Dylan Kinnett dylan-k

When I'm working with my growing collection of text files, I find some of these regular expressions to be useful.

See also:

Strip a Tag, and its contents, include linebreaks

	#!/bin/bash
	#
	# Crawls a domain
	# Retreives all visible URLs and their page titles
	# Saves to CSV
	# $1 = URL
	# $2 = csv filename
	#
	# USAGE:
	# save this script as, say, crawler.sh”.

	#!/usr/bin/env python
	import json
	import sys

	# See https://msdn.microsoft.com/en-us/library/aa753582%28VS.85%29.aspx
	# and https://github.com/shaarli/Shaarli/blob/v0.6.5/index.php#L1899
	HEADER = u'<!DOCTYPE NETSCAPE-Bookmark-file-1><DL>'
	FOOTER = u'</DL>'
	ITEM = u'<DT><A HREF="{url}" ADD_DATE="{time_created}" TAGS="{tags}">{title}</A>'

	import os, sys, re

	patterns = [
	# <img src='http://s.wordpress.com/latex.php?latex=%5Cmathcal%7BO%7D%28n%29&bg=T&fg=000000&s=0' alt='\mathcal{O}(n)' title='\mathcal{O}(n)' class='latex' />
	(r'<img.?title=\'(.?)\' class=\'latex\' />',
	'$$ \\1 $$ ',
	0),

	# [<img class=" size-full wp-image-1722 aligncenter" src="http://erikbern.com/wp-content/uploads/2016/01/avg.png" alt="avg" width="512" height="512" />](http://erikbern.com/wp-content/uploads/2016/01/avg.png)
	(r'\[(<img.?)\]\(.?\)',

	<?php

	function my_find_expired_events( $ids ) {

	$args = array(
	'post_type' => 'tribe_events',
	'nopaging' => true,
	'fields' => 'ids',
	'meta_query' => array(
	array(

	#!/bin/bash

	if [[ ! "${#}" == 2 ]] ; then
	echo "Please provide input and output directories, and no other arguments."
	exit 1
	fi

	input="${1}"
	output="${2}"

	<?php

	/*******************************
	* this will work in the loop
	*******************************/
	/* check if the posts publish date is older than 60 days */
	if( strtotime( $post->post_date ) < strtotime('-60 days') ) {

	/* post is older than 60 days - do something with it!! */

	#!/usr/bin/ruby
	# SIFTTTER 1.5: An IFTTT-to-Day One Logger by Craig Eley 2014 <http://craigeley.com>
	# Based on tp-dailylog.rb by Brett Terpstra 2012 <http://brettterpstra.com>
	# Multiple Date Function by Paul Hayes 2014 <http://paulrhayes.com>
	#
	# Notes:
	# * Uses `mdfind` to locate a specific folder of IFTTT-generated text files changed in the last day
	# * The location of your folder should be hardcoded in line 67, and the location of your Day One in line 66
	# * Scans leading timestamps in each line matching the selected dates
	# * Does not alter text files in any way