pije76

import csv
from cStringIO import StringIO

from scrapy.http import Request
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector

from scrapy_tests.items import CrunchfeedItem

class Crunchfeed(BaseSpider):

pije76

#!/usr/bin/env python
# encoding: utf-8

import sys, os, getopt
from django.core.management import setup_environ
import settings
setup_environ(settings)

from django.db.models import Q

pije76

from one_session_per_user.models import User, Visitor
from django.contrib.sessions.models import Session


class OneSessionPerUserMiddleware(object):
    """http://stackoverflow.com/a/1814797"""

    def process_request(self, request):
        if isinstance(request.user, User):
            current_key = request.session.session_key

pije76

Quick and Dirty Integration of elasticsearch api with rails

Take the following with a grain of salt ...

We started prototyping with ES & Rails about 2 days ago and I quickly discovered that things became a bit unwieldy the more I utilized elasticsearch. For now I am running with this type of integration with rails 3.2.15 to assess elasticsearch.

While we have done preliminary reviews on how to set up a production environment (still scratching my head on how to handle the split brain bug) , there's certainly plenty of what I'm not aware of, so if you see a fault in this approach, please let me know.

I may update this later on with a couple of convenience methods on the data models ...

pije76

#!/bin/bash

# Source: http://toomuchdata.com/2012/06/25/how-to-install-python-2-7-3-on-centos-6-2/

# Install stuff #
#################

# Install development tools and some misc. necessary packages
yum -y groupinstall "Development tools"
yum -y install zlib-devel  # gen'l reqs

pije76

#!/usr/bin/env bash

# Simple move this file into your Rails `script` folder. Also make sure you `chmod +x puma.sh`.
# Please modify the CONSTANT variables to fit your configurations.

# The script will start with config set by $PUMA_CONFIG_FILE by default

PUMA_CONFIG_FILE=config/puma.rb
PUMA_PID_FILE=tmp/pids/puma.pid
PUMA_SOCKET=tmp/sockets/puma.sock

pije76

#!/bin/sh
### BEGIN INIT INFO
# Provides: unicorn
# Required-Start:    $all
# Required-Stop:     $network $local_fs $syslog
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: starts the unicorn instances
# Description:       starts the unicorn server instances using start-stop-daemon
#

pije76

#!/bin/sh
#
# init.d script for single or multiple unicorn installations. Expects at least one .conf 
# file in /etc/unicorn
#
# Modified by jay@gooby.org http://github.com/jaygooby
# based on http://gist.github.com/308216 by http://github.com/mguterl
#
## A sample /etc/unicorn/my_app.conf
## 

pije76

require 'bundler/capistrano'

set :application, "net"
set :repository,  "git@githost.com:net.git"

set :scm, :git

set :default_environment, {
  'PATH' => "$HOME/.rbenv/shims:$HOME/.rbenv/bin:$PATH"
}

pije76

# RAILS_ROOT/config/unicorn.rb
# Search for "# SET ME!" and replace these with your own settings!.

HOW_DEEP_WE_R_FROM_RAILS_ROOT = "../.."

# Set environment to development unless something else is specified
RAILS_ROOT = File.expand_path(HOW_DEEP_WE_R_FROM_RAILS_ROOT, File.dirname(__FILE__))
SHARED_PATH = File.expand_path('../shared', RAILS_ROOT)

ENV['BUNDLE_GEMFILE'] = File.expand_path("#{HOW_DEEP_WE_R_FROM_RAILS_ROOT}/Gemfile", File.dirname(__FILE__))