Markbnj

sudo apt-add-repository ppa:vbernat/haproxy-1.5
sudo apt-get update
sudo apt-get -qy install haproxy
sudo cp /etc/haproxy/haproxy.cfg /etc/haproxy/haproxy.cfg.orig

# To enable logging edit /etc/rsyslog.conf to match the following:
#
# provides UDP syslog reception
# $ModLoad imudp
# $UDPServerRun 514

Markbnj

# DockerFile for building a base image for python services

FROM ubuntu:15.04
MAINTAINER Someone <someone@some.where>

# common stuff
RUN echo "#!/bin/sh\nexit 0" > /usr/sbin/policy-rc.d && \
mkdir /home/root && \
dpkg-reconfigure locales && \
locale-gen en_US en_US.UTF-8 && \

Markbnj

# Script to update elasticsearch.yml and launch the service. In this
# scenario the service is being launched inside a container on ec2
# but the technique is easily generalizable.
#
# Expects the following environment vars to be set inside the container
#
#   HOST_IP        - the IP address of the host running the container
#   AWS_ACCESS_KEY - the AWS account access key
#   AWS_SECRET_KEY - the AWS account secret key
#   CLUSTER_NAME   - the name of the ES cluster to join

Markbnj

# Sometimes you need to get the IP of the ec2 instance a container
# is running on. This script will get the IP from the local metadata
# service and inject it as an environment var.
localip=$(curl -s http://169.254.169.254/latest/meta-data/local-ipv4)
export HOST_IP=$localip
sudo docker run -i -t -e "HOST_IP=$localip" --name="test" -h="test" some-repo

Markbnj

# An example showing how to set up phantomjs for use with Selenium

from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities


# These arguments will be passed on the phantomjs command line
# when webdriver launches it. See the reference page at
# http://phantomjs.org/api/command-line.html for more settings.
#

Markbnj

# sets the http/s proxy for the current shell to
# the passed argument, which should be in the form
# http://xxx.xxx.xxx.xxx:xxxx
export http_proxy=$1
export https_proxy=$http_proxy
export no_proxy="localhost,127.0.0.1"

Markbnj

import requests
import json


# For information on endpoints and arguments see the geonames
# API documentation at:
# 
#   http://www.geonames.org/export/web-services.html

class Geonames(object):

Markbnj

import requests
import json


GOOGLE_API_KEY = "<A google API key>"


TEXT_SEARCH_TEMPLATE = "https://maps.googleapis.com/maps/api/place/textsearch/json?key={}&query={}"
NEARBY_SEARCH_TEMPLATE = "https://maps.googleapis.com/maps/api/place/nearbysearch/json?key={}&location={},{}&radius={}"
DETAIL_SEARCH_ID_TEMPLATE = "https://maps.googleapis.com/maps/api/place/details/json?key={}&placeid={}"

Markbnj

# The scrapyd daemon adds a lot of power and flexibility to scrapy, but it also adds a layer of indirection
# (another process) that can make debugging a running spider troublesome. Use this code to launch scrapyd
# in ipdb (or pdb). You'll be able to breakpoint and catch exceptions inside the spiders it launches.

import scrapyd.runner
import ipdb

ipdb.runcall(scrapyd.runner.main)

Markbnj

from boto import ec2

class Resource(object):
    """
    Represents a single resource returned from the Discovery class's
    get_resources method.
    """
    def __init__(self, host_name, private_host_name, ip, private_ip, tags):
        self.__host_name = host_name
        self.__private_host_name = private_host_name