# cwjobs - last edited 15 December 2017 User-agent: * User-agent: Twitterbot allow: /*?WT.mc_id=* # allow aggregated jobs # 8/9/2017 Allow: /*?q*&page* # 2/11/2016 Disallow: /*==$ Disallow: /*.ashx$ # 25/08/2015 RD added to block facets on unified results Disallow: /*?page=1$ # don't index page=1 Disallow: /*&page=* # this is where there is a page parameter on a facited link - its a catch all Disallow: /*?WT.mc_id=* # stop aggregated jobs Disallow: /*&WT.mc_id=* # stop aggregated jobs Disallow: /*?similarjobsmodal=* Disallow: /*&similarjobsmodal=* #17/08/2016 Added by RD to block call backs Disallow: /jsd/ Disallow: /insidejob/wp-admin/ Disallow: */apply$ Disallow: */apply?* # 05/07/2016 Added by RD to block call backs - considered and decided to block! Disallow: /Login/ Disallow: /savedjobs Disallow: /personalisation Disallow: /*?CompanyId=* Disallow: /Accessible/ Disallow: /Authenticated/ Disallow: /cannedsearch/ Disallow: /CannedSearch/ Disallow: /CompanySearch/ Disallow: /JobSearch/JobBasket.aspx Disallow: /JobSearch/JobContactDetails.aspx Disallow: /JobSearch/JobPrinterFriendlyDetails.aspx Disallow: /JobSearch/jobs-on-a-map.aspx Disallow: /JobSearch/PromotedClick.aspx Disallow: /JobSearch/RSS.aspx Disallow: /JobSearch/SendToAFriend.aspx Disallow: /JobSearch/UnAuthApplyOnline.aspx Disallow: /JobSearch/PreExternalApplyOnline.aspx Disallow: /JobSearch/JobsByEmailSetup.aspx Disallow: /JobLink/ Disallow: /pgl/ Disallow: /pjb_ui/ Disallow: /WebServices/ Disallow: /Webservices/ Disallow: /Maintenance.aspx Disallow: /service/nolayout.aspx Disallow: /CompanyBrowse/Roger-Jones-Recruitment-Ltd_Vacancies_c336468.html # 22/05/2015 added to block facets on results.aspx Disallow: /*&Rate=* Disallow: /*&RateType=* Disallow: /*&ValidFromDay=* Disallow: /*&CompanyType=* #Disallow: /*&JobTitle=* Disallow: /*&Discipline=* Disallow: /*&JobType1=* Disallow: /*&JobType=* Disallow: /*&radius=* # this is where the radius is in a secondary faceted link Disallow: /*&Radius=* # this is where the radius is in a secondary faceted link Disallow: /*&postedwithin=* # this is where the postedwithin is in a secondary faceted link Disallow: /*&Postedwithin=* # this is where the postedwithin is in a secondary faceted link Disallow: /*&sort=* # this is where the sort is in a secondary faceted link Disallow: /*&Sort=* # this is where the sort is in a secondary faceted link Disallow: /*&salary=* # this is where the salary is in a secondary faceted link Disallow: /*&Salary=* # this is where the salary is in a secondary faceted link # to be added 08/09/2015 Disallow: /*/jbe/* Disallow: /JobsByEmail/* Disallow: /JobSearch/AdvancedJobSearch.aspx Disallow: /account/ # updated 09/03/17 RD Disallow: /Account/ # updated 09/03/17 RD Disallow: /AccountDetails/* Disallow: /*/similarjobs/* Disallow: /Jobsearch/ApplyViaDocuments.aspx Disallow: /~/* Disallow: /login Disallow: /Help/* Disallow: /SalaryChecker/SalaryCheckerResults.aspx Disallow: /jobseekers/*_new.asp Disallow: /tag/* Disallow: /jobwidget/* Disallow: /JobSearch/LocationSelect.aspx Disallow: /JobSearch/EmailLink.aspx # added 18/05/2016 to stop Google logging these Disallow: /JobSearch/*/api/* Disallow: /jobsearch/*/api/* # added 18/05/2016 other old URLs to block RD Disallow: /help/ Disallow: */articledetail.asp Disallow: */archivedetails.asp Disallow: /LocationHub/ Disallow: /jobs-at/jobs/in- Disallow: /jobs-at/*/jobs/part-time/ Disallow: /jobs-at/*/jobs/permanent/ Disallow: /jobs-at/*/jobs/contract/ Disallow: /jobs-at/*/jobs/temporary/ Disallow: /mail_rd.asp Disallow: /newwave_rd.asp Disallow: /sitecore/*/www. Disallow: /careers-advice/*/www. User-Agent: OmniExplorer_Bot Disallow: / # removed 05 Sept 2014 # User-Agent: MJ12bot # Disallow: / User-Agent: Verticrawlbot Disallow: / User-agent: AddSearchBot Disallow: / User-agent: admantx Disallow: / User-agent: AhrefsBot Disallow: / User-agent: Baiduspider User-agent: Baiduspider-video User-agent: Baiduspider-image Disallow: / User-agent: ChangeDetection Disallow: / User-agent: dotbot Disallow: / User-agent: Exabot Disallow: / User-agent: GozaikBot Disallow: / User-agent: grapeshot Disallow: / User-Agent: Ichiro Disallow: / #User-Agent: LinkedInBot/1.0 removed 22/11/17 RD #Disallow: / User-agent: proximic Disallow: / User-agent: SeznamBot Disallow: / User-agent: sogou spider Disallow: / User-agent: trovitBot Disallow: / User-agent: WeSEE Disallow: / User-agent: WijuBot Disallow: / User-agent: XoviBot Disallow: / User-agent: YakazBot/1.0 Disallow: / User-agent: Yandex Disallow: / # Pingdom added 24/09/2014 RD User-agent: Pingdom.com Disallow: / User-agent: Pingdom.com_bot Disallow: / User-agent: pingdom.com_bot_version_1.4_(http://www.pingdom.com/) Disallow: / User-agent: Pingdom Disallow: / User-agent: Pingdom GIGRIB Disallow: / # end pingdom # Mail.RU added 24/09/2014 RD User-agent: Mail.RU_Bot/2.0 Disallow: / User-agent: Mail.RU_Bot Disallow: / User-agent: mail.ru_bot/robots/2.0 Disallow: / User-agent: Mail.RU Disallow: / User-agent: Mail.Ru Disallow: / User-agent: Mozilla/5.0 (compatible; Linux x86_64; Mail.RU_Bot/2.0; +http://go.mail.ru/help/robots) Disallow: / # end Mail.RU User-agent: Bing Crawl-delay: 1 User-agent: Slurp Crawl-delay: 1