A python script to identify corporate land owners

land_owner_extract.py

import sys, itertools, re

#Global Vars:
owner_field   = 'Owner'
file_location = r'/Users/jenningsanderson/Desktop/Tax_Parcels2014.dbf'
limit         = 10000000
pattern       = r".*(LLC|BANK|GROUP|\sLP)+.*"
output_file   = r'/Users/jenningsanderson/Desktop/companies.shp'


#########################################   Runtime   ##################################
try:
	from osgeo import ogr
except:
	sys.exit('ERROR: cannot find GDAL/OGR modules')

print "Importing File: ", file_location
db_file = ogr.Open(file_location)
lyr = db_file.GetLayer(0)
feature_count = lyr.GetFeatureCount()


print "Making new export file: ", output_file
driver = ogr.GetDriverByName("ESRI Shapefile")
data_source = driver.CreateDataSource(output_file)
dest_layer = data_source.CreateLayer('layer1',
    srs = lyr.GetSpatialRef(),
    geom_type=lyr.GetLayerDefn().GetGeomType())
feature  = lyr.GetFeature(0)
[dest_layer.CreateField(feature.GetFieldDefnRef(i)) for i in range(feature.GetFieldCount())]



print "Number of features: ", feature_count
print "Iterating..."
error_count = 0
match       = 0

prog = re.compile(pattern)

for feature in itertools.islice(lyr, limit):	#Safe guard
	try:
		owner_string = feature.GetField(owner_field)
		if prog.match(owner_string):
			match += 1
			dest_layer.CreateFeature(feature)
	except:
		error_count += 1

print "Successfully Matched: ", match
print "Did not have names: ", error_count

For Windows: osgeo4w