amferraz

from scrapy.utils.project import get_project_settings

def stop_reactor():
    reactor.stop() #Stops reactor to prevent script from hanging

if __name__ == '__main__':
    
    #Handles engine_stopped to stop twisted reactor
    dispatcher.connect(stop_reactor, signal=signals.engine_stopped)
    

amferraz

Requirements

• bootstrap with typeahead
• jquery

Explanation

This will use bootstrap with typeahead to create an autocomplete search.

amferraz

class CustomSpider(BaseSpider):
    def __init__(self, start_url=None, **kwargs):
        super(BaseSpider, self).__init__(*args, **kwargs)
        if start_url:
            self.start_url = start_url

    def start_requests(self):
        return [Request(self.start_url)]

amferraz

# -*- coding:utf-8 -*-
 
import pika
from pika import exceptions
from pika.adapters import twisted_connection
from twisted.internet import defer, reactor, protocol, task
 
# First of all, what is a Twisted deferred?
# reference http://migre.me/eBL9F
#

amferraz

#!/usr/bin/env python
# http://www.rabbitmq.com/tutorials/tutorial-two-python.html
import pika
import sys

connection = pika.BlockingConnection(pika.ConnectionParameters(
        host='localhost'))
channel = connection.channel()

message = ' '.join(sys.argv[1:]) or "Hello World!"

amferraz

Vagrant.configure("2") do |config|
  config.vm.box = "MY_BOX_NAME"

  config.vm.provider :aws do |aws, override|
    aws.access_key_id = "MY_ACCESS_KEY_ID"
    aws.secret_access_key = "MY_SECRET_ACCESS_KEY"
    aws.keypair_name = "MY_KEYPAIR_NAME"
    aws.security_groups = "MY_VAGRANT_SECURITY_GROUP"

    # take a look here for AMIs/regions info:

amferraz

# -*- coding: utf-8 -*-
from vagrant import Vagrant

vm_name = 'vm_name_on_vagrantfile'
v = Vagrant()

hostname = v.hostname(vm_name=vm_name)

amferraz

from twisted.internet import reactor
from scrapy.crawler import Crawler
from scrapy.settings import Settings
from scrapy import signals
from testspiders.spiders.followall import FollowAllSpider


class MyPipeline(object):

    def process_item(self, item, spider):

amferraz

Function	Shortcut
previous tab	⌘ + left arrow
next tab	⌘ + right arrow
go to tab	⌘ + number
go to window	⌘ + Option + Number
go to split pane by direction	⌘ + Option + arrow
go to split pane by order of use	⌘ + ] , ⌘ + [
split window horizontally (same profile)	⌘ + D
split window vertically (same profile)	⌘ + d

amferraz

# coding: utf-8

import requests
from lxml import html

home = requests.get('http://www.submarino.com.br/')
home_tree = html.fromstring(home.text)

products_links_xpath = '//*[@id="tab"]/div/ul/li/div/a/@href'
products_links = home_tree.xpath(products_links_xpath)