[Tutor] encoding question

[eryksun]

On Sun, Jan 5, 2014 at 2:57 AM, Alex Kleider <akleider at sonic.net> wrote:
> def ip_info(ip_address):
>
>     response =  urllib2.urlopen(url_format_str %\
>                                    (ip_address, ))
>     encoding = response.headers.getparam('charset')
>     print "'encoding' is '%s'." % (encoding, )
>     info = unicode(response.read().decode(encoding))

decode() returns a unicode object.

>     n = info.find('\n')
>     print "location of first newline is %s." % (n, )
>     xml = info[n+1:]
>     print "'xml' is '%s'." % (xml, )
>
>     tree = ET.fromstring(xml)
>     root = tree.getroot()   # Here's where it blows up!!!
>     print "'root' is '%s', with the following children:" % (root, )
>     for child in root:
>         print child.tag, child.attrib
>     print "END of CHILDREN"
>     return info

Danny walked you through the XML. Note that he didn't decode the
response. It includes an encoding on the first line:

    <?xml version="1.0" encoding="ISO-8859-1" ?>

Leave it to ElementTree. Here's something to get you started:

    import urllib2
    import xml.etree.ElementTree as ET
    import collections

    url_format_str = 'http://api.hostip.info/?ip=%s&position=true'
    GML = 'http://www.opengis.net/gml'
    IPInfo = collections.namedtuple('IPInfo', '''
        ip
        city
        country
        latitude
        longitude
    ''')

    def ip_info(ip_address):
        response = urllib2.urlopen(url_format_str %
                                   ip_address)
        tree = ET.fromstring(response.read())
        hostip = tree.find('{%s}featureMember/Hostip' % GML)
        ip = hostip.find('ip').text
        city = hostip.find('{%s}name' % GML).text
        country = hostip.find('countryName').text
        coord = hostip.find('.//{%s}coordinates' % GML).text
        lon, lat = coord.split(',')
        return IPInfo(ip, city, country, lat, lon)


    >>> info = ip_info('201.234.178.62')
    >>> info.ip
    '201.234.178.62'
    >>> info.city, info.country
    (u'Bogot\xe1', 'COLOMBIA')
    >>> info.latitude, info.longitude
    ('10.4', '-75.2833')

This assumes everything works perfect. You have to decide how to fail
gracefully for the service being unavailable or malformed XML
(incomplete or corrupted response, etc).