bytearchive

#!/usr/bin/env python3

from argparse import ArgumentParser
from urllib.parse import urlparse
from scrapy.crawler import CrawlerProcess
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor

parser = ArgumentParser()
parser.add_argument('-d', '--domain')

bytearchive

#! /bin/sh
# ==================================================================
#  ______                           __     _____
# /_  __/___  ____ ___  _________ _/ /_   /__  /
#  / / / __ \/ __ `__ \/ ___/ __ `/ __/     / /
# / / / /_/ / / / / / / /__/ /_/ / /_      / /
#/_/  \____/_/ /_/ /_/\___/\__,_/\__/     /_/

# Multi-instance Apache Tomcat installation with a focus
# on best-practices as defined by Apache, SpringSource, and MuleSoft

bytearchive

import json
import datetime
import pytz
from random import randint
import logging
import time
import redis

main_prefix = "bqueues:"

bytearchive

#! /usr/bin/env python
# -*- coding: utf-8 -*-
"""This module's docstring summary line.

This is a multi-line docstring. Paragraphs are separated with blank lines.
Lines conform to 79-column limit.

Module and packages names should be short, lower_case_with_underscores.
Notice that this in not PEP8-cheatsheet.py

bytearchive

#! /usr/bin/env python
# -*- coding: utf-8 -*-
"""This module's docstring summary line.

This is a multi-line docstring. Paragraphs are separated with blank lines.
Lines conform to 79-column limit.

Module and packages names should be short, lower_case_with_underscores.
Notice that this in not PEP8-cheatsheet.py

bytearchive

#!/usr/bin/env python

import os
import requests
import uuid
from random import randint
from uuid import uuid4

def read_in_chunks(file_object, chunk_size=65536):
    while True:

bytearchive

import os
import sys

# constants, configure to match your environment
HOST = 'http://localhost:9200'
INDEX = 'test'
TYPE = 'attachment'
TMP_FILE_NAME = 'tmp.json'
# for supported formats, see apache tika - http://tika.apache.org/1.4/formats.html
INDEX_FILE_TYPES = ['html','pdf', 'doc', 'docx', 'xls', 'xlsx', 'xml']

bytearchive

# post_loc.txt contains the json you want to post
# -p means to POST it
# -H adds an Auth header (could be Basic or Token)
# -T sets the Content-Type
# -c is concurrent clients
# -n is the number of requests to run in the test

ab -p post_loc.txt -T application/json -H 'Authorization: Token abcd1234' -c 10 -n 2000 http://example.com/api/v1/locations/

bytearchive

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

bytearchive

#########################
# .gitignore file for Xcode4 and Xcode5 Source projects
#
# Apple bugs, waiting for Apple to fix/respond:
#
#    15564624 - what does the xccheckout file in Xcode5 do? Where's the documentation?
#
# Version 2.6
# For latest version, see: http://stackoverflow.com/questions/49478/git-ignore-file-for-xcode-projects
#