def get_shapefile_directory_list(state=None, geo_type=None):
_, directories, _ = next(os.walk(EXTRACT_DIR))
shapefile_directory_list = [
os.path.join(EXTRACT_DIR, directory) for directory in directories
if len(glob.glob(os.path.join(EXTRACT_DIR, directory, '*.shp'))) > 0
]
if geo_type:
# handle cd112, cd113, zcta5, etc.
if geo_type in ['cd', 'zcta5']:
geo_type_check = '_us_%s' % geo_type
shapefile_directory_list = filter(
lambda directory: geo_type_check in directory,
shapefile_directory_list)
else:
geo_type_check = '_%s' % geo_type.lower()
shapefile_directory_list = filter(
lambda directory: directory.endswith(geo_type_check),
shapefile_directory_list)
if state:
state_check = '_%s_' % get_fips_code_for_state(state)
shapefile_directory_list = filter(
lambda directory: state_check in directory or
('_us_' in directory and '_us_zcta5' not in directory),
shapefile_directory_list)
return shapefile_directory_list
def get_shapefile_directory_list(state=None, geo_type=None):
shapefile_directory_list = [
os.path.join(EXTRACT_DIR, directory) \
for directory in os.walk(EXTRACT_DIR).next()[1]
]
if geo_type:
# handle cd112, cd113, zcta5, etc.
if geo_type in ['cd','zcta5']:
geo_type_check = '_us_%s' % geo_type
shapefile_directory_list = filter(
lambda directory: geo_type_check in directory,
shapefile_directory_list
)
else:
geo_type_check = '_%s' % geo_type.lower()
shapefile_directory_list = filter(
lambda directory: directory.endswith(geo_type_check),
shapefile_directory_list
)
if state:
state_check = '_%s_' % get_fips_code_for_state(state)
shapefile_directory_list = filter(
lambda directory: state_check in directory \
or ('_us_' in directory and '_us_zcta5' not in directory),
shapefile_directory_list
)
return shapefile_directory_list
def get_filename_list_from_ftp(target, state):
target_files = urllib2.urlopen(target).read().splitlines()
filename_list = []
for line in target_files:
filename = '%s%s' % (target, line.decode().split()[-1])
filename_list.append(filename)
if state:
state_check = '_%s_' % get_fips_code_for_state(state)
filename_list = filter(
lambda filename: state_check in filename or
('_us_' in filename and '_us_zcta5' not in filename),
filename_list)
return filename_list
def build_dict_list(filename,
state=None,
geo_type=None,
include_polygon=False):
shapefile = ogr.Open(filename)
layer = shapefile.GetLayer()
state_check = get_fips_code_for_state(state) if state else None
dict_list = []
feature = layer.GetNextFeature()
while feature:
item = {}
if geo_type == 'zcta5':
# ZCTA shapefiles have different attribute names
_item_options = {
'include_polygon': include_polygon,
}
item = csv_helpers.make_zcta5_row(feature, item, geo_type,
_item_options)
else:
# All other geo_types share attribute names
# Filter rows by state if -s arg is passed
_statefp = feature.GetField("STATEFP")
if not state_check or (state_check == _statefp):
_item_options = {
'statefp': _statefp,
'include_polygon': include_polygon,
'geoid': feature.GetField("GEOID"),
'state_dict': STATE_FIPS_DICT[str(_statefp)],
}
item = csv_helpers.make_basic_row(feature, item, geo_type,
_item_options)
if geo_type:
row_builder = getattr(csv_helpers,
'make_%s_row' % geo_type)
item = row_builder(feature, item, _item_options)
if item:
dict_list.append(item)
feature.Destroy()
feature = layer.GetNextFeature()
shapefile.Destroy()
return dict_list
def get_filename_list_from_ftp(target, state):
target_files = urllib2.urlopen(target).read().splitlines()
filename_list = []
for line in target_files:
filename = '%s%s' % (target, line.split()[-1])
filename_list.append(filename)
if state:
state_check = '_%s_' % get_fips_code_for_state(state)
filename_list = filter(
lambda filename: state_check in filename \
or ('_us_' in filename and '_us_zcta5' not in filename),
filename_list
)
return filename_list
def build_dict_list(filename, state=None, geo_type=None,
include_polygon=False):
shapefile = ogr.Open(filename)
layer = shapefile.GetLayer()
state_check = get_fips_code_for_state(state) if state else None
dict_list = []
feature = layer.GetNextFeature()
while feature:
item = {}
if geo_type == 'zcta5':
# ZCTA shapefiles have different attribute names
_item_options = {
'include_polygon': include_polygon,
}
item = csv_helpers.make_zcta5_row(
feature, item, geo_type, _item_options)
else:
# All other geo_types share attribute names
# Filter rows by state if -s arg is passed
_statefp = feature.GetField("STATEFP")
if not state_check or (state_check == _statefp):
_item_options = {
'statefp': _statefp,
'include_polygon': include_polygon,
'geoid': feature.GetField("GEOID"),
'state_dict': STATE_FIPS_DICT[str(_statefp)],
}
item = csv_helpers.make_basic_row(feature, item, geo_type, _item_options)
if geo_type:
row_builder = getattr(csv_helpers, 'make_%s_row' % geo_type)
item = row_builder(feature, item, _item_options)
if item:
dict_list.append(item)
feature.Destroy()
feature = layer.GetNextFeature()
shapefile.Destroy()
return dict_list
