adrianshort

# Extract URLs from a web page to a CSV file
# $ python extract-urls.py http://mysite.com/mypage.html myfile.csv
# By Adrian Short 6 Sep 2012
  
import sys
import urllib
import csv
from bs4 import BeautifulSoup

url = sys.argv.pop(1)

adrianshort

# Scrape webpage into a podcast RSS feed
# https://www.sutton.gov.uk/index.aspx?articleid=4332

require 'nokogiri'
require 'open-uri'
require 'time'
require 'pp'

FEED_TITLE = "Cheam North and Worcester Park Local Committee"
FEED_IMAGE = "https://dl.dropbox.com/u/300783/logo.png"

adrianshort

require 'csv'
require 'pp'
require 'erb'
require 'time'

# https://gist.github.com/adrianshort/5547284
# $ ruby csv2georss.rb myfile.csv > feed.xml

template = ERB.new <<-EOF
<?xml version="1.0" encoding="UTF-8" ?>

adrianshort

# D'Hondt method calculations
# https://en.wikipedia.org/wiki/D'Hondt_method
# By Adrian Short (@adrianshort) 26 May 2014

# European Parliament election, London region, 22 May 2014

@parties = {
  '4 Freedoms Party (UK EPP)' =>              28014,
  'An Independence from Europe' =>            26675,
  'Animal Welfare Party' =>                   21092,

adrianshort

====== @!!PAGE@ ======

**@!!PAGE@** is 

===== External links =====

  * [[http://www.example.com/|Official website]]
  * [[wp>@!!PAGE@]]

{{tag>tag1 tag2 "tag3 with spaces"}}

adrianshort

# Convert Jekyll blog posts to DokuWiki pages
# Adrian Short (https://adrianshort.org/) 15 Feb 2015

require 'fileutils'
require 'yaml'
require 'pp'
require 'pandoc-ruby'

INPUT_DIR = "./_posts"
OUTPUT_BASEDIR = "./blog"

adrianshort

#!/usr/bin/env sh

# Download PDF files for a planning application from Sutton Council planning website
# If you run this more than once it'll only download the new files uploaded for that application.
# Usage: $ get.sh <application number>, e.g. $ get.sh B2015/71962
# Install curl and wget before use. Mac users can install them with Homebrew.
# Windows users: Try running this in Cygwin or install Linux in a virtual machine.
# Adrian Short 26 Feb 2016

COOKIEJAR=cookiejar.txt

adrianshort

require 'uk_planning_scraper'
require 'csv'

apps = UKPlanningScraper::Authority.named('Aberdeen').scrape({ validated_days: 200, keywords: 'bt phone kiosk'})
puts "#{apps.size} applications scraped."

CSV.open("aberdeen.csv", "w") do |csv|
  csv << apps.first.keys # header row
  apps.each { |app| csv << app.values }
end