Any suggestions as to a better way to handle the problem of encoding in the following context would be appreciated. The problem arose because 'Bogota' is spelt with an acute accent on the 'a'.

$ cat IP_info.py3
#!/usr/bin/env python3
# -*- coding : utf -8 -*-
# file: 'IP_info.py3'  a module.

import urllib.request

url_format_str = \
    'http://api.hostip.info/get_html.php?ip=%s&position=true'

def ip_info(ip_address):
    """
Returns a dictionary keyed by Country, City, Lat, Long and IP.

Depends on http://api.hostip.info (which returns the following:
'Country: UNITED STATES (US)\nCity: Santa Rosa, CA\n\nLatitude:
38.4486\nLongitude: -122.701\nIP: 76.191.204.54\n'.)
THIS COULD BREAK IF THE WEB SITE GOES AWAY!!!
"""
    response =  urllib.request.urlopen(url_format_str %\
                                   (ip_address, )).read()
    sp = response.splitlines()
    country = city = lat = lon = ip = ''
    for item in sp:
        if item.startswith(b"Country:"):
            try:
                country = item[9:].decode('utf-8')
            except:
                print("Exception raised.")
                country = item[9:]
        elif item.startswith(b"City:"):
            try:
                city = item[6:].decode('utf-8')
            except:
                print("Exception raised.")
                city = item[6:]
        elif item.startswith(b"Latitude:"):
            try:
                lat = item[10:].decode('utf-8')
            except:
                print("Exception raised.")
                lat = item[10]
        elif item.startswith(b"Longitude:"):
            try:
                lon = item[11:].decode('utf-8')
            except:
                print("Exception raised.")
                lon = item[11]
        elif item.startswith(b"IP:"):
            try:
                ip = item[4:].decode('utf-8')
            except:
                print("Exception raised.")
                ip = item[4:]
    return {"Country" : country,
            "City" : city,
            "Lat" : lat,
            "Long" : lon,
            "IP" : ip            }

if __name__ == "__main__":
    addr =  "201.234.178.62"
    print ("""    IP address is %(IP)s:
        Country: %(Country)s;  City: %(City)s.
        Lat/Long: %(Lat)s/%(Long)s""" % ip_info(addr))
"""

The output I get on an Ubuntu 12.4LTS system is as follows:
alex@x301:~/Python/Parse$ ./IP_info.py3
Exception raised.
    IP address is 201.234.178.62:
        Country: COLOMBIA (CO);  City: b'Bogot\xe1'.
        Lat/Long: 10.4/-75.2833


I would have thought that utf-8 could handle the 'a-acute'.

Thanks,
alex
_______________________________________________
Tutor maillist  -  Tutor@python.org
To unsubscribe or change subscription options:
https://mail.python.org/mailman/listinfo/tutor

Reply via email to