Patrick Lemiuex reduxdj

reduxdj / pandora_jar.js

Created November 15, 2011 16:57

Pandora ad hacker bookermarklet

	/*
	* Pandora has changed their dom recently and also did some insidious things
	* like trying to check to see if the ads are in the body or playback occasionally
	* stops at which you have to reload the page because of some random interval
	* checking pandora does, although playback is resumed from the current point, thanks
	* to Pandora. This doesn't happen very often, and I am working on a better fix for that.
	*
	* It's a total cat and mouse game, but I'll update the code regularly,
	* so use at your own risk...
	*

reduxdj / using e regex and some parsing for top-level domains

Created April 24, 2011 01:43

Here's a simple function that parses out urls in text

	import re
	def parse_content_for_url(content):
	reg = '([a-zA-Z0-9._%-]+)\.(ZW\|AC\|AD\|AE\|AERO\|AF\|AG\|AI\|AL\|AM\|AN\|AO\|AQ\|AR\|ARPA\|AS\|ASIA\|AT\|AU\|AW\|AX\|AZ\|BA\|BB\|BD\|BE\|BF\|BG\|BH\|BI\|BIZ\|BJ\|BM\|BN\|BO\|BR\|BS\|BT\|BV\|BW\|BY\|BZ\|CA\|CAT\|CC\|CD\|CF\|CG\|CH\|CI\|CK\|CL\|CM\|CN\|CO\|COM\|COOP\|CR\|CU\|CV\|CX\|CY\|CZ\|DE\|DJ\|DK\|DM\|DO\|DZ\|EC\|EDU\|EE\|EG\|ER\|ES\|ET\|EU\|FI\|FJ\|FK\|FM\|FO\|FR\|GA\|GB\|GD\|GE\|GF\|GG\|GH\|GI\|GL\|GM\|GN\|GOV\|GP\|GQ\|GR\|GS\|GT\|GU\|GW\|GY\|HK\|HM\|HN\|HR\|HT\|HU\|ID\|IE\|IL\|IM\|IN\|INFO\|INT\|IO\|IQ\|IR\|IS\|IT\|JE\|JM\|JO\|JOBS\|JP\|KE\|KG\|KH\|KI\|KM\|KN\|KP\|KR\|KW\|KY\|KZ\|LA\|LB\|LC\|LI\|LK\|LR\|LS\|LT\|LU\|LV\|LY\|MA\|MC\|MD\|ME\|MG\|MH\|MIL\|MK\|ML\|MM\|MN\|MO\|MOBI\|MP\|MQ\|MR\|MS\|MT\|MU\|MUSEUM\|MV\|MW\|MX\|MY\|MZ\|NA\|NAME\|NC\|NE\|NET\|NF\|NG\|NI\|NL\|NO\|NP\|NR\|NU\|NZ\|OM\|ORG\|PA\|PE\|PF\|PG\|PH\|PK\|PL\|PM\|PN\|PR\|PRO\|PS\|PT\|PW\|PY\|QA\|RE\|RO\|RS\|RU\|RW\|SA\|SB\|SC\|SD\|SE\|SG\|SH\|SI\|SJ\|SK\|SL\|SM\|SN\|SO\|SR\|ST\|SU\|SV\|SY\|SZ\|TC\|TD\|TEL\|TF\|TG\|TH\|TJ\|TK\|TL\|TM\|TN\|TO\|TP\|TR\|TRAVEL\|TT\|TV\|TW\|TZ\|UA\|UG\|UK\|US\|UY\|UZ\|VA\|VC\|VE\|VG\|VI\|VN\|VU\|WF\|WS\|XN\|XXX\|YE\|YT\|ZA\|ZM\|ZW)?'
	li = re.findall(reg,content)
	left_index = 0
	inc = 0
	for item in li:
	l

reduxdj / craiglist_scraper.py

Created April 17, 2011 02:38

Scrapes a Craisglist posting and returns an object with what it can find

	"""
	scrape_craigslist.py
	requires libxml and BeautifulSoup

	Created by Patrick Lemiuex on 2011-04-12.
	MIT Open Source License
	Copyright (c) 2009-2010 the original author or authors

	Permission is hereby granted, free of charge, to any person obtaining a
	copy of this software and associated documentation files (the "Software"),