def getFiveDigitZCTAs(depends_on="http://www.census.gov/geo/www/cob/z52000.html", creates=root + "FiveDigitZCTAs/"):
MakeDir(creates)
wget(depends_on, creates + "__Index.html")
Soup = BS.BeautifulSoup(open(creates + "__Index.html"))
A = [
(Contents(x.findParent()).split(" - ")[0].strip(), str(dict(x.attrs)["href"]))
for x in Soup.findAll("a")
if "_shp" in str(x)
]
for (name, url) in A:
print "Downloading", name
wget("http://www.census.gov" + url, creates + url.split("/")[-1])
os.system("cd " + creates + " ; unzip " + url.split("/")[-1])
def WgetMultiple(link, fname, maxtries=10):
link = link if is_string_like(link) else link['URL']
opstring = '--user-agent="Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1.7) Gecko/20091221 Firefox/3.5.7"'
time.sleep(5)
for i in range(maxtries):
wget(link, fname, opstring)
F = open(fname,'r').read().strip()
if F.startswith('<!DOCTYPE HTML'):
return
else:
print 'download of ' + link + ' failed: ' + F[:20]
time.sleep(15)
print 'download of ' + link + ' failed after ' + str(maxtries) + ' attempts'
return
def bls_downloader(download_dir,code):
MakeDirs(download_dir)
download_dir += ('/' if download_dir[-1] != '/' else '')
MakeDir(download_dir + 'RawDownloads/')
get = "ftp://ftp.bls.gov/pub/time.series/" + code + '/'
WgetMultiple(get,download_dir + 'RawDownloads/index.html')
Soup = BeautifulSoup(open(download_dir + 'RawDownloads/index.html'))
A = Soup.findAll('a')
Records = [(Contents(a),str(dict(a.attrs)['href'])) for a in A]
Records = [r for r in Records if 'Current' not in r[0].split('.')]
RecordsR = [r for r in Records if 'AllData' in r[0]]
if RecordsR:
Records = RecordsR + [r for r in Records if not '.data.' in r[0]]
T = tb.tabarray(records = Records,names = ['File','URL'])
for (f,u) in T:
wget(u,download_dir + 'RawDownloads/' + f + '.txt')
makemetadata(code,download_dir + 'RawDownloads/',download_dir + 'metadata.pickle',download_dir + 'filenames.tsv')
MakeDir(download_dir + '__FILES__')
processtextfile(download_dir + 'RawDownloads/',download_dir + '/__FILES__/documentation.txt')
MakeDir(download_dir + '__PARSE__')
for l in listdir(download_dir + 'RawDownloads/'):
if '.data.' in l:
Rename(download_dir + 'RawDownloads/' + l, download_dir + '__PARSE__/' + l)
SPs = [download_dir + 'RawDownloads/' + l for l in listdir(download_dir + 'RawDownloads/') if l.endswith('.series.txt')]
assert len(SPs) == 1, 'Wrong number of series paths.'
serpath = SPs[0]
parse_series(download_dir + 'RawDownloads/',download_dir + 'series.txt')
delete(serpath)
def getStates(depends_on="http://www.census.gov/geo/cob/bdy/st/st00shp/st99_d00_shp.zip", creates=root + "States/"):
MakeDir(creates)
wget(depends_on, creates + "st99_d00_shp.zip")
os.system("cd " + creates + " ; unzip st99_d00_shp.zip")
def getMSA(depends_on="http://www.census.gov/geo/www/cob/mmsa2003.html", creates=root + "MSA/"):
MakeDir(creates)
for x in ["cs99_03c_shp.zip", "cb99_03c_shp.zip", "md99_03c_shp.zip"]:
wget("http://www.census.gov/geo/cob/bdy/metroarea/2003/shp/" + x, creates + x)
os.system("cd " + creates + " ; unzip " + x)
def getCounties(depends_on="http://www.census.gov/geo/cob/bdy/co/co00shp/co99_d00_shp.zip", creates=root + "Counties/"):
MakeDir(creates)
wget(depends_on, creates + "co99_d00_shp.zip")
os.system("cd " + creates + " ; unzip co99_d00_shp.zip")
def getCensusRegions(
depends_on="http://www.census.gov/geo/cob/bdy/rg/rg99_d00_shp.zip", creates=root + "CensusRegions/"
):
MakeDir(creates)
wget(depends_on, creates + "rg99_d00_shp.zip")
os.system("cd " + creates + " ; unzip rg99_d00_shp.zip")
def modwget(dd,path): if 'opstring' in dd.dtype.names: wget(dd['URL'],path,opstring=dd['opstring']) else: wget(dd['URL'],path)
