From f4d0245a7e3e026779ef7baa997b8793737f327e Mon Sep 17 00:00:00 2001
From: Michael Orlitzky <michael@orlitzky.com>
Date: Wed, 11 Nov 2009 10:57:20 -0500
Subject: [PATCH] Modified the Data module and download script to download the
 Summary File 1 data.

---
 bin/download_data | 15 +++++-----
 src/Data.py       | 72 ++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 76 insertions(+), 11 deletions(-)

diff --git a/bin/download_data b/bin/download_data
index 37741cd..81bffc4 100755
--- a/bin/download_data
+++ b/bin/download_data
@@ -17,13 +17,13 @@ from Data import State, County
 
 
 # Create the State objects.
-de = State(10, 'Delaware')
-dc = State(11, 'District of Columbia')
-md = State(24, 'Maryland')
-ny = State(36, 'New York')
-pa = State(42, 'Pennsylvania')
-va = State(51, 'Virginia')
-wv = State(54, 'West Virginia')
+de = State(10, 'Delaware', 'DE')
+dc = State(11, 'District of Columbia', 'DC')
+md = State(24, 'Maryland', 'MD')
+ny = State(36, 'New York', 'NY')
+pa = State(42, 'Pennsylvania', 'PA')
+va = State(51, 'Virginia', 'VA')
+wv = State(54, 'West Virginia', 'WV')
 
 
 # Now we add all of the counties belonging to each state, starting
@@ -404,5 +404,6 @@ wv.add_county(109, 'Wyoming')
 # Now that the counties have been added, create a list of states to
 # pass to the download_lines function.
 states = [de, dc, md, ny, pa, va, wv]
+Data.download_sf1(states)
 Data.download_blocks(states)
 Data.download_lines(states)
diff --git a/src/Data.py b/src/Data.py
index e08f466..d953124 100644
--- a/src/Data.py
+++ b/src/Data.py
@@ -17,30 +17,52 @@ class State:
 
     Example:
 
-    http://www2.census.gov/geo/tiger/TIGER2009/24_MARYLAND
+    SF1:   http://www2.census.gov/census_2000/datasets/Summary_File_1/Maryland
+    TIGER: http://www2.census.gov/geo/tiger/TIGER2009/24_MARYLAND
     
     """
 
+    SF1_ROOT = 'http://www2.census.gov/census_2000/datasets/Summary_File_1'
     TIGER_ROOT = 'http://www2.census.gov/geo/tiger/TIGER2009'
     
-    def __init__(self, initial_id=None, initial_name=None):
+    def __init__(self, initial_id=None, initial_name=None, abbreviation = None):
         self.id = initial_id
+        self.abbreviation = abbreviation
         self.name = initial_name
         self.counties = []
 
 
+    def sf1_data_root(self):
+        sdr =  self.SF1_ROOT + '/'
+        sdr += self.name.replace(' ', '_')
+        return sdr
+
+
     def tiger_data_root(self):
         tdr =  self.TIGER_ROOT + '/'
         tdr += str(self.id) + '_' + self.name.upper().replace(' ', '_')
         return tdr
 
 
+    def sf1_data_url(self):
+        sdu = self.sf1_data_root() + '/'
+        sdu += self.sf1_zipfile_name()
+        return sdu
+
+
     def blocks_data_url(self):
         bdu =  self.tiger_data_root() + '/'
         bdu += self.blocks_zipfile_name()
         return bdu
 
 
+    def sf1_data_path(self):
+        sdp = 'data/census2000/'
+        sdp += self.name.lower().replace(' ', '_')
+        sdp += '/sf1'
+        return sdp
+
+
     def blocks_data_path(self):
         bdp =  'data/census2000/'
         bdp += self.name.lower().replace(' ', '_')
@@ -55,10 +77,20 @@ class State:
         return ldp
 
 
+    def sf1_zipfile_name(self):
+        return self.abbreviation.lower() + 'geo_uf1.zip'
+
+
     def blocks_zipfile_name(self):
         return 'tl_2009_' + str(self.id) + '_tabblock00.zip'
 
 
+    def sf1_geo_file_path(self):
+        sgfp = self.sf1_data_path() + '/'
+        sgfp += self.abbreviation.lower() + 'geo.uf1'
+        return sgfp
+
+
     def blocks_shapefile_path(self):
         bsp =  self.blocks_data_path() + '/'
         bsp += 'tl_2009_' + str(self.id) + '_tabblock00.shp'
@@ -137,6 +169,38 @@ class County:
 
 
 
+def download_sf1(states):
+    """
+    Download the Summary File 1 geo file for each state.
+    """
+
+    for state in states:
+        # First, create the blocks data path if it doesn't exist.
+        FileUtils.mkdir_p(state.sf1_data_path(), 0755)
+
+        if not os.path.exists(state.sf1_geo_file_path()):
+            url = state.sf1_data_url()
+            tmpfile = state.sf1_zipfile_name()
+            print "Grabbing SF1 data for %s." % state.name
+            print "Downloading %s to %s..." % (url, tmpfile)
+
+            try:
+                # This can fail for a bunch of reasons...
+                urllib.urlretrieve(url, tmpfile)
+                print "Unzipping %s to %s..." % (tmpfile, state.sf1_data_path())
+                z = zipfile.ZipFile(tmpfile)
+                z.extractall(state.sf1_data_path())
+            except:
+                # That we don't care about.
+                pass
+            finally:
+                # But we always clean up after ourselves.
+                print "Removing %s..." % tmpfile
+                FileUtils.rm_f(tmpfile)
+                print "Done.\n"
+
+
+
 def download_blocks(states):
     """
     Download the TIGER/Line block files for each state.
@@ -149,7 +213,7 @@ def download_blocks(states):
         if not os.path.exists(state.blocks_shapefile_path()):
             url = state.blocks_data_url()
             tmpfile = state.blocks_zipfile_name()
-            print "Grabbing data for %s." % state.name
+            print "Grabbing TIGER blocks data for %s." % state.name
             print "Downloading %s to %s..." % (url, tmpfile)
 
             try:
@@ -184,7 +248,7 @@ def download_lines(states):
             if not os.path.exists(county.lines_shapefile_path()):
                 url = county.tiger_data_url()
                 tmpfile = county.lines_zipfile_name()
-                print "Grabbing data for %s (%s)." % (county.full_name(), state.name)
+                print "Grabbing TIGER lines data for %s (%s)." % (county.full_name(), state.name)
                 print "Downloading %s to %s..." % (url, tmpfile)
                 
                 try:
-- 
2.44.2