def QueryAPI(catname):
params = {'action':'query','list':'categorymembers','format':'json','cmtitle':'Category:'+catname, 'cmprop':'title','cmnamespace':'1','cmlimit':'500'}
api = MWApi('http://en.wikipedia.org')
while True:
data = api.get(params)
for page in data['query']['categorymembers']:
print page['title']
if data.has_key('query-continue'):
params['cmcontinue'] = data['query-continue']['categorymembers']['cmcontinue']
else:
break
def login(username, password):
try:
mw = MWApi(host=app.config['MEDIAWIKI']['host'],
api_path=app.config['MEDIAWIKI']['api'])
mw.login(username, password)
mw.populateTokens()
user = User(username, password, edittoken=mw.tokens['edittoken'],
watchtoken=mw.tokens['watchtoken'])
session['username'] = user.username
session['password'] = user.password
return mw
except:
raise LoginFailedError("Unable to Login")
from db import *
from flask import *
import json
from werkzeug.contrib.cache import MemcachedCache
from werkzeug.contrib.atom import AtomFeed
from mwapi import MWApi
app = Flask(__name__)
app.debug = True
setup_app(app)
cache = MemcachedCache(['127.0.0.1:11211'])
api = MWApi("http://en.wikipedia.org")
@app.route('/issues')
def first_issues():
issues_data = cache.get("all_issues")
if not issues_data:
issues = Issue.query.order_by(Issue.date.desc()).all()
data = [issue.serialize() for issue in issues]
issues_data = json.dumps(data)
cache.set("all_issues", issues_data)
return (issues_data, 200, {'Content-Type': 'application/json'})
@app.route('/issues/<int:offset>')
def issues(offset):
# Stub, here because I'm lazy
def session(self, url: str) -> MWApi:
sess = MWApi(url, "/api.php")
sess.login(self._username, self._password)
return sess
from datetime import datetime
from dateutil import parser
from mwapi import MWApi
import codecs
import requests
import urllib2
import re
from flask import Flask
from db import *
START_YEAR = 2005
CUR_YEAR = datetime.now().year
api = MWApi('http://en.wikipedia.org')
def content_for_title(title):
title = urllib2.unquote(title)
data = api.get(action='parse', page=title, redirects=1,
prop='text')['parse']
text = data['text']['*']
return text
def get_subpages(prefix, namespace):
pages = api.get(action='query',
list='allpages',
apprefix=prefix,
apnamespace=namespace,