# 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: https://www.teflexpress.co.uk//robots.txt
# Ignored: http://www.teflexpress.co.uk//robots.txt

# Website Sitemap
Sitemap: https://www.teflexpress.co.uk/sitemap

# Crawlers Setup
User-agent: *
Disallow: /CVS
Disallow: /*.svn$
Disallow: /*.idea$
Disallow: /*.sql$
Disallow: /*.tgz$

## Do not crawl links with session location
Disallow: /*?location=

Disallow: /uploads/
Disallow: /userImages/
Disallow: /images/
Disallow: /images1/
Disallow: /images_new/
Disallow: /includes/
Disallow: /includes_new/
Disallow: /is-integration/
Disallow: /js/
Disallow: /noname_config/
Disallow: /paypal/
Disallow: /pdf-cert/
Disallow: /promos/
Disallow: /promotions/
Disallow: /revealpopup/
Disallow: /taskImages/
Disallow: /.well-known/
Disallow: /__jrjlog/
Disallow: /TeflCambridge_cert/
Disallow: /Scripts/
Disallow: /admin/
Disallow: /cambridgeAdminMyPHP/
Disallow: /cgi-bin/
Disallow: /config/
Disallow: /courseIcons/
Disallow: /css/
Disallow: /css1/
Disallow: /data/
Disallow: /demo/
Disallow: /designtemplate/
Disallow: /dev/
Disallow: /font/
Disallow: /fpdf/
Disallow: /helps/
Disallow: /EF-Reports/
Disallow: /Mail-1.2.0/
Disallow: /Newsletters/
Disallow: /PHPExcel/
Disallow: /TEFLNCM_new/
Disallow: /TEFL_DB/
Disallow: /accredited-tefl-courses/
Disallow: /admin-old/
Disallow: /blog/
Disallow: /blog-old/
Disallow: /bugtracker/
Disallow: /captcha/
Disallow: /companyLogo/
Disallow: /controllers/
Disallow: /courseIcons/
Disallow: /course_images/
Disallow: /cron-jobs/
Disallow: /cspu/
Disallow: /db-restore-lv/
Disallow: /dump/
Disallow: /eleexpres/
Disallow: /email_signature/
Disallow: /email_template/
Disallow: /flash/
Disallow: /fpdf/
Disallow: /htm5videocompatibility/
Disallow: /i-to-itesol.com/
Disallow: /is-integration-te/
Disallow: /jplayer/
Disallow: /js1/
Disallow: /landing.teflexpress.co.uk/
Disallow: /libs/
Disallow: /mailfiles/
Disallow: /pdf-cert/
Disallow: /pdf-transcript/
Disallow: /pdfs/
Disallow: /picture_library/
Disallow: /player/
Disallow: /plesk-stat/
Disallow: /podcast/
Disallow: /practicum-integrated-course/
Disallow: /prettyphoto/
Disallow: /q76RIO9NphpMyAdmin/
Disallow: /res/
Disallow: /restore/
Disallow: /skin/
Disallow: /sql/
Disallow: /tcpdf/
Disallow: /te/
Disallow: /te-newhome/
Disallow: /teaching-english-to-young-learners/
Disallow: /tefl-dbaccess/
Disallow: /teflexpr_wblog/
Disallow: /teflexpress.co.uk/
Disallow: /teflexpressinternational/
Disallow: /teflnewsletter/
Disallow: /tesolexpressonline/
Disallow: /test/
Disallow: /vc-demo/
Disallow: /vci/
Disallow: /video/
Disallow: /vtigercrm/
Disallow: /webinar_help_downloads/
Disallow: /webinar_resources/
Disallow: /wiziq-test-api/
Disallow: /wiziq_download_record/
Disallow: /wiziqapi/

Disallow:/podcast/
Disallow: /newversion/
Disallow: /shop.php?*
Disallow: /online_enroll1_com.php?*
Disallow: /ContactEnquire.php*
Disallow: /*.swf
Disallow: /enroll1.php?*
Disallow: /weekendCourse_reg.php?*
Disallow: /jobsapply/
Disallow: /requestCallback.php
Disallow: /OnlineCourses-*
Disallow: /coursePageAudioPlay.php*
Disallow: /maintenance.html
Disallow: /index.php?succ=1  
Disallow: /logoutUser.php  
Disallow: /JobsAll-*
Disallow: /forgotPasswd.php
Disallow: /grammarpdf_enroll.php
Disallow: /lessonplanning_enroll.php
Disallow: /podcast/wp-content/	
Disallow: /podcast/wp-admin/ 	
Disallow: /podcast/wp-includes/ 
Disallow: /podcast/page/*
Disallow: /blog/wp-admin/ 	
Disallow: /Shop-*
Disallow: /efstudents
Disallow: /online-tefl-course-new/*
Disallow: /dev
Disallow: /accredited-tefl-courses/tefl-courses-description-EE.php
Allow: /wp-admin/admin-ajax.php


# Some bots are known to be trouble, particularly those designed to copy
# entire sites or download them for offline viewing. 
#
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: /

# Xenu Crawler
User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

# W3C Crawler
User-agent: libwww
Disallow: /

# LookSmart Crawler
User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: Nutch
Disallow: /

User-agent: spock
Disallow: /

User-agent: OmniExplorer_Bot
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: BecomeBot
Disallow: /

User-agent: genieBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: MLBot
Disallow: /

User-agent: 80bot
Disallow: /

User-agent: Linguee Bot
Disallow: /

User-agent: aiHitBot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: SBIder/Nutch
Disallow: /

User-agent: SBIder
Disallow: /


User-agent: Jyxobot
Disallow: /

User-agent: mAgent
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Speedy Spider
Disallow: /

User-agent: ShopWiki
Disallow: /

User-agent: Huasai
Disallow: /

User-agent: DataCha0s
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: Atomic_Email_Hunter
Disallow: /

User-agent: Mp3Bot
Disallow: /

User-agent: WinHttp
Disallow: /

User-agent: betaBot
Disallow: /

User-agent: core-project
Disallow: /

User-agent: panscient.com
Disallow: /

User-agent: Java
Disallow: /

User-agent: libwww-perl
Disallow: /


User-agent: wget
Disallow: /

User-agent: grub-client
Disallow: /

User-agent: k2spider
Disallow: /

# Hits many times per second, not acceptable

User-agent: NPBot
Disallow: /

User-agent: Microsoft.URL.Control
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: /

User-agent: Twiceler
Disallow: /


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