def main():
assert os.path.exists(ALMANAC_DIR), ALMANAC_DIR
files = glob.glob(ALMANAC_DIR + '*/people/*/rep_*.htm') + \
glob.glob(ALMANAC_DIR + '*/people/*/*s[12].htm')
files.sort()
for fn in files:
district = web.storage()
demog = None
dist = web.lstrips(web.rstrips(fn.split('/')[-1], '.htm'), 'rep_')
diststate = dist[0:2].upper()
distnum = dist[-2:]
distname = tools.fixdist(diststate + '-' + distnum)
d = almanac.scrape_person(fn)
load_election_results(d, distname)
if ALMANAC_DIR + '2008' in fn:
if 'demographics' in d:
demog = d['demographics']
elif distname[-2:] == '00' or '-' not in distname: # if -00 then this district is the same as the state.
#print "Using state file for:", distname
statefile = ALMANAC_DIR + '2008/states/%s/index.html' % diststate.lower()
demog = almanac.scrape_state(statefile).get('state')
demog_to_dist(demog, district)
district.almanac = 'http://' + d['filename'][d['filename'].find('nationaljournal.com'):]
#print 'district:', distname, pformat(district)
db.update('district', where='name=$distname', vars=locals(), **district)
def main():
assert os.path.exists(ALMANAC_DIR), ALMANAC_DIR
files = glob.glob(ALMANAC_DIR + 'people/*/rep_*.htm') + \
glob.glob(ALMANAC_DIR + 'people/*/*s[12].htm')
files.sort()
for fn in files:
district = web.storage()
demog = None
dist = web.lstrips(web.rstrips(fn.split('/')[-1], '.htm'), 'rep_')
diststate = dist[0:2].upper()
distnum = dist[-2:]
distname = tools.fixdist(diststate + '-' + distnum)
d = almanac.scrape_person(fn)
load_election_results(d, distname)
if 'demographics' in d:
demog = d['demographics']
elif distname[-2:] == '00' or '-' not in distname: # if -00 then this district is the same as the state.
#print "Using state file for:", distname
statefile = ALMANAC_DIR + 'states/%s/index.html' % diststate.lower()
demog = almanac.scrape_state(statefile).get('state')
demog_to_dist(demog, district)
district.almanac = 'http://' + d['filename'][d['filename'].find('nationaljournal.com'):]
#print 'district:', distname, pformat(district)
db.update('district', where='name=$distname', vars=locals(), **district)
def main():
districts = simplejson.load(file(DATA_DIR + '/load/districts/index.json'))
assert os.path.exists(ALMANAC_DIR), ALMANAC_DIR
out = {}
for fn in glob.glob(ALMANAC_DIR + 'people/*/rep*'):
district = web.storage()
dist = web.lstrips(web.rstrips(fn.split('/')[-1], '.htm'), 'rep_')
diststate = dist[0:2].upper()
distnum = dist[-2:]
d = almanac.scrape_person(fn)
if 'demographics' in d:
demog = d['demographics']
else:
#@@ maybe only when diststate + '-00' in districts?
statefile = ALMANAC_DIR + 'states/%s/index.html' % diststate.lower()
demog = almanac.scrape_state(statefile).get('state')
if demog:
district.cook_index = get_int(demog, 'Cook Partisan Voting Index')
district.area_sqmi = cleanint(web.rstrips(demog['Area size'], ' sq. mi.'))
district.poverty_pct = get_int(demog, 'Poverty status')
district.median_income = get_int(demog, 'Median income')
(district.est_population_year,
district.est_population) = coalesce_population(demog, [
(2006, 'Pop. 2006 (est)'),
(2005, 'Pop. 2005 (est)'),
(2000, 'Pop. 2000'),
])
if 'interest_group_rating' in d:
district.interest_group_rating = d['interest_group_rating']
district.almanac = 'http://' + d['filename'][d['filename'].find('nationaljournal.com'):]
# Nationaljournal numbers districts of congressmen-at-large
# and territorial delegates '01' in its URLs, but our
# districts file numbers them '00'.
if distnum == '01' and diststate + '-00' in districts:
distnum = '00'
out[diststate + '-' + distnum] = district
return out
