stats_file=~/specworkload-january.txt
cd /srv/launchpad.net-logs/production
zgrep specworkload */launchpad-access[0-9]*.log-201201* > $stats_file
# 33319 requests!

bots_re="(Googlebot|YandexBot|Speedy Spider|AhrefsBot|bingbot|\
Google Web Preview|Baiduspider|Sogou web spider|Exabot|YodaoBot|\
yacybot|suggybot)"
egrep -v "$bots_re" $stats_file
# Only 336 requests after excluding the ones from bots

# The first grep at the top actually include the requests that had
# +specworkload as the referrer as well, so we need to exclude them.
egrep "GET /~[^/]*/(\+|%20)specworkload"

# If we also exclude those made by gogle appengine apps, it goes down to 261.
grep -vi appengine-google

# 146 of those came from a google search, and most of them didn't seem to be
# searching for anyone's specworkload page
grep  www.google | grep "q=[^&\"]*"
# q=blueprints+playstation+3
# q=asus%20blueprint
# q=xylo%20blue%20print
# q=arduino%20blueprints
# q=list%20of%20android%20based%20projects
# q=rpmsg%20presentation%20elc
# q=blueprint%20of%20a%20modem
# q=blueprint%20imac

# Out of the remaining 115 requests, only 25 have a referrer (23 of those are
# under blueprints.lp.net). And those are for 44 distinct pages.
grep -o "~[a-z]*/+specworkload" | sort | uniq
# ~aballester/+specworkload
# ~alvarojusten/+specworkload
# ~andypiperuk/+specworkload
# ~angelicaisabelb/+specworkload
# ~apetresc/+specworkload
# ~awijit/+specworkload
# ~brantcgardner/+specworkload
# ~cgalisteo/+specworkload
# ~dashohoxha/+specworkload
# ~dberhane/+specworkload
# ~edrews/+specworkload
# ~elqanah/+specworkload
# ~gbutters/+specworkload
# ~gersonchicareli/+specworkload
# ~gldrayton/+specworkload
# ~golisp/+specworkload
# ~ichaudhry/+specworkload
# ~ishanarora/+specworkload
# ~jchapoulie/+specworkload
# ~joojooclub/+specworkload
# ~kamalmostafa/+specworkload
# ~kjoller/+specworkload
# ~kristovizer/+specworkload
# ~libdjconsole/+specworkload
# ~linaro/+specworkload
# ~maister/+specworkload
# ~makkus/+specworkload
# ~mdm/+specworkload
# ~metafly/+specworkload
# ~mojtabanow/+specworkload
# ~nelis/+specworkload
# ~nephelyn/+specworkload
# ~paracha/+specworkload
# ~pbolgar/+specworkload
# ~rajaiskandars/+specworkload
# ~rrebanks/+specworkload
# ~saif/+specworkload
# ~slaeyer/+specworkload
# ~snowplow/+specworkload
# ~sputnick/+specworkload
# ~steabert/+specworkload
# ~stk/+specworkload
# ~svennhg/+specworkload
# ~theosib/+specworkload
# ~tramchamploo/+specworkload
# ~transmissionbt/+specworkload
# ~tzm/+specworkload
# ~ubuland/+specworkload
# ~vendicator/+specworkload
# ~victorgmz/+specworkload
# ~wanderingalbatross/+specworkload