Research-Stack/2-Search-Space/search/stract/scripts/blogroll_optic.py

342 lines
8.1 KiB
Python
Vendored

#!.venv/bin/python3
# blogs from https://blogroll.org/
blogroll_org = [
'50watts.com',
'davidrevoy.com',
'blog.lostartpress.com',
'austinkleon.com',
'gwennseemel.com',
'steve-best.github.io',
'lizclimo.tumblr.com',
'johnpweiss.com',
'theschoolofthetransferofenergy.com',
'lucybellwood.com',
'fullmoonfiberart.com',
'davidffisher.com',
'theusedlife.com',
'ganzeer.today',
'veronique.ink',
'shiftinglight.com',
'zettl.blog',
'cmhb.de',
'radicalcut.blogspot.com',
'cultrface.co.uk',
'pluralistic.net',
'siderea.dreamwidth.org',
'hermitary.com',
'alittlebitofrest.com',
'rasterweb.net',
'derekkedziora.com',
'tracydurnell.com',
'jpkoning.blogspot.com',
'marginalrevolution.com',
'bfoliver.com',
'stephenfollows.com',
'davidbordwell.net',
'lichvanwinkle.blogspot.com',
'silverscreenings.org',
'brickexperimentchannel.wordpress.com',
'jamesg.blog',
'widowbadass.com',
'appellationbeer.com',
'awhiskandaspoon.com',
'foodandwineaesthetics.com',
'baileysbeerblog.blogspot.com',
'silviamaggidesign.com',
'interconnected.org',
'colly.com',
'ruk.ca',
'typeoff.de',
'andy-bell.co.uk',
'davesmyth.com',
'going-medieval.com',
'goodoptics.wordpress.com',
'thesphinxblog.com',
'pepysdiary.com',
'scholars-stage.org',
'bookandsword.com',
'inthewilderness.net',
'bedlamfarm.com',
'granolashotgun.com',
'summerhillstead.wordpress.com',
'refarmer.ca',
'dreamvalleyfarmstead.com',
'hearthwilde.com',
'thedruidsgarden.com',
'urbannature.blog',
'lessthan1000followers.com',
'disquiet.com',
'hiphopisntdead.blogspot.com',
'theredhandfiles.com',
'impossiblesongs.blogspot.com',
'ethanhein.com',
'boffosocko.com',
'minutestomidnight.co.uk',
'simply.jenett.org',
'kottke.org',
'winnielim.org',
'jonathanwrotethis.wordpress.com',
'mariovillalobos.com',
'piperhaywood.com',
'manuelmoreale.com',
'cjchilvers.com',
'charliebleecker.com',
'om.co',
'rubenerd.com',
'lazybear.io',
'thisdaysportion.com',
'craigmod.com',
'exilelifestyle.com',
'kelake.org',
'beetleypete.com',
'cdevroe.com',
'kickscondor.com',
'brainbaking.com',
'thewrittenaddiction.com',
'mudkri.ca',
'cimple.life',
'chriscoyier.net',
'alirezahayati.com',
'danielsisson.com',
'musingsfromatangledmind.com',
'eli.li',
'bottledaux.com',
'inhab.it',
'campegg.com',
'xianblog.wordpress.com',
'findingcoopersvoice.com',
'adamenglebright.com',
'lucasdidthis.com',
'teachertomsblog.blogspot.com',
'hamneggs716.com',
'ritaottramstad.com',
'robert.winter.ink',
'velveteenrabbi.blogs.com',
'blog.tobiasrevell.com',
'maggiemcneill.com',
'anniemueller.com',
'oceanicwilderness.com',
'gilest.org',
'noisydeadlines.net',
'kwon.nyc',
'hyperborea.org',
'jon.bo',
'oh.mg',
'darice.org',
'lordmatt.co.uk',
'swistle.com',
'morrick.me',
'dylanharris.org',
'cubicgarden.com',
'scripting.com',
'nitinkhanna.com',
'47nil.com',
'autodidacts.io',
'verisimilitudes.net',
'joelchrono12.xyz',
'bruh.ltd',
'a.wholelottanothing.org',
'blog.rachelbinx.com',
'protesilaos.com',
'inthemargins.ca',
'log.kvl.me',
'jeffperry.me',
'cabel.com',
'takeonrules.com',
'bix.blog',
'timapple.com',
'ericwbailey.website',
'diasyrmus.com',
'popagandhi.com',
'theonlinephotographer.com',
'somewherein.jp',
'denisebushphoto.wordpress.com',
'atlasminor.com',
'aows.co',
'grahamsisland.com',
'charlenewinfred.com',
'thevisualchronicle.com',
'islandinthenet.com',
'seanbonner.com',
'astroanarchy.blogspot.com',
'75centralphotography.com',
'iancylkowski.com',
'davidduchemin.com',
'nicktaurojr.com',
'chuq.me',
'sidewayseye.net',
'tmichellemoore.com',
'joshwithers.blog',
'joevancleave.blogspot.com',
'photothunk.blogspot.com',
'steelsnowflake.org',
'scottnesbitt.online',
'whatever.scalzi.com',
'aworkinglibrary.com',
'themarginalian.org',
'hootreview.com',
'acorneredgurl.com',
'morningporch.com',
'wendyprattpoetry.com',
'jamierubin.net',
'karlcalagan.com',
'casualoptimist.com',
'mnmlscholar.com',
'williamgallagher.com',
'mavengame.com',
'transactionswithbeauty.com',
'kristybowen.blogspot.com',
'putah-creek.tumblr.com',
'kristinberkey-abbott.blogspot.com',
'renpowell.com',
'terriwindling.com',
'thenewleafjournal.com',
'steelthistles.blogspot.com',
'siamorweng.wordpress.com',
'florinpopa.blog',
'nancyfriedman.typepad.com',
'grammarphobia.com',
'shadycharacters.co.uk',
'rollofnickels.blogspot.com',
'appalachianground.com',
'writingball.blogspot.com',
'blindjournalist.wordpress.com',
'analogoffice.net',
'thepassivevoice.com',
'type-writer.org',
'sarahavenir.com',
'miskatonic.org',
'wellappointeddesk.com',
'backreaction.blogspot.com',
'ribbonfarm.com',
'overcomingbias.com',
'nintil.com',
'languagelog.ldc.upenn.edu',
'centauri-dreams.org',
'junkcharts.typepad.com',
'observationalepidemiology.blogspot.com',
'blog.nuclearsecrecy.com',
'skullsinthestars.com',
'statmodeling.stat.columbia.edu',
'profmattstrassler.com',
'harsimony.wordpress.com',
'dynomight.net',
'schwitzsplinters.blogspot.com',
'cyclostationary.blog',
'caseyhandmer.wordpress.com',
'werd.io',
'cheapskatesguide.org',
'kevq.uk',
'darknetdiaries.com',
'blog.thenewoil.org',
'ben-evans.com',
'chrishannah.me',
'daringfireball.net',
'blog.jim-nielsen.com',
'krebsonsecurity.com',
'blog.zedas.fr',
'baldurbjarnason.com',
'alirezahayati.com',
'flameeyes.blog',
'adactio.com',
'thecrow.uk',
'rachelbythebay.com',
'gregmorris.co.uk',
'numericcitizen.me',
'lkhrs.com',
'rusingh.com',
'duckrowing.com',
'zylstra.org',
'thenewsprint.co',
'bbbhltz.codeberg.page',
'andregarzia.com',
'jvt.me',
'roytang.net',
'blog.dshr.org',
'pxlnv.com',
'seirdy.one',
'zerokspot.com',
'miriamsuzanne.com',
'daverupert.com',
'vzqk50.com',
'drwho.virtadpt.net',
'jeffgeerling.com',
'raymondcamden.com',
'verisimilitudes.net',
'furbo.org',
'opensourcemusings.com',
'bt.ht',
'futurelawyer.typepad.com',
'marcthiele.com',
'heydingus.net',
'notes.ghed.in',
'simonwillison.net',
'david-smith.org',
'rodneybrooks.com',
'dansinker.com',
'theprivacydad.com',
'alongtheray.com',
'sinclairtrails.com',
'100r.co',
'adventuretaco.com',
'roadtothesea.com',
'walkingarizona.blogspot.com',
'mpmilestogo.site',
'rollingsteeltent.blogspot.com',
'geographicaljourneys.wordpress.com',
'rollingexistence.com',
'luxagraf.net',
'andrewskurka.com',
'notesfromtheroad.com',
'brewedjourney.blogspot.com',
'pedestrianobservations.com',
'nhgardensolutions.wordpress.com',
'capnaux.com',
'hikingdude.com',
'nomadonline.blog',
'wildmanlife.com',
]
# some blogs handpicked from hackernews
hackernews_blogs = [
'danluu.com',
'blog.acolyer.org',
'blog.samaltman.com',
'paulgraham.com',
'ciechanow.ski',
'antirez.com',
'jacquesmattheij.com',
'chris-granger.com',
'righto.com',
'troyhunt.com',
'susanrigetti.com',
'mtlynch.io',
'fabiensanglard.net',
'drewdevault.com',
'calpaterson.com',
'rachelbythebay.com',
'bellard.org',
'jvns.ca',
'tonsky.me',
'stephendiehl.com',
'words.steveklabnik.com',
'robert.ocallahan.org',
'blog.benjojo.co.uk',
'justine.lol',
'zachholman.com'
]
blogs = set(blogroll_org + hackernews_blogs)
optic = "DiscardNonMatching;\n"
for blog in blogs:
optic += f"""Rule {{
Matches {{
Site("|{blog}|")
}},
Action(Boost(0))
}};
"""
print(optic)