# Authors: Sidney Steward and Francys Scott
# Date: May 15, 2013
# Purpose: Wellesley Events final project

# File was modified by Eni Mustafaraj on Feb 20, 2015.

from datetime import datetime
import urllib2
from xml.dom.minidom import parseString
import json

def get_text(dom, nodeName):
    "Helper function to read the text from a given node."
    txt = ""
    try: txt = dom.getElementsByTagName(nodeName)[0].firstChild.nodeValue
    except: print "Couldn't find text for node: ", nodeName
    return txt.strip()
  
eventTypeDict = {"Arts":['Event-Concert', 'Event-Exhibit', 'Event-Film', 
                    'Event-Performance'],
            "Sports":['P E R A Camp', 'P E R A Class','P E R A Contest', 
                      'P E R A Meeting', 'P E R A Open Recreation',
                      'P E R A Practice', 'P E R A Recreation Program', 
                      'P E R A Scrimmage', 'P E R A Special Event',
                      'Student: Club Sport', 'Student: Club Sport Contest', 
                      'Student: Club Sport Practice'],
            "CWS":['Event-Workshop', 'Event-Training', 'Event-Webinar'],
            "LPS":['Event-Interviews', 'Event-Lecture', 'Event-Panel', 
                   'Event-Seminar', 'Event-Symposium', 'Registrar-Lecture'],
            "Religious":['Event-Religious/Spiritual', 'Student: Religious/Spiritual'],
            "Student":['Student: Ceremony', 'Student: Class (Non-credit)', 
                       'Student: Party', 'Student: Performance',
                       'Student: Reception', 'Student: Recital', 'Student: Rehearsal', 
                       'Student: Seminar','Student: Study Break', 'Student: Symposium', 
                       'Student: Trip', 'Student: Community Service',
                       'Student: Concert', 'Student: Conference', 'Student: Dinner', 
                       'Student: Exhibit', 'Student: Film Showing',
                       'Student: Lecture', 'Student: Lunch/Brunch', 'Student: Meeting', 
                       'Student: Overnight', 'Student: Panel',
                       'Student: Vendor', 'Student: Wellness', 'Student: Workshop'],
            "Miscellaneous":['Event-Announcement', 'Event-Breakfast', 'Event-Ceremony', 
                             'Event-Community Service', 'Event-Dinner', 'Event-Luncheon', 
                             'Event-Meeting', 'Event-Party', 'Event-Reception', 'Event-Recital', 
                             'Event-Rehearsal','Event-Study Break', 'Event-Tour', 
                             'Event-Wellness', 'Registrar-Class Presentation', 'Registrar-Exam',
                             'Registrar-Film', 'Registrar-Honors Oral', 'Registrar-Meeting', 
                             'Registrar-Review Session',
                             'Registrar-Tutoring', 'Vendor']}

def read_data(url):
    "Reads data from RSS and extracts a few desired fields"
    page = urllib2.urlopen(url)  
    data = page.read()
    xmldoc = parseString(data)
    items = xmldoc.getElementsByTagName('item') # every event is an item

    eventsDct = {}
    for item in items:
        title = get_text(item, 'title')
        starttime = get_text(item, 'start_time')
        endtime = get_text(item, 'end_time')
        link = get_text(item, 'link')
        id = get_text(item, 'link').split('=')[1] # get event id
        organizer = get_text(item, 'requestor')
        description = get_text(item, 'description')
        place = get_text(item, 'location')
        eventType = get_text(item, 'event_type').strip()   # remove white space
        for key in eventTypeDict:
            if eventType in eventTypeDict[key]: category = key
            else: category = ""
            break
        
        eventsDct[id] = {'id': id, 'title': title, 'url': link, 'starttime': starttime,
                         'endtime': endtime, 'organizer': organizer, 'description': description,
                         'eventType': eventType, 'category': category, 'place': place}

    return eventsDct
        
# Main method.
# Execute the code to read the feed and store the events
URL = "https://events.wellesley.edu/cs-rss.php"
events = read_data(URL)
#create_events()
print len(events)
print events.items()[:4]

json.dump(events, open("WCevents.json", 'w'))