import requests

my_times_api_key = 'YOUR-API-GOES-HERE'

payload = {'q'         : 'inequality', 
           'begin_date': '20130101' ,
           'end_date'  : '20131231',
           'api-key'   :  my_times_api_key,
           'sort'      : 'oldest' ,
           'offset'    :  20}

base_url = 'http://api.nytimes.com/svc/search/v2/articlesearch.json?'

r = requests.get(base_url, params = payload)

r.url

r.text

r.json()

json = r.json()


json.keys()


json.keys()

json['status']

json['response']['docs']

json['response']['meta']['hits']

from time import sleep

base_url = 'http://api.nytimes.com/svc/search/v2/articlesearch.json?'

years = [2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013]

for year in years:
    year_string = str(year)
    payload = { 'q'         : 'inequality', 
                'begin_date':  year_string + '0101',
                'end_date'  :  year_string + '1231',
                'api-key'   :  my_times_api_key,
                'sort'      : 'newest' ,
                'page'      :  0}
    
    r = requests.get(base_url, params = payload)
    json = r.json()
    count  = json['response']['meta']['hits']
    print year, count
    sleep(.1)

import csv

outfile = open('inequality_annual.csv', 'w')
csv_writer = csv.writer(outfile)

header = ['year','article_count']
csv_writer.writerow(header)

base_url = 'http://api.nytimes.com/svc/search/v2/articlesearch.json?'

years = [2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013]

for year in years:
    year_string = str(year)
    payload = { 'q'         : 'inequality', 
                'begin_date':  year_string + '0101',
                'end_date'  :  year_string + '1231',
                'api-key'   :  my_times_api_key,
                'sort'      : 'newest' ,
                'page'      :  0}
    
    sleep(.1)
    
outfile.close()

!cat inequality.csv

from time import sleep

base_url = 'http://api.nytimes.com/svc/search/v2/articlesearch.json?'

payload = { 'q'         : 'inequality', 
            'api-key'   :  my_times_api_key,
            'sort'      : 'newest' ,
            'page'      :  0}
    
years = [2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013]
counts = []
for year in years:
 
    
    year_string = str(year)
    payload['begin_date'] = year_string + '0101'
    payload['end_date']   = year_string + '1231'
    r = requests.get(base_url, params = payload)
    json = r.json()
    count  = json['response']['meta']['hits']
    counts.append(count)
    sleep(.1)   

%pylab inline
import matplotlib.pyplot as plt

plt.scatter(years,counts)
plt.ticklabel_format(useOffset=False)

outfile = open('inequality_annual.csv', 'w')
csv_writer = csv.writer(outfile)


base_url = 'http://api.nytimes.com/svc/search/v2/articlesearch.json?'

def last_day_calculator(month):
    '''A little function that tells you the last day of the month.'''
    if month in [1,3,5,7,8,10,13]:
        last_day = '31'
    elif month in [4,6,9,11]:
        last_day = '30'
    else:
        last_day = '28'
    return last_day


#Loop through each year 2006-2013
for year in range(2006,2013):
    #turn the interger into string
    year_string = str(year)
    
    #Loop through each month
    for month in range(1,3):
        
        
        
        #figure out the last day of that month
        last_day_string = last_day_calculator(month)
            
        month_string =  "%02d" % month

        
        payload = { 'q'         : 'inequality',
                    'begin_date':  year_string + month_string + '01',
                    'end_date'  :  year_string + month_string + last_day_string,
                    'api-key'   :  my_times_api_key,
                    'sort'      : 'newest' ,
                    'page'      :  0}
        
         
        r = requests.get(base_url, params = payload)
        json = r.json()
        count  = json['response']['meta']['hits']
        csv_writer.writerow( [year_string, month_string, count] )

        
        sleep(.5)
        
outfile.close()       



!cat inequality_annual.csv