Sitemap: http://www.hark.com/sitemaps/sitemap_index.xml.gz
User-agent: *
Disallow: /a/
Disallow: /at/
Disallow: /cgi-bin/
Disallow: /doubleclick/
Disallow: /_vti_bin/
Disallow: /users/
Disallow: /admin/
Disallow: /edit/
Disallow: /svndirs/
Disallow: /clips/embed_code/
Disallow: /clips/send_to_friend/
Disallow: /clips/inline_like_it/
Disallow: /original.txt
Disallow: /clips/versions/
Disallow: /clips.rss
Disallow: /collections/embed_code/
Disallow: /collections/facebook/
Disallow: /collections/tweet/
Disallow: /collections/versions/
Disallow: /tshirts/
Disallow: *clipped=false
Disallow: /*/download
Disallow: /*/execute_download
Disallow: /*?collection_id
Disallow: /video
Disallow: /alphabird
Disallow: /*/homepage_embed*

# Takedown Request
# Amie Lowhorn
Disallow: /users/351076

# WordPress Blog
Disallow: /blog/wp-content/plugins/
Disallow: /blog/wp-includes/
Disallow: /blog/wp-admin/

# Use robots.txt to prevent crawling of search results pages or other auto-generated pages that don't add much value for users coming from search engines.
# Block keywords params pages as well, as these are both search pages and returns soft-404s for empty searches.
# http://www.google.com/support/webmasters/bin/answer.py?answer=35769
Disallow: /search
Disallow: *keywords=

# 100,000s of links are being generated by things that haven't been identified:
#   http://www.hark.com/0VMHgSm 5wr/bVH /6Uk2laiRbJycjkhzk2tczalPA=
#   http://www.hark.com/clips/tpjpjqjbwn-fiesta-beat?iframe=true&width=80%&height=80%
Disallow: /*=$
Disallow: /*%$

# Don't download or cache json files or really old json files.
Disallow: /*.json
Disallow: /*.query