Created
March 16, 2015 23:10
-
-
Save milesgrimshaw/03b4b082b4493240c8ea to your computer and use it in GitHub Desktop.
Script to collect search count data for various terms in Yelp across top 60 US cities
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
require 'oauth' | |
require 'json' | |
require 'pp' | |
require 'csv' | |
consumer_key = '#YOURS' | |
consumer_secret = '#YOURS' | |
token = '#YOURS' | |
token_secret = '#YOURS' | |
api_host = 'api.yelp.com' | |
consumer = OAuth::Consumer.new(consumer_key, consumer_secret, {:site => "http://#{api_host}"}) | |
access_token = OAuth::AccessToken.new(consumer, token, token_secret) | |
cities = [ | |
"New+York", "Los+Angeles", "Chicago", "Houston", "Philadelphia", "Pheonix", "San+Antonio", "San+Diego", "Dallas", "San+Jose", "Austin", "Jacksonville", | |
"Indianapolis", "San+Francisco", "Columbus", "Fort+Worth", "Charlotte", "Detroit", "El+Paso", "Memphis", "Boston", "Seattle", "Denver", "Washington", | |
"Nashville", "Baltimore", "Louisville", "Portland", "Oklahoma+City", "Milwaukee", "Las+Vegas", "Albuquerque", "Tucson", "Fresno", "Sacramento", | |
"Long+Beach", "Kansas+City", "Mesa", "Virginia+Beach", "Atlanta","Colorado+Springs", "Raleigh", "Omaha", "Miami", "Oakland", "Tulsa", "Minneapolis", | |
"Cleveland", "Wichita", "Arlington", "New+Orleans", "Bakersfield", "Tampa", "Honolulu", "Anaheim", "Aurora", "Santa+Ana", "St.+Louis,MA", "Riverside", | |
"Corpus+Christi", "Pittsburgh" | |
] | |
segments = [ | |
"fitness+class", "bootcamp", "crossfit+gym", "yoga+class", "pilates+class", "martial+arts+class", "spin+class", | |
"biking+class", "boxing", "ballet+class", "barre+class", "yoga", "pilates" | |
] | |
CSV.open("yelp_two.csv", "wb") do |csv| | |
row = Array.new | |
row << "City" | |
for y in 0..(segments.length-1) | |
row << segments[y] | |
end | |
csv << row | |
for z in 0..(cities.length-1) | |
city = cities[z] | |
row = Array.new | |
row << city | |
pp city | |
for i in 0..(segments.length-1) | |
item = segments[i] | |
path = "/v2/search?term=#{item}&location=#{city}" | |
result = JSON.parse(access_token.get(path).body) | |
count = result["total"] | |
pp count | |
row << count | |
end | |
csv << row | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment