Quick project to determine how many hashtags an Instagram user has used. First grab all posts by user, then process posts and perform hashtag calculation.

process.coffee

fs = require 'fs'

files = fs.readdirSync "#{process.cwd()}/json"

dataMap = {}
for file in files
  raw = require "#{process.cwd()}/json/#{file}"
  for x in raw.data
    dataMap[x.id] = x

tagMap = {}
count = 0
for key, val of dataMap
  count += 1
  for t in val.tags
    if tagMap[t]
      tagMap[t] += 1
    else
      tagMap[t] = 1

console.log "Processed #{count} records"

tagCounts = []
for tag, count of tagMap
  if tagCounts[count]
    tagCounts[count].push(tag)
  else
    tagCounts[count] = [tag]


module.exports.tagMap = tagMap
module.exports.tagCounts = tagCounts
module.exports.printCounts = (counts) ->
  for index, val of counts
    if val
      console.log(index, "counts of", val)
  return null

scrape.coffee

request = require 'request'
fs = require 'fs'
crypto = require 'crypto'
md5 = crypto.createHash 'md5'

options =
  url: "https://api.instagram.com/v1/users/#{process.env.USER_ID}/media/recent"
  qs:
    access_token: process.env.ACCESS_TOKEN
    count: 1000
  json: true

count = 0

processData = (data) ->
  console.log 'length', data.data.length
  fs.writeFileSync "#{process.cwd()}/json/#{data.data[0].id}.json", JSON.stringify(data)


handleResponse = (err, response, body) ->
  if count is 1000
    return
  if not err
    processData body
    count += 1
    options =
      url: body.pagination.next_url
      json: true
    setTimeout (->
      request options, handleResponse
    ), 5000

request options, handleResponse