cjwinchester

import requests
import csv
import json

def getCounties():
    "Function to return a dict of FIPS codes (keys) of U.S. counties (values)"
    d = {}
    r = requests.get("http://www2.census.gov/geo/docs/reference/codes/files/national_county.txt")
    reader = csv.reader(r.text.splitlines(), delimiter=',')    
    for line in reader:

cjwinchester

mkdir -p goat && ffmpeg -i goat.mp4 -vf "transpose=1" -r 10 goat/goat%03d.png && convert -resize 50% -delay 5 -loop 0 goat/goat*.png goat.gif

cjwinchester

"""

Unpacking a list of tuples to test for multiple replacement values. (Borrowed from a code snippet in "Mining the Social Web": http://shop.oreilly.com/product/0636920030195.do)

"""

REPLACE_LIST = [
    (', Incorporated',', Inc.'),
    (' Incorporated',' Inc.'),
    (', LLC',''),

cjwinchester

import requests
import json

def getDomainList():
    url = "http://data.iana.org/TLD/tlds-alpha-by-domain.txt"
    r = requests.get(url)
    s = r.text.split("\n")
    date =  s[0].split("Last Updated ")[1]
    
    js = {}

cjwinchester

#!/bin/bash
wget http://www.ssa.gov/oact/babynames/state/namesbystate.zip -O baby_names_by_state.zip
unzip baby_names_by_state.zip NE.TXT
sed -e '1i\state,sex,year,name,count' NE.TXT | csvcut -c sex,year,name,count | csvjson > ne-babies.json
rm NE.TXT baby_names_by_state.zip

cjwinchester

#!/bin/bash

wget -O fips_ref.txt http://www2.census.gov/geo/docs/reference/state.txt
wget --mirror --continue --no-directories ftp://ftp2.census.gov/geo/tiger/TIGER2015/PLACE/

for f in *.zip
do
    unzip $f
done

cjwinchester

"""

Pings the Nebraska Auditor of Public Accounts' budget database -- http://www.nebraska.gov/auditor/reports/index.cgi?budget=1 -- and returns a cleaner, transposed csv (or JSON) of summary budget data for every political subdivision in Nebraska.

~~ ARGUMENTS ~~
outfile: name of file to write to
delimit: delimiter for outfile, or pass "json" to return JSON
budget_year_list: list of budget years you want to grab data for, in the form ["2013-2014", "2014-2015"]

"""

cjwinchester

import requests
from bs4 import *
from time import *
import re
from string import ascii_lowercase

f = open('dougwarrants.txt', 'wb')
baseurl = "http://omahasheriff.com/services/warrants/criminal?searchterm="

for letter in ascii_lowercase:

cjwinchester

import requests
from bs4 import *
import time
import json
import os
import glob

# download flag gifs from CIA website
def getFlags():
    base = "https://www.cia.gov/library/publications/the-world-factbook/docs/flagsoftheworld.html"

cjwinchester

import os
import json
import re
import collections

def sub(text):
  return re.sub("ia-|ne-|us-|-topojson|-geojson|.json|.zip", "", text)
  
def getType(x):
    if "topojson" in x: