zip_code = zip_re.findall(address[2])[0].strip()
street = address[0].strip()
else:
po_street = po_address[0].strip()
po_city = city_re.findall(po_address[2])[0].strip()
po_zip_code = zip_re.findall(po_address[2])[0].strip()
po_state = state_re.findall(po_address[2])[0].strip()
address_state = state_re.findall(address[2])[0].strip()
city = city_re.findall(address[2])[0].strip()
zip_code = zip_re.findall(address[2])[0].strip()
street = address[0].strip()
phone = dogcatcher.find_phone(phone_re, county)
fax = dogcatcher.find_phone(fax_re, county)
email = dogcatcher.find_emails(email_re, county)
hours = hours_re.findall(county)[0].strip(" \r\n")
if "PO Box" not in po_street:
review = review + "c"
fips = dogcatcher.find_fips(county_name, voter_state)
if fips == "":
print county_name + " has no findable FIPS. It may be a spellling difference."
sys.exit()
result.append([
authority_name, first_name, last_name, county_name, fips, street, city,
address_state, zip_code, po_street, po_city, po_state, po_zip_code,
reg_authority_name, reg_first, reg_last, reg_street, reg_city,
street = street.replace(po_street, "").replace(", , ",", ").strip(", ")
city = city_re.findall(address)[0].strip()
address_state = state_re.findall(address)[0].strip()
zip_code = zip_re.findall(address)[0].strip()
print street + ", " + city + ", " + address_state + " " + zip_code
print po_street + ", " + po_city + ", " + po_state + " " + po_zip_code
phone = dogcatcher.find_phone(phone_re, county)
fax = dogcatcher.find_phone(fax_re,county)
email = dogcatcher.find_emails(email_re, county)
try:
if county_name == "Staunton City":
website = "http://www.staunton.va.us/directory/departments-h-z/registrar/how-to-vote"
else:
website = dogcatcher.website_find(website_re, county)
except:
website = ""
fips = dogcatcher.find_fips(county_name, voter_state)
county_result.append([authority_name, first_name, last_name, county_name, fips,
street, city, address_state, zip_code,
po_street, po_city, po_state, po_zip_code,
#There's only a single physical or mailing address, and all addresses are only two lines. State is not included.
#Address_re finds the address. We then check whether it's a physical or mailing address, and assign the other variables accordingly.
#Since the city and zip code are explicitly set out in the data (as City: Foovile \n Zip: 11111), this gets both directly from the county data, instead of extracting it from the complete address.
address = address_re.findall(county)[0].strip()
if "PO " in address:
po_street = address
po_city = city_re.findall(county)[0].strip()
po_zip_code = zip_re.findall(county)[0].strip()
else:
street = address
city = city_re.findall(county)[0].strip()
zip_code = zip_re.findall(county)[0].strip()
email = dogcatcher.find_emails(email_re, county).replace("%20", "")
phone = dogcatcher.find_phone(phone_re, county)
fax = dogcatcher.find_phone(fax_re, county)
fips = dogcatcher.find_fips(county_name, voter_state)
result.append([
authority_name, first_name, last_name, county_name, fips, street, city,
address_state, zip_code, po_street, po_city, po_state, po_zip_code,
reg_authority_name, reg_first, reg_last, reg_street, reg_city,
reg_state, reg_zip_code, reg_po_street, reg_po_city, reg_po_state,
reg_po_zip_code, reg_phone, reg_fax, reg_email, reg_website, reg_hours,
phone, fax, email, website, hours, voter_state, source, review
])
reg_po_state = state_re.findall(reg_csz)[0].strip()
reg_po_zip_code = zip_re.findall(reg_csz)[0].strip().title()
if reg_street:
reg_city = city_re.findall(reg_csz)[0].strip().title()
reg_state = state_re.findall(reg_csz)[0].strip()
reg_zip_code = zip_re.findall(reg_csz)[0].strip().title()
phone = dogcatcher.find_phone(phone_re, town, areacode = "203")
if ("(203) 203-") in phone:
phone = dogcatcher.clean_phone(phone.partition(" ")[2])
print phone
email = dogcatcher.find_emails(email_re, town)
fax = dogcatcher.find_phone(fax_re, town)
official_name = name_re.findall(town)[0].title()
first_name, last_name, review = dogcatcher.split_name(official_name, review)
#This section finds the full address for the town clerk. After finding the address, it identifies a city/state/zip (csz) combination and a PO Box number if that exists.
#It removes both the CSZ and the PO Address (if it exists) from the full address, leaving behind a street address with some garbage.
#It then cleans up the street address and pulls the city, state, and zip out of the csz, and assigns them as appropriate to the street address and state.
address = abs_address_re.findall(town)[0]
csz = csz_re.findall(address)[0]
if not address.replace(csz,""):
#They split in a neat place, so we're able to use partition instead of a regular expression.
#Another part of the content is the county website, so we split that off as well.
#This yields three pieces of data: absentee (absentee voting official), registration (registration official), and county_web (website official).
offices = county.partition("div >Voter Registration")
absentee = offices[0]
regweb = offices[2].partition("County Website")
registration = regweb[0]
county_web = regweb[2]
website = dogcatcher.find_website(website_re, county_web)
reg_website = website
email = dogcatcher.find_emails(email_re, absentee)
reg_email = dogcatcher.find_emails(email_re, registration)
phone = dogcatcher.find_phone(phone_re, absentee)
reg_phone = dogcatcher.find_phone(phone_re, registration)
# print absentee
# print registration
print name_re.findall(absentee)
absentee_official = name_re.findall(absentee)[0].replace("</div>","") #In one county, the regular expression used yields </div> as a response. The other easy fix creates more problems, so we just remove the </div>.
first_name, last_name, review = dogcatcher.split_name(absentee_official, review)
if absentee_official:
authority_name = direct_re.findall(absentee)[2].replace(county_name + " County","").replace(county_name + " Co","").replace(county_name,"").replace(" . "," ").strip(", .")
else:
try:
po_street = po_re.findall(jurisdiction)[0].replace("v: ","")
except:
po_street = ""
if not po_street:
street = mailing_address.replace("v: ","")
elif digit_re.findall(mailing_address.replace(po_street,"")):
street = mailing_address.replace(po_street,"")
else:
po_street = mailing_address
street = street.rstrip(",")
email = dogcatcher.find_emails(email_re, jurisdiction)
phone = dogcatcher.phone_find(phone_re, jurisdiction)
fax = dogcatcher.phone_find(fax_re, jurisdiction)
try:
city = city_re.findall(jurisdiction)[0].replace("v: ","")
except:
city = ""
zip_code_all = zip_code_re.findall(jurisdiction)
if len(zip_code_all) == 2:
zip_code = zip_code_all[1].replace("v: ","")
elif len(zip_code_all) == 1:
zip_code = zip_code_all[0].replace("v: ","")
else:
zip_code = ""
authority_name, first_name, last_name, county_name, town_name, fips, street, city, address_state, zip_code, po_street, po_city, po_state, po_zip_code, reg_authority_name, reg_first, reg_last, reg_street, reg_city, reg_state, reg_zip_code, reg_po_street, reg_po_city, reg_po_state, reg_po_zip_code, reg_phone, reg_fax, reg_email, reg_website, reg_hours, phone, fax, email, website, hours, review = dogcatcher.begin(voter_state)
print reg_po_state
county_name = county_names[county_data.index(county)]
print "___________________________________"
print county
print "+++++++++++++++++++++++++++++++++++"
name = name_re.findall(county)[0].strip()
first_name, last_name, authority_name, review = dogcatcher.make_name(name, ", ", review)
email = h.unescape(dogcatcher.find_emails(email_re, county))
website = dogcatcher.find_website(website_re, county)
phone = dogcatcher.find_phone(phone_re, county)
fax = dogcatcher.find_phone(fax_re, county, area_re.findall(phone)[0]) #The fax #s don't come with area codes.
#We know that there are either one or two address-shaped things in any given county.
#So we first find all of the addresses, and then proceed based on whether there's one or two.
addresses = address_re.findall(county)
if len(addresses)==1:
#This section finds the full address. After finding the address, it identifies a city/state/zip (csz) combination and a PO Box number if that exists.
#It removes both the CSZ and the PO Address (if it exists) from the full address, leaving behind a street address with some garbage.
#It then cleans up the street address and pulls the city, state, and zip out of the csz, and assigns them as appropriate to the street address and state.
# There's only a single physical or mailing address, and all addresses are only two lines. State is not included.
# Address_re finds the address. We then check whether it's a physical or mailing address, and assign the other variables accordingly.
# Since the city and zip code are explicitly set out in the data (as City: Foovile \n Zip: 11111), this gets both directly from the county data, instead of extracting it from the complete address.
address = address_re.findall(county)[0].strip()
if "PO " in address:
po_street = address
po_city = city_re.findall(county)[0].strip()
po_zip_code = zip_re.findall(county)[0].strip()
else:
street = address
city = city_re.findall(county)[0].strip()
zip_code = zip_re.findall(county)[0].strip()
email = dogcatcher.find_emails(email_re, county).replace("%20", "")
phone = dogcatcher.find_phone(phone_re, county)
fax = dogcatcher.find_phone(fax_re, county)
fips = dogcatcher.find_fips(county_name, voter_state)
result.append(
[
authority_name,
first_name,
last_name,
county_name,
fips,
street,
