extract_amazon_id.py

import lxml.html
import re

src = """
lksjdfls <div id ='amazon_345343'> kdjff lsdfs </div> sdjfls <div id
=   "amazon_35343433">sdfsd</div><div id='amazon_8898'>welcome</div>
hello, my age is 86 years old and I was born in 1945. Do you know
that
PI is roughly 3.1443534534534534534 """

regex = re.compile('amazon_(\d+)')

doc = lxml.html.document_fromstring(src)

for div in doc.xpath('//div[starts-with(@id, "amazon_")]'):
    match = regex.match(div.get('id'))
    if match:
        print match.groups()[0]