Re: Matching Postal Addresses
Re: Matching Postal Addresses
- Subject: Re: Matching Postal Addresses
- From: Michael Rothwell <email@hidden>
- Date: Thu, 13 Nov 2003 07:22:17 -0500
The USPS "Web Tools" API is more straight-forward. XML in, XML out.
http://www.usps.com/webtools/htm/Address-Information.htm
On Nov 12, 2003, at 3:13 PM, Michael Rothwell wrote:
Here's a snippet of Python code. It scrapes the usps.com website and
returns XML. I wish Apple would embrace Python as a first-class OSX
development language -- with Aqua widget binding, etc.
# imported libraries
###################################################################
import httplib, sys, string, urllib
import exceptions
import string, os, sys
from mimetools import choose_boundary
from MimeWriter import MimeWriter
import base64
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
def extractData(text):
ret = ""
try:
ret = string.split(text,">")[1]
ret = string.split(ret,"<")[0]
return string.strip(ret)
except:
return text
def CSZ(text):
ret = ""
try:
ret = "<csz>" + string.replace(string.replace(string.strip(text
+ "")," -", "-")," "," ") + "</csz>\n"
ary = string.split(text," ")
CS=string.strip(ary[0])
C=CS[0:-3]
S=string.strip(CS[-3:])
Z=string.replace(string.strip(ary[1])," ","")
ret = ret + "<city>" + C + "</city>\n<state>" + S +
"</state>\n<zip>" + Z + "</zip>\n"
except:
return text
return ret
def pyGetAddressFromUSPS(address1,address2,city,state,addrline="0"):
server = "www.usps.com"
params = urllib.urlencode({"zipcode": "", "Selection": 1,
"address": address1 + " " + address2, "address1": address1,
"address2": address2, "city": city,"state":
state,"urbanization":"","firm":""})
url = "http://"; + server + "/zip4/zip4_response.jsp?" + params
method = "GET"
stuff = ""
ret = ""
try:
conn = httplib.HTTPConnection(server + ":80")
conn.connect()
#conn.sock.settimeout(100.0)
headers = {"Host": server, "Accept": "text/html"}
conn.request(method, url, params, headers)
response = conn.getresponse()
stuff = response.read()
conn.close()
except:
return ""
if stuff + "" != "":
count = 0
try:
ary = string.split(stuff,"\n")
for line in ary:
if (string.find(line,"<Firm Line/>") >= 0):
tmp = extractData(line)
if (tmp + "" != ""):
ret = ret + "<firm>" + tmp + "</firm>\n"
if
(string.find(line,"<Address Line/>") >= 0):
tmp = extractData(line)
if tmp[:1] == "(":
tmp=""
if (tmp + "" != ""):
ret = ret + "<address>" + tmp +
"</address>\n"
if
(string.find(line,"<City-State-ZIP/>") >= 0):
tmp = CSZ(extractData(line))
if (tmp + "" != ""):
ret = ret + tmp
if (ret + "" != ""):
ret = "<usps><line>" + string.strip(addrline) +
"</line>" + ret + "</usps>"
return ret
except:
return ""
Jason McInnes wrote:
Thansk, everyone for your help,
Given my timeframe, (a couple of weeks) and the nature
of my application (batch conversion routine), I'm
partial to the screen scraping suggestion by Michael.
I've never done it before. Any suggestions on where I
could quickly learn how to do it?
I searched the archive, but didn't come up with
anything concrete...
Thanks!
Jason
_______________________________________________
cocoa-dev mailing list | email@hidden
Help/Unsubscribe/Archives:
http://www.lists.apple.com/mailman/listinfo/cocoa-dev
Do not post admin requests to the list. They will be ignored.
_______________________________________________
cocoa-dev mailing list | email@hidden
Help/Unsubscribe/Archives:
http://www.lists.apple.com/mailman/listinfo/cocoa-dev
Do not post admin requests to the list. They will be ignored.