RIDB ES Indexer

indexer.py

from lxml import etree
from pyelasticsearch import ElasticSearch
es = ElasticSearch('http://localhost:9200/')


def RecArea(filename):
    ns = etree.FunctionNamespace("http://www.recreation.gov/architecture/")
    ns.prefix = "arc"
    doc = etree.parse(filename)
    for area in doc.xpath('//arc:RecArea'):
        values = {}
        children = area.getchildren()
        for child in children:
            if child.tag.replace("{http://www.recreation.gov/architecture/}", "") == "RecAreaID":
                recareaid = child.text
            values[child.tag.replace("{http://www.recreation.gov/architecture/}", "")] = child.text
       
        address_path = str("//arc:RecAreaAddress/arc:RecAreaID[text()='%s']/.." % recareaid)
        for address in doc.xpath(address_path):
            children = address.getchildren()
            for child in children:
                values[child.tag.replace("{http://www.recreation.gov/architecture/}", "")] = child.text
        print values
        es.index("ridb", "RecArea", values, id=recareaid)

RecArea('formatted.xml')