://weather.yahoo.com/?p=us")
print(response)
html = response.read()
#print(html)
text = str(html)
#print(text)

#Use RegEx to find the data we want.

fDataCrop = findall("<span class=\"f\"><span class=\"num\">[0-9]+</span><span class=\"deg\">&deg;", text)
print("The data cropped out of the webpage is:", fDataCrop)

cDataCrop = findall("<span class=\"c\"><span class=\"num\">[0-9]+</span><span class=\"deg\">&deg;", text)
print("The data cropped out of the webpage is:", cDataCrop)


if len(fDataCrop) != 1:
   print("We have a problem parsing the data! Help!")
else:
   #Get just the digits
   temp = findall("[0-9]+", fDataCrop[0]) 
   fTemp = int(temp[0])
   
   temp = findall("[0-9]+", cDataCrop[0]) 
   cTemp = int(temp[0])

   print("The scraped F temp is:", fTemp)
   print("The scraped C temp is:", cTemp)