gcetusic

def sort_data(data, ignored_keys=None):
    """
    Sort members of lists and dictionaries, regardless of type
    """
    if ignored_keys is None:
        ignored_keys = []

    if isinstance(data, dict):
        return {k: sort_data(data[k], ignored_keys=ignored_keys) for k in sorted(data)}

gcetusic

/etc/ufw/applications.d/plexmediaserver

[plexmediaserver]
title=Plex Media Server (Standard)
description=The Plex Media Server
ports=32400/tcp|3005/tcp|5353/udp|8324/tcp|32410:32414/udp

[plexmediaserver-dlna]
title=Plex Media Server (DLNA)
description=The Plex Media Server (additional DLNA capability only)

gcetusic

# Copyright 2016 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file
# except in compliance with the License. A copy of the License is located at
#
#     http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is distributed on an "AS IS"
# BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations under the License.

gcetusic

The Data

Compression

• Original: 708MB
• xz -3: 70MB, 5:41.02 (2.07 mb/sec - 10:1 ratio)
• bzip2 -3: 74MB, 4:39.11 (2.53 mb/sec - 9.5:1 ratio)
• gzip -3: 103MB: 0:15.15 (46.73 mb/sec - 6.87:1 ratio)
• lzop -3: 146MB, 0:06.53 (108.42 mb/sec - 4.85:1 ratio)

gcetusic

import xmldataset
import pandas as pd
import argparse
import time
import re
import os
from datetime import datetime
from multiprocessing import Pool
from glob import glob

gcetusic

import asyncio
from aiohttp import web
import subprocess


async def uptime_handler(request):
    # http://HOST:PORT/?interval=90
    interval = int(request.GET.get('interval', 1))
    
    # Without the Content-Type, most (all?) browsers will not render 

gcetusic

import xmldataset
import pandas as pd
import re
import os
from datetime import datetime

# TODO: make this dynamic in the script that iterates over files in folders
input_file = 'Downloads/zade_30_cat_20180306_000530.xml'
account = '1009'
#################

gcetusic

from collections import defaultdict

def toposort(graph):
    """http://code.activestate.com/recipes/578272-topological-sort/
    
    Dependencies are expressed as a dictionary whose keys are items
and whose values are a set of dependent items. Output is a list of
sets in topological order. The first set consists of items with no
dependences, each subsequent set consists of items that depend upon
items in the preceeding sets.

gcetusic

One-line Tree in Python

Using Python's built-in defaultdict we can easily define a tree data structure:

def tree(): return defaultdict(tree)

That's it!

gcetusic

# coding: utf-8

from weasyprint import HTML, CSS


def get_page_body(boxes):
    for box in boxes:
        if box.element_tag == 'body':
            return box