# robots.txt for http://www.sil.si.edu/ User-agent: * #these likely need to be deleted. check linking first. put on disallow 12/09 Disallow: www.sil.si.edu/silpublications/MSRLBibliographies/stores-bibliography.pdf Disallow: www.sil.si.edu/silpublications/tapestry-bibliography/ Disallow: www.sil.si.edu/SILpublications/AfricanAmericanIndiansBibliography.pdf Disallow: www.sil.si.edu/SILpublications/MLKBibliography.pdf Disallow: www.sil.si.edu/silpublications/MovingLibrariesBib.pdf Disallow: /staff/ Disallow: /about/ Disallow: /BCAProject/ Disallow: /BHL/ Disallow: /Branches/ Disallow: /DigitalCollections/trade-literature/samples/ Disallow: /Galaxy/ Disallow: /Graphics/ Disallow: /libqual/ Disallow: /Link-checking/ # don't delete this, just don't index it. Disallow: /onlineopinionF3r/ Disallow: /ProjectAccess/ Disallow: /research/InternetResources/ # old subject guides? Disallow: /research/SILstaff/ Disallow: /ResearchIntern/ Disallow: /RSVP/ #this can probably just be deleted Disallow: /Search/ # check references - not for main site. seems to use old search engine Disallow: /seasonal/ Disallow: /SILGalaxy/ #test pages I think Disallow: /SpecialCollections/ Disallow: /Subject-Guide/ Disallow: /USExExProject/ Disallow: /voyages/ #nothing in here Disallow: /Web4/ User-agent: Smithsonian-public-search # please index these new Contributions directories ! Allow: /pdf_hi/ Allow: /pdf_lo/ # try to not index images to reduce number of pages indexed TEST Disallow: /*.jpg Disallow: /*.gif # by directory Disallow: /404/ Disallow: /Cataloging/ # the following are in the Digital Collections dir # in BAE Disallow: /1000/ Disallow: /600/ # in BCA Disallow: /bca_00_00_00/ Disallow: /bca_01_00_00/ Disallow: /bca_02_00_00/ Disallow: /bca_03_01_00/ Disallow: /bca_03_02_00/ Disallow: /bca_03_03_00/ Disallow: /bca_03_04_00/ Disallow: /bca_04_00_00/ Disallow: /bca_05_00_00/ Disallow: /bca_06_00_00/ Disallow: /bca_07_00_00/ Disallow: /bca_08_00_00/ Disallow: /bca_09_00_00/ Disallow: /bca_10_00_00/ Disallow: /bca_11_00_00/ Disallow: /bca_12_01_01/ Disallow: /bca_12_01_02/ Disallow: /bca_12_02_01/ Disallow: /bca_12_02_02/ Disallow: /bca_12_03_01/ Disallow: /bca_12_03_02/ Disallow: /bca_12_04_01/ Disallow: /bca_12_04_02/ Disallow: /bca_12_04_03/ Disallow: /bca_12_04_04/ Disallow: /bca_12_04_05/ Disallow: /bca_12_04_06/ Disallow: /bca_12_04_07/ Disallow: /bca_12_05_00/ Disallow: /bca_12_06_01/ Disallow: /bca_12_06_01s/ Disallow: /bca_12_06_02/ Disallow: /bca_12_07_00/ Disallow: /bca_13_01_00/ Disallow: /bca_13_02_00/ Disallow: /bca_13_03_00/ Disallow: /bca_14_01_00/ Disallow: /bca_14_02_00/ Disallow: /bca_14_03_00/ Disallow: /bca_15_01_00/ Disallow: /bca_15_02_00/ Disallow: /bca_15_03_00/ Disallow: /bca_15_04_00/ Disallow: /bca_16_01_00/ Disallow: /bca_16_02_00/ Disallow: /bca_16_03_00/ Disallow: /bca_17_01_00/ Disallow: /bca_17_02_00/ Disallow: /bca_18_01_00/ Disallow: /bca_18_02_01/ Disallow: /bca_18_02_02/ Disallow: /bca_19_00_00/ Disallow: /bca_20_01_00/ Disallow: /bca_20_02_00/ Disallow: /bca_21_01_00/ Disallow: /bca_21_02_00/ Disallow: /bca_21_03_00/ Disallow: /bca_21_04_00/ Disallow: /bca_21_05_00/ # in bhlcollections and HSTcollections just pngs Disallow: /pages/ # in HST Disallow: /Cooper/PDF/ Disallow: /Lewton/high/ Disallow: /Lewton/low/ Disallow: /Scientific-Identity/pdf/ Disallow: /Incunabula/fullsize/ Disallow: /IndexAnimalium/volumes/ Allow: /IndexAnimalium/volumes/index.cfm # NHRareBooks not sure about this dir Disallow: /NYCoachMakersMagazine/PDFs/ Disallow: /Trade-Literature/samples/ Disallow: /Scientific-Instruments/pdf/ Disallow: /Scientific-Instruments/files/ Disallow: /Sewing-Machines/sil/ Disallow: /Sewing-Machines/graphics/ Disallow: /Sewing-Machines/nmahtex/ Disallow: /Sewing-Machines/PDF/ Disallow: /USExEx/19-01/ Disallow: /USExEx/19-02/ Disallow: /USExEx/19-03/ Disallow: /USExEx/19-04/ Disallow: /USExEx/19-05/ Disallow: /USExEx/19-07/ Disallow: /USExEx/19-08/ Disallow: /USExEx/19-09/ Disallow: /USExEx/19-10/ Disallow: /USExEx/19-11/ Disallow: /USExEx/19-12/ Disallow: /USExEx/19-13/ Disallow: /USExEx/19-14/ Disallow: /USExEx/19-15/ Disallow: /USExEx/19-16/ Disallow: /USExEx/19-17/ Disallow: /USExEx/19-18/ Disallow: /USExEx/19-19/ Disallow: /USExEx/19-20/ Disallow: /USExEx/19-21/ Disallow: /USExEx/19-22/ Disallow: /USExEx/19-23/ Disallow: /USExEx/19-24/ Disallow: /USExEx/19-24a/ Disallow: /USExEx/19-26/ Disallow: /USExEx/19-28/ Disallow: /USExEx/19-29a/ Disallow: /USExEx/19-29b/ Disallow: /USExEx/19-30/ Disallow: /USExEx/19-31/ Disallow: /USExEx/19-34/ Disallow: /USExEx/Cultural_objects/ Disallow: /USExEx/narrative_images/ Disallow: /USExEx/objects/ Disallow: /USExEx/pdf/ Disallow: /USExEx/Scientific_images/ Disallow: /eresources/CIRLAEFlowChart_files/ Disallow: /Chasing-Venus/full-size/ Disallow: /Chasing-Venus/mp3/ Disallow: /Chasing-Venus/Henry-Statue/ Disallow: /Odyssey/school-librarians/ Disallow: /Exhibitions/Odyssey/OdyBanners/ Disallow: /Underwater-Web/raw-images/ Disallow: /Underwater-Web/sounds/ Disallow: /1926-New-Guinea/62916/ Disallow: /1926-New-Guinea/video/ Allow: /1926-New-Guinea/video/index.cfm Disallow: /1926-New-Guinea/Photographs/ Disallow: /ImageGalaxy/verity/ Disallow: /ISD/ Disallow: /Newsletter/graphics/ Disallow: /Newsletter/PDF/ Disallow: /OnDisplay/Flight/baseimages/ Disallow: /OnDisplay/Flight/archivesimages/ Disallow: /OnDisplay/Flight/audio/ Disallow: /OnDisplay/Hirshhorn/jpgs/ Disallow: /OnDisplay/NestsandEggs/zoom/ Disallow: /OnDisplay/Ramelli/zoom/ Disallow: /OnDisplay/Shoppers/photos/ Disallow: /onlineopinionF3r/ Disallow: /ProjectAccess/ # not sure of implications of this Disallow: /RSS/ Disallow: /Dibner-Library-Lectures/25/plates/ Disallow: /Caneva lecture-2nd version/ Disallow: /Grinnell/sources/ Disallow: /SILPublications/HMSG/ Allow: /SILPublications/HMSG/HMSG_audiotapes.htm Disallow: /StyleSheets/ Disallow: /USExExProject/samples/ Disallow: /USExExProject/files/ Disallow: /USExExProject/conversion/ # within various directories only images Disallow: /images/ Disallow: /flash/ Disallow: /graphics/ Disallow: /thumbnails/ Disallow: /thumb/ #this is the thumb file for contributions Disallow: /fullsize/ Disallow: /_vti_cnf/ Sitemap: http://www.sil.si.edu/SITEMAPS_INDEX_www_sil_si_edu.xml # End of robots.txt file