from pattern import web
from pattern.web import URL, Element
import re
from datetime import datetime, date, timedelta
url = URL(
'https://docs.google.com/spreadsheets/d/1J2I40hglES63YZHROcOL3oAjDPqiiKLRPE_ikAWsR-Q/pubhtml?gid=1267634591'
).read()
dom = Element(url)
dom = dom.by_tag('tbody')[0]
#date Get the date from the header
today = date = dom.by_class('s0')[1].content
#places Read the place from available class='s4' inside <td>
places = []
for ix in dom.by_class('s4'):
places.append(ix.content)
reading_row = [4, 10, 16, 22]
pol_reading = []
def cleanhtml(raw_html):
cleanr = re.compile('<.*?>')
cleantext = re.sub(cleanr, '', raw_html)
cleantext = cleantext.strip("Highest: ")
return cleantext
def cleandate(txt):
from pattern import web
from pattern.web import URL, Element
url = URL('https://docs.google.com/spreadsheets/d/1J2I40hglES63YZHROcOL3oAjDPqiiKLRPE_ikAWsR-Q/pubhtml?gid=1267634591').read()
dom = Element(url)
dom = dom.by_tag('tbody')[0]
#date Get the date from the header
date = dom.by_class('s0')[1].content
#places Read the place from available class='s4' inside <td>
places = []
for ix in dom.by_class('s4'):
places.append(ix.content)
try:
reading_row = [4, 10, 16, 22]
pol_reading = []
for row in reading_row:
reading = dom.by_tag('tr')[row]
reading = reading.by_tag('td')
for i in reading:
if len(i) >= 1:
pol_reading.append(i.content)
pol_updated_row = [5, 11, 17, 23]
pol_updated = []