dinner_recipe = '''
amtunititem
24slicesbaguette
2+tbspolive oil
1cuptomatoes
1jarpesto
''' # From http://effbot.org/zone/element-index.htm import xml.etree.ElementTree as etree tree = etree.fromstring(dinner_recipe) # For invalid HTML use http://effbot.org/zone/element-soup.htm # import ElementSoup, StringIO # tree = ElementSoup.parse(StringIO.StringIO(dinner_recipe)) pantry = set(['olive oil', 'pesto']) for ingredient in tree.getiterator('tr'): amt, unit, item = ingredient if item.tag == "td" and item.text not in pantry: print ("%s: %s %s" % (item.text, amt.text, unit.text))