getArticle.py~

import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import app.parser.getData as importArticles
import app.parser.articleRetrieval.getArticles as getContent
import app.parser.sentences as sent
import app.parser.getChunks as gc
import app.analytics.tag as tag
import app.parser.articleRetrieval.wikipediaParse as wp
import app.analytics.functions.hasDate as hd
import nltk

data = open('data/train.txt','r').readlines()

#A

def getArticle(article):
    
    singleSets = []
    print article
    try:
        #chunks = gc.getChunks(article)
        #print "CHUNKS"
        tags =  tag.getTags(article)
        #if tags == []:
        #    continue # check this is right. go to next itteration
        """The Stanford Open IE tags"""
        subject = tags['subject']
        relation = tags['relation']
        objects = tags['object']
        #objects = objects.split()
        print article
        print "Subject: " + subject
        print "Relation: " + relation
        print "Objects: " + objects
    
        """content = wp.getArticle(subject)
        rawSentences = sent.getSentences(content)
        sentences = []
        for sentence in rawSentences:
            if(hd.hasDate(sentence) != []):
                sentences.append(sentence)
        listOfYears.append(article[0])
        SS = {'title':article[1], 'sentences':sentences, 'year':article[0]}
        singleSets.append(SS)"""
    except:
        pass

X = data[15].split(',')
print X
print getArticle(X[1])