Parse some JSON for the CWW

parse_json.py

# This relies on chicago-classifications.json being in the 
# same folder as this parse_json.py file
# 
# It will then make a .tsv from the JSON stream
# Kickass, Mr. Fidino and @sethherr

import json

cww_json = open( "chicago-classifications.json", "r" )

export = open('cww_tab.tsv', 'w')
export.write("species\tcount\tbehavior\tbabies\tid\n")
export.close()

for line in cww_json:
  photo_data = json.loads(line)
  if "species" in photo_data["annotations"][0]:
    tsv_line = photo_data["annotations"][0]["species"]
  else: 
    tsv_line = "nothing"
  tsv_line += "\t"

  if "count" in photo_data["annotations"][0]:
    tsv_line += photo_data["annotations"][0]["count"]
  else:
    tsv_line += "NA"
  tsv_line += "\t"

  if "behavior" in photo_data["annotations"][0]:
    tsv_line += ', '.join(photo_data["annotations"][0]["behavior"])
  else:
    tsv_line += "NA"
  tsv_line += "\t"

  if "babies" in photo_data["annotations"][0]:
    tsv_line += photo_data["annotations"][0]["babies"]
  else:
    tsv_line += "NA"
  tsv_line += "\t"

  tsv_line += photo_data['_id']['$oid']
  print tsv_line
  tsv_line += "\n"

  with open('cww_tab.tsv', 'a') as file:
    file.write(tsv_line)

cww_json.close()