seed.py 文件源码

def load_tweetkeywords():
    """
    Check and see which keywords are used in each tweet, and load the association
    table linking tweets and keywords
    """

    # TweetKeyword.query.delete()

    tweets = Tweet.query.all()
    keyword_query = Keyword.query.all()
    keywords = []
    [keywords.append(word.keyword) for word in keyword_query]

    tknzr = TweetTokenizer()

    for tweet in tweets:
        tokenized_tweets = tknzr.tokenize(tweet.text)

        for token in tokenized_tweets:
            if token in keywords:
                tweet_id = Tweet.query.filter(Tweet.tweet_id == tweet.tweet_id).one()
                keyword_id = Keyword.query.filter(Keyword.keyword == token).one()
                tweet_keyword = TweetKeyword(keyword_id=keyword_id.keyword_id, tweet_id=tweet_id.tweet_id)
                print "Added to TweetKeyword table: {}".format(tweet_keyword.keyword_id)
                db.session.add(tweet_keyword)

    db.session.commit()



################################################################################