getarticles.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

def getArticle(article):
    article = article.split(',')
    singleSets = []
    try:
        chunks = gc.getChunks(article[1])
        print chunks
        tags =  tag.getTags(article[1],chunks)
        #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()

        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
    return singleSets

data = open('data/todayinhistory.txt').readlines()

print getArticle(data[0])