dzzt.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree

import urllib2


xml = u"""<rss xmlns:g="http://base.google.com/ns/1.0" version="2.0">
<channel>
<title>...</title>
<description>...</description>
<link>http://www.example.com/</link>
<item>
<title>
<![CDATA[ Armani Idole d'Armani 50ml Eau de Parfum Spray ]]>
</title>
<link>
<![CDATA[
    http://www.example.com/Armani_ Idole d-Armani 50ml EDP Spray ?language=en&currency=GBP
    ]]>
</link>
<description>
<![CDATA[
    Armani Idole d Armani 50ml Eau de Parfum Spray Demonstration Bottle, Plain Box, Unused RSP £50.55 LOVESCENTS SPECIAL PRICE....£33.99 Idole d’Armani is a spicy floral developed by perfumer Bruno Jovanovic and features notes of clementine, pear, ginger, davana, saffron, jasmine, loukoum rose, patchouli and vetiver.
    ]]>
</description>
<g:brand>
<![CDATA[ GIORGIO ARMANI ]]>
</g:brand>
<g:condition>new</g:condition>
<g:id>
<![CDATA[ 353_gb ]]>
</g:id>
<g:image_link>
<![CDATA[
    http://www.example.com/image/cache/data/Idole%20d'Armani-500x500.jpg
    ]]>
    </g:image_link>
    <g:availability>in stock</g:availability>
    <g:mpn>
    <![CDATA[ GAIDOLEW001 ]]>
    </g:mpn>
    <g:price>34.99 GBP</g:price>
    <g:product_type>
    <![CDATA[ Womens Fragrances ]]>
    </g:product_type>
    <g:product_type>
    <![CDATA[ Womens Fragrances &gt; Eau de Toilette ]]>
    </g:product_type>
    <g:product_type>
    <![CDATA[ Womens Fragrances &gt; Perfumes ]]>
    </g:product_type>
    <g:product_type>
    <![CDATA[ Womens - Best Sellers ]]>
    </g:product_type>
    <g:shipping_weight>200.00kg</g:shipping_weight>
    <g:google_product_category>
    <![CDATA[
    Health &amp; Beauty &gt; Personal Care &gt; Cosmetics &gt; Perfume &amp; Cologne
    ]]>
    </g:google_product_category>
    <g:adwords_publish>
    <![CDATA[ true ]]>
    </g:adwords_publish>
    </item>
    </channel>
</rss>"""

NS = 'http://base.google.com/ns/1.0'
NSMAP = {'g': NS }

tree = etree.fromstring(xml)
items = tree.findall('.//rss/channel/g:brand',namespaces=NSMAP)
for item in items:
    print item.text.strip()