A script to scrape the data from Time Warner Cable's channel listings

time_warner_channel_listings.py

#!/usr/bin/python
import json, sys

# convert time warner cable's json channel listing to csv
#  http://www.timewarnercable.com/northeast/support/clu/clu.ashx?CLUID=476&Zip=14534&Embedded=true

# 1. use chrome's "network" tab in "developer tools" to obtain a curl command line to retrieve the listing (http://www.timewarnercable.com/CustomerService/Clu/CluJson.ashx?[..])
# 2. retrieve the listing w/ curl
# 3. nuke the non-ascii bytes perl -i.bak -pe 's/[^[:ascii:]]//g' time_warner_channel_listings.json

# this pretty-printer might be helpful: http://jsonprettyprint.com/json-pretty-printer.php

f=open("time_warner_channel_listings.json")
j=f.read()

chans = json.loads(j)

for chan in chans["channelList"]:
	# 1904- starter tv. 1905- standard tv. 1906- preferred tv. 2527- twc sports pass.
	print( "%s, %d, %d, %d, %d, %d" % (chan['n'], chan['no'], 1904 in chan['pkg'],1905 in chan['pkg'],1906 in chan['pkg'],2527 in chan['pkg']))