gitabites

import requests
import json
import csv

#here, we're going to retrieve the most shared articles from the NYT within the past 30 days and determine which author has contributed the most articles
#first, we hit up the most-shared endpoint and store the response as an object
pop_request = 'http://api.nytimes.com/svc/mostpopular/v2/mostshared/all-sections/30.json?api-key=[your-key]'
pop = requests.get(pop_request)

#store just the content

gitabites

# modified from http://brianabelson.com/open-news/2013/12/17/scrape-the-gibson.html

import requests
from bs4 import BeautifulSoup
from pprint import pprint
from urlparse import urljoin
import dataset
import csv
import pandas as pd

gitabites

#Main vs skim emails
mainboxCount = db.emails.find({"category": "main"}).count() 
print "Number of emails in mainbox: " + str(mainboxCount)
 
skimboxCount = db.emails.find({"category": "skim"}).count() 
print "Number of emails in skimbox:" + str(skimboxCount)
 
#to find main emails received at given day of week:
mainMonday = db.emails.find({"headers.Date":{"$regex":"Mon"}, "category": "main"}).count()
print "Number of mainbox emails received on Mondays: " + str(mainMonday)

gitabites

#number of reclassifications, cumulative
skimToMain = db.recategorization.find({"recategorizedTo": "main"}).count()
print "Number of messages recategorized to main, cummulative:" + str(skimToMain)

mainToSkim = db.recategorization.find({"recategorizedTo": "skim"}).count()
print "Number of messages recategorized to skim, cummulative:" + str(maintoSkim)


#Weekly reclassifications
from datetime import date, timedelta