User-agent: *
Disallow: 

#
# we took this robots.txt from http://www.wikipedia.org/ and friends
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#

#######BINGBOT TEST AREA
User-Agent: bingbot
Allow: /$
Allow: /contest/
Allow: /contests/
Disallow: /
#######END BINGBOT TEST AREA

# FatBot 2.0; http://www.thefind.com/crawler
User-agent: FatBot*
Disallow: /

User-agent: istellabot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: AhrefsBot 
Disallow: /

User-agent: Clickagy Intelligence Bot v2
Disallow: /

User-agent: MauiBot
Disallow: /

# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Wikipedia work bots:
User-agent: IsraBot
Disallow:

User-agent: Orthogaffe
Disallow:

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /

# Don't allow the wayback-maschine to index user-pages
#User-agent: ia_archiver
#Disallow: /wiki/User
#Disallow: /wiki/Benutzer

#
# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
# Inktomi's "Slurp" can read a minimum delay between hits; if your
# bot supports such a thing using the 'Crawl-delay' or another
# instruction, please let us know.
#
# There is a special exception for API mobileview to allow dynamic
# mobile web & app views to load section content.
# These views aren't HTTP-cached but use parser cache aggressively
# and don't expose special: pages etc.
#

########## ADDED BY SCOTT ##########
User-agent: *
Crawl-delay: 1
Disallow: /*MemcacheServiceApiHelper
Disallow: /canvas/checkout*
# feed /story/show/6105326004994048
Disallow: /story/show*
# comment json /comment/image/5058729783590912
Disallow: /comment/image*
Sitemap: http://www.pixoto.com/sitemap-index.xml

# Image Detail PAGES
Disallow: /images-*/*/*/*/imageduel-history

# PROFILE PAGES 
Disallow: /*/awards
Disallow: /*/recent
Disallow: /*/favorites
Disallow: /*/following
Disallow: /*/followers
# END PROFILE PAGES 

Disallow: /awards/*
Disallow: /art-shop/*

# Json urls
Disallow: /*?json=true
# Time leaderboards
# /images-*/nudes-and-boudoir/all/leading/in-july-2015/page-72
Disallow: /images-*/*/*/*/*/in-*/page-*
# Country Leaderboard pages /images-*/people/portraits-of-women/leading/PK/in-all/page-9?
Disallow: /images-*/*/*/*/*/*/in-*/page-*
# /images-photography/all/all/leading/in-all
# /images-photography/all/all/leading/in-july-2016
# /images-photography/all/all/leading/on-08-10-2016
# /images-photography/all/all/leading/afghanistan/in-year-2016
# /images-photography/all/all/leading/united-states/california/huntington-beach/in-year-2016
Disallow: /images-*/*/*/*/on-*
Disallow: /images-*/*/*/*/*/on-*
Disallow: /images-*/*/*/*/*/*/on-*
Disallow: /images-*/*/*/*/*/*/*/on-*
Disallow: /images-*/*/*/*/in-week-*
Disallow: /images-*/*/*/*/*/in-week-*
Disallow: /images-*/*/*/*/*/*/in-week-*
Disallow: /images-*/*/*/*/*/*/*/in-week-*

Disallow: /players-*/*/leading/in-week-*
Disallow: /players-*/*/leading/*/in-week-*
Disallow: /players-*/*/leading/*/*/in-week-*
Disallow: /players-*/*/leading/*/*/*/in-week-*

Disallow: /stock/leading?search=tags*

# Disallow: /images-*/*/*/*/in-*
# Allow: /images-*/*/*/*/in-all
# Old?
Disallow: /images-*/*/*/leading/
#### PROTECTED URLS THAT WE DONT WANT CRAWL ATTEMPTS ######
Disallow: /images-*/*/*/*/imageduel-history
############ END ROBOT CODE HERE #############

User-agent: Googlebot-Image
Disallow: /*-c$

User-agent: AhrefsBot
Disallow: /images-*/*/*/leading/*
Disallow: /players-*/*/leading/*
Crawl-Delay: 30