#
# Peteris Krumins (peter@catonmat.net), 2007.09.08
# http://www.catonmat.net  -  good coders code, great reuse
#
# Scraper pattern file for picurls.com website
# 
# The format of the file is the following:
# [url:|title:|desc:] regex pattern
#
# url:, title:, desc: are optional. they specify if the entry
# on a website should be matched against its url, title or description.
#
# if url:, title:, desc: are not specified, it defaults to matching
# pattern against title and description.
#

# match picture urls
#
url: \.jpg$
url: \.gif$
url: \.png$

# match common patterns describing posts having pictures in them
#
[[(].*picture.*[])]
[[(].*pic.*[])]
[[(].*image.*[])]
[[(].*photo.*[])]
[[(].*comic.*[])]
[[(].*chart.*[])]
[[(].*graph.*[])]

photos? of
pics? of
images? of
pictures? of
comics? of
charts? of
graphs? of
grapics? of
(this|these|those) photos?
(this|these|those) pics?
(this|these|those) images?
photosets? (on|of)

# match domains containing just pics
url: xkcd\.com
url: flickr\.com
url: photobucket\.com
url: imageshack\.us
url: bestpicever\.com

