remove placemarks from a kml file

filter_kml.py

# python 2
# pip instal --user pykml
from pykml import parser

# kml source: https://www.census.gov/geo/maps-data/data/kml/kml_zcta.html
kml_file = 'cb_2017_us_zcta510_500k.kml'

# zip codes in one column text file
zip_file = 'our-zipcodes.txt'

zipcodes = {}
with open(zip_file) as zf:
    for line in zf:
        zipcodes[line.strip()] = 1

removed = 0
kept = 0

with open(kml_file) as f:
    doc = parser.parse(f)
    root = doc.getroot()

    folder = root.Document.Folder # parent of Placemark
    for pm in folder.getchildren():
        #print pm.tag, pm.getparent().tag

        if pm.tag == '{http://www.opengis.net/kml/2.2}Placemark':
            keep = False
            #zipcode = ''
            for sd in pm.ExtendedData.SchemaData.getchildren():
                if 'ZCTA5CE10' in sd.values():
                    if sd.text in zipcodes:
                        #zipcode = sd.text
                        keep = True
                    break
            if not keep:
                removed += 1
                folder.remove(pm)
            else:
                kept += 1

    doc.write('output.kml', xml_declaration=True, encoding='UTF-8')
print 'removed: ', removed
print 'kept: ', kept