Created
April 24, 2017 20:11
-
-
Save citizenrich/75ea8e03bd61725a9219ddc2341a6a0b to your computer and use it in GitHub Desktop.
So far on census API
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import os | |
import requests | |
from bs4 import BeautifulSoup | |
import pandas as pd | |
from itertools import zip_longest | |
census_key = os.environ.get("CENSUS_KEY") | |
# base = 'http://api.census.gov/data/2011/acs5' | |
base = 'http://api.census.gov/data/2015/acs5' | |
# washington dc is 11 | |
params = {'key': census_key, 'get': 'B00001_001E', 'for': 'state:11'} | |
params2 = {'key': census_key, 'get': 'B00001_001E', 'for': 'tract:*', 'in': 'state:11+county:*'} | |
y = requests.get(base, params=params) | |
print(y.url, y.text) | |
z = requests.get(base, params=params2) | |
print(z.url, z.text) | |
rent_base = 'http://api.census.gov/data/2015/acs5' | |
params3 = {'key': census_key, 'get': 'NAME,B01003_001E,B25057_001E,B25058_001E,B25059_001E', 'for': 'tract:*', 'in': 'state:11'} | |
w = requests.get(rent_base, params3) | |
print(w.url, w.text) | |
all_base = 'http://api.census.gov/data/2015/acs5' | |
params4 = {'key': census_key, 'get': '*', 'for': 'tract:*', 'in': 'state:11'} | |
a = requests.get(all_base, params4) | |
print(a.url, a.text) | |
bs_url = 'http://api.census.gov/data/2015/acs5/variables.html' | |
y = requests.get(bs_url) | |
soup = BeautifulSoup(y.text, 'lxml') | |
table = soup.find_all('table')[0] | |
names = [] | |
for link in table.find_all('a'): | |
names.append(link.get('name')) | |
# print(names) | |
def grouper(iterable, n, fillvalue=''): | |
args = [iter(iterable)] * n | |
return zip_longest(*args, fillvalue=fillvalue) | |
list_of_lists_of_lists = [] | |
for g in grouper(names, 30): | |
gstring = ','.join(g) | |
params_template = {'key': census_key, 'get': gstring, 'for': 'tract:*', 'in': 'state:11'} | |
b = requests.get(all_base, params_template) | |
# print(b.text) | |
list_of_lists_of_lists.append(b.text) | |
# STOPPED WORKING HERE. String error with data type. | |
for i, lol in enumerate(list_of_lists_of_lists): | |
# header = lol.pop() <- not working for some reason | |
header = lol[0] | |
if i == 0: | |
df = pd.DataFrame(lol, header) | |
else: | |
df = pd.concat(df, pd.DataFrame(lol, header), axis=1) #, join_axes=[df[0]["tract"]] | |
df.to_csv('out.csv') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment