# accuweather2sms.py

# -*- coding: utf-8 -*-
# accuweather2sms.py  !!!

url = 'https://www.accuweather.com/en/ca/toronto/m5j/hourly-weather-forecast'

try: import messaging, appuifw
except: pass
# help(messaging)

print 'AccuWeather SMS'

import urllib2 # note: most recommended above urllib
import HTMLParser
hpx = HTMLParser.HTMLParser()
import re

user_agent = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.6) Gecko/20040113 Firefox/2.0.0.11 Opera/9.25 Ubuntu/dapper-security'}

allow='''0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~''' #string.printable

def cleanup(s):
    sss=''
    for z in s:
        if z in allow:
            sss+=z
        sss.replace('&#176;','')
    return sss
def html2text(h):
    h = cleanup(h)
    str1 = hpx.unescape(h)
    int2 = str1.lower().find("<body")
    if int2>0:
       str1 = str1[int2:]
    int2 = str1.lower().find("</body>")
    if int2>0:
       str1 = str1[:int2]
    list1 = ['<br>',  '<tr',  '<td', '</p>', 'span>', 'li>', '</h', 'div>' ]
    list2 = [chr(13), chr(13), chr(9), chr(13), chr(13),  chr(13), chr(13), chr(13)]
    bolFlag1 = True
    bolFlag2 = True
    strReturn = ""
    for int1 in range(len(str1)):
      str2 = str1[int1]
      for int2 in range(len(list1)):
        if str1[int1:int1+len(list1[int2])].lower() == list1[int2]:
           strReturn = strReturn + list2[int2]
      if str1[int1:int1+7].lower() == '<script' or str1[int1:int1+9].lower() == '<noscript':
         bolFlag1 = False
      if str1[int1:int1+6].lower() == '<style':
         bolFlag1 = False
      if str1[int1:int1+7].lower() == '</style':
         bolFlag1 = True
      if str1[int1:int1+9].lower() == '</script>' or str1[int1:int1+11].lower() == '</noscript>':
         bolFlag1 = True
      if str2 == '<':
         bolFlag2 = False
      if bolFlag1 and bolFlag2 and (ord(str2) != 10) :
        strReturn = strReturn + str2
      if str2 == '>':
         bolFlag2 = True
      if bolFlag1 and bolFlag2:
        strReturn = strReturn.replace(chr(32)+chr(13), chr(13))
        strReturn = strReturn.replace(chr(9)+chr(13), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(32), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(9), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(13), chr(13))
    strReturn = strReturn.replace(chr(13), '\n')
    return strReturn

zzz='''
Temp (
Wind (
Forecast
Rain
Snow
Ice
Cloud
Humidity
Dew
Visibility
UV Index
'''.strip().splitlines()

day='''
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
'''.strip().splitlines()

allow='''0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~''' #string.printable

def next8page(h):
    return max(re.findall(r'''(?<=href=['"])%s\?.*?(?=['"])''' % (site),h))

def sort_data(h):
    h=h.replace('\t','  ')
    while '\n\n' in h:
        h=h.replace('\n\n','\n')
    h=h.replace('\n',' \n')
    for z in day:
        h=h.replace(z,'$$$'+z)
    h=h.split('$$$')

    rrr=[]
    for s in h:
        row=[]
        s=s.splitlines()
        while s:
            t=s.pop(0).strip()
            if t in day:
                d=dd=t
                t='\n.\n'+t
                for _ in 'z'*8:
                    m = s.pop(0)
                    if ('12am' in m):
                        d = day[day.index(dd)+1]
                        t = t.replace(dd,d)
                    row.append(t+': '+m)
            else:
                p=''
                if t in zzz:
                    if 'Temp (' in t:
                        t='Temp (Celsius)'
                        p='c'
                    elif 'Dew ' in t:
                        t='Dew Point'
                        p='c'
                    for z in range(8):
                        m = s.pop(0).strip()
                        if p: m=m[:-2]
                        row[z] += '\n'+t+': '+m+p
        rrr += row
    s = '\n'.join(rrr)
    while '   ' in s:
        s=s.replace('   ','  ')
    s=s.replace('\n\n','\n')
    return s
#

site = "https://www.accuweather.com/en/ca/toronto/m5j/hourly-weather-forecast/55488"

def req(urlx):
    h=''
    for z in '321':
        print z+'...',
        while 1:
            try:
                req = urllib2.Request(url=urlx,headers=user_agent)
                html = urllib2.urlopen(req).read()
                break
            except:
                print '...',
        h2t = html2text(html).split('Next 8 hours')[1]
        print
        print h2t
        print
        h += sort_data(h2t)
        if z != '1':
            urlx = next8page(html)
    return h

print 'might take a few minutes collecting data from the website'
msg = req(site)
# msg = sort_data(s) # for testing

# num=1235551234
# num=appuifw.query(u"Enter Number: ", "number", u"")

if msg:
    msg='24 Hour Intervals...\nAccuWeather SMS App via Kirk Lawrence\n\n'+msg
    print msg
    try:
        messaging.sms_send(u'%d' % (num), msg)
        print '\nMessage Sent!'
    except:
        print "\nSMS Unable To Send!"