In [66]:
import pickle
import pandas as pd
from mwclient import Site
import datetime
import time

In [67]:
start_time = time.time()
start_time


Out[67]:
1483482304.675926

In [68]:
pol_tracker = None
def read_politician_tracker() : 
    global pol_tracker
    pol_tracker = pd.read_csv('profile-reading-tracker')
    pol_tracker = pol_tracker[['handle','finished_reading']]
read_politician_tracker()
pol_tracker.head()


Out[68]:
handle finished_reading
0 Quincy_Timberlake False
1 Fanny_Edelman False
2 Stojan_Novaković False
3 Paul_Scheffer False
4 Ed_Robb False

In [69]:
def get_unread_politician(pol_tracker):
    data_to_be_read = pol_tracker[pol_tracker['finished_reading'] == False]
    if(data_to_be_read.shape[0] > 0) :
        return data_to_be_read.iloc[0]['handle']
    else:
        return None
    
def write_read_politician(pol_tracker, politician):
    pol_tracker.loc[pol_tracker['handle'] == politician, 'finished_reading'] = True
    pol_tracker.to_csv('profile-reading-tracker')
    
get_unread_politician(pol_tracker)


Out[69]:
'Quincy_Timberlake'

In [70]:
user_agent = 'Uni Koblenz-Landau student, kandhasamy@uni-koblenz.de'
wiki = Site(host='en.wikipedia.org', clients_useragent=user_agent)

In [56]:
#this is just for testing whether writing the tracker file and reading back works or not
for i in range(1, 10):
    handle = get_unread_politician(pol_tracker)
    print(handle)
    write_read_politician(pol_tracker, handle)
    pol_tracker.head()


Yang_Ti-liang
Georges_Colombier
Gottlieb_Duttweiler
Mohammad_Natsir
Ján_Ševčík
Georges_Othily
Athanasios_N._Miaoulis
Kristalina_Georgieva
Otto_Hoetzsch

In [53]:
#read_politician_tracker()
pol_tracker.head()


Out[53]:
handle finished_reading
0 Quincy_Timberlake True
1 Fanny_Edelman True
2 Stojan_Novaković True
3 Paul_Scheffer True
4 Ed_Robb True