# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html User-agent: * # CSS, JS, Images Allow: /core/*.css$ Allow: /core/*.css? Allow: /core/*.js$ Allow: /core/*.js? Allow: /core/*.gif Allow: /core/*.jpg Allow: /core/*.jpeg Allow: /core/*.png Allow: /core/*.svg Allow: /profiles/*.css$ Allow: /profiles/*.css? Allow: /profiles/*.js$ Allow: /profiles/*.js? Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /profiles/*.svg # Directories Disallow: /core/ Disallow: /profiles/ # Files Disallow: /README.md Disallow: /composer/Metapackage/README.txt Disallow: /composer/Plugin/ProjectMessage/README.md Disallow: /composer/Plugin/Scaffold/README.md Disallow: /composer/Plugin/VendorHardening/README.txt Disallow: /composer/Template/README.txt Disallow: /modules/README.txt Disallow: /sites/README.txt Disallow: /themes/README.txt Disallow: /web.config # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips Disallow: /node/add/ Disallow: /search/ Disallow: /user/register Disallow: /user/password Disallow: /user/login Disallow: /user/logout Disallow: /media/oembed Disallow: /*/media/oembed # Paths (no clean URLs) Disallow: /index.php/admin/ Disallow: /index.php/comment/reply/ Disallow: /index.php/filter/tips Disallow: /index.php/node/add/ Disallow: /index.php/search/ Disallow: /index.php/user/password Disallow: /index.php/user/register Disallow: /index.php/user/login Disallow: /index.php/user/logout Disallow: /index.php/media/oembed Disallow: /index.php/*/media/oembed #Penn College Crawl-delay: 10 Disallow: /student-life/orientation/welcome-weekend/ Disallow: /admissions/scholarships/penn-college-scholarship Disallow: /node/ Disallow: /r/ Disallow: /catalog/ Disallow: /email/ Disallow: /academics/career-services/career-fair/ Disallow: /academics/career-services/career-fair/directory Disallow: /academics/career-services/career-fair/register Disallow: /search Disallow: /search/ Disallow: /webform/ Disallow: /academicaffairs/ Disallow: /academicsuccess/ Disallow: /admissions_email/ Disallow: /admin/ Disallow: /advertising/ Disallow: /advidement/ Disallow: /armyROTC/ Disallow: /ARP/ Disallow: /artcamp/ Disallow: /askpenncolleg/ Disallow: /ASPIE2016/ Disallow: /assessment/ Disallow: /athletetraining/ Disallow: /athletics/ Disallow: /bcards/ Disallow: /bursar/ Disallow: /busind/ Disallow: /businesscamp/ Disallow: /careerservices/ Disallow: /catalog/majors/GSP.shtml Disallow: /childcare/ Disallow: /closetohome/ Disallow: /collegehealth/ Disallow: /commencement/ Disallow: /facilitiesandevents/ Disallow: /consumerinfo/ Disallow: /contact/ Disallow: /counseling/ Disallow: /ctm-employee-discount-program Disallow: /currentstudents/ Disallow: /degrees/ Disallow: /degreesthatwork/ Disallow: /digitalcamp/ Disallow: /dining/ Disallow: /disabilityservices/ Disallow: /distance/ Disallow: /ecards/ Disallow: /emergencyResponse/ Disallow: /esl/ Disallow: /etec/ Disallow: /explore/ Disallow: /finaid/ Disallow: /firstyear/ Disallow: /fitness/ Disallow: /foodcamp/ Disallow: /futurestudents/ Disallow: /giving/ Disallow: /glbt/ Disallow: /governance/ Disallow: /green/ Disallow: /healthcamp/ Disallow: /holidaycard/ Disallow: /homecoming/ Disallow: /homeimages/ Disallow: /hospitalityservices/ Disallow: /humanresources/ Disallow: /ia/ Disallow: /international/ Disallow: /intramurals/ Disallow: /its/ Disallow: /iwanttobe/ Disallow: /jobsatpenncollege/ Disallow: /k12/admin/ Disallow: /k12educators/ Disallow: /library/ Disallow: /nacat/ Disallow: /naturalgas/ Disallow: /newHire/ Disallow: /nssc/ Disallow: /och/ Disallow: /offcampus/ Disallow: /oh2015/ Disallow: /oit/ Disallow: /openhouse/ Disallow: /orientation/ Disallow: /pctoday/ Disallow: /photos/ Disallow: /picnic/ Disallow: /pirc/ Disallow: /police/ Disallow: /president/ Disallow: /privacy/ Disallow: /prm/ Disallow: /profile/ Disallow: /psn/ Disallow: /r/ Disallow: /registrar/ Disallow: /requestinfo/ Disallow: /reslife/ Disallow: /rmce/ Disallow: /scholarships/ Disallow: /schools/ Disallow: /scripts/ Disallow: /share/ Disallow: /sis/ Disallow: /smartgirls/ Disallow: /sonsofitaly/ Disallow: /spring/ Disallow: /studentactivities/ Disallow: /studentaffairs/ Disallow: /studentblog/ Disallow: /studentpolicy/ Disallow: /styles/ Disallow: /sunnyportal/ Disallow: /surplus/ Disallow: /testcenter/ Disallow: /tparticulation/ Disallow: /trail/ Disallow: /transferstudents/ Disallow: /victorianhouse/ Disallow: /videos/ Disallow: /visit/ Disallow: /wdce/ Disallow: /wtc/ Disallow: /files/imported/ Disallow: /admissions/financial-aid/scholarships/penn-college-scholarships Disallow: /chef Disallow: /cgi-bin/ Disallow: /files/cgi-bin/ #Bots User-agent: SemrushBot Disallow: / User-agent: SemrushBot-SA Disallow: / User-agent: SemrushBot-SI Disallow: /