pawelmhm

from scrapy.spider import  Spider
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import Selector
from scrapy.item import Item, Field
import urllib

class Question(Item):
    tags = Field()
    answers = Field()

pawelmhm

#!/usr/bin/python

from __future__ import print_function
from optparse import OptionParser
import sys
from collections import OrderedDict
import warnings
warnings.filterwarnings("ignore")

import pandas as pd

pawelmhm

#!/usr/local/bin/python3.5
import asyncio
from aiohttp import ClientSession


class Crawler(object):
    i = 1
    limit = 5
    url = "http://localhost:8080/{}"

pawelmhm

import json
import sys

from twisted.internet.ssl import DefaultOpenSSLContextFactory
from twisted.web import server
from twisted.web.resource import Resource
from twisted.internet import reactor
from twisted.python import log

pawelmhm

# -*- coding: utf-8 -*-
from __future__ import absolute_import, division, unicode_literals

import logging
from collections import OrderedDict
from time import time
from urllib.parse import urldefrag

from scrapy.core.downloader import Downloader
from scrapy.core.downloader.handlers.http11 import HTTP11DownloadHandler, \