nishad

# Given a list of words, remove any that are
# in a list of stop words.

def removeStopwords(wordlist, stopwords):
    return [w for w in wordlist if w not in stopwords]

nishad

export JENA_FUSEKI_VERSION=3.7.0

export JENA_HOME=~/opt/apache-$JENA_FUSEKI_VERSION
export FUSEKI_HOME=~/opt/apache-jena-fuseki-$JENA_FUSEKI_VERSION
export FUSEKI_BASE=~/opt/apache-jena-fuseki-$JENA_FUSEKI_VERSION
export JENA_BASE=~/opt/apache-jena-$JENA_FUSEKI_VERSION
export JENA=~/opt/apache-jena-$JENA_FUSEKI_VERSION
export FUSEKI=~/opt/apache-jena-$JENA_FUSEKI_VERSION
export FUSEKIROOT=~/opt/apache-jena-fuseki-$JENA_FUSEKI_VERSION
export JENAROOT=~/opt/apache-jena-$JENA_FUSEKI_VERSION

nishad

import requests
from bs4 import BeautifulSoup

# We've now imported the two packages that will do the heavy lifting
# for us, reqeusts and BeautifulSoup

# Let's put the URL of the page we want to scrape in a variable
# so that our code down below can be a little cleaner
url_to_scrape = 'http://apps2.polkcountyiowa.gov/inmatesontheweb/'

nishad

<nav id="access">
    <ul class="menu">
        <li><a href="#">Home</a></li>
        <li><a href="#">Page 1</a>
            <ul class="sub-menu">
                <li><a href="#">Page 1.1</a></li>
                <li><a href="#">Page 1.2</a></li>
                <li><a href="#">Page 1.3</a></li>
                <li><a href="#">Page 1.4</a></li>
                <li><a href="#">Page 1.5</a></li>

nishad

#!/usr/bin/env python
# encoding: utf-8
"""
csv2xml.py

Created by Justin van Wees on 2011-04-18.
"""
import sys
import os
import string

nishad

#!/bin/bash
time_stamp=$(date +%Y-%m-%d)
mkdir -p ~/Backup/Downloads/$time_stamp
mv ~/Downloads/* ~/Backup/Downloads/$time_stamp

nishad

#!/bin/bash
time_stamp=$(date +%Y%m%d)
mkdir -p ~/Backup/Desktop/$time_stamp
mv ~/Desktop/* ~/Backup/Desktop/$time_stamp

nishad

nishad

Use wget to mirror a single page and its visible dependencies (images, styles)

Graphic via State of Florida CFO Vendor Payment Search (flair.myfloridacfo.com)

This is a quick command I use to snapshot webpages that have a fun image I want to keep for my own collection of WTFViz. Why not just right-click and save the image? Oftentimes, the webpage in which the image is embedded contains necessary context, such as captions and links to important documentation just incase you forget what exactly that fun graphic was trying to explain.

nishad

#!/bin/bash

git-random(){ gitRan=$(curl -L -s http://whatthecommit.com/ |grep -A 1 "\"c" |tail -1 |sed  's/<p>//'); git commit -S -m "$gitRan"; }

if [ -z "$1" ]; then
    	git add --all .
	git-random
else
    	git add --all .
	git commit -S -m "$*"