Ejemplo n.º 1
0
import re
from bs4 import BeautifulSoup
import urllib3
import numpy as np
from flask.ext.pymongo import PyMongo
import os
import sys

app = Flask(__name__)
app.config['MONGO_URI'] = os.getenv('MONGOHQ_URL')
mongo = PyMongo(app)
processor = TextProcessor()

with app.app_context():
    processor.map_data(mongo.db.postings.find())
    processor.build_doc_matrix()


@app.route('/', methods=['GET', 'POST'])
def main():
    if request.method == 'GET':
        return render_template('index.html')

    url = request.form['url'].strip()
    domain = 'newyork.craigslist.org/'

    if not domain in url:
        return render_template('index.html', error='Please enter a valid URL')

    # process unseen document
    try: