[interchange-cvs] interchange - kwalsh modified dist/robots.cfg

interchange-cvs at icdevgroup.org interchange-cvs at icdevgroup.org
Thu Mar 8 10:40:35 EST 2007


User:      kwalsh
Date:      2007-03-08 15:40:35 GMT
Modified:  dist     robots.cfg
Log:
    * Racke suggested (in IRC) that the file would be more version control
      friendly if each UA and IP etc. was on its own line.

Revision  Changes    Path
2.2       +148 -26   interchange/dist/robots.cfg


rev 2.2, prev_rev 2.1
Index: robots.cfg
===================================================================
RCS file: /var/cvs/interchange/dist/robots.cfg,v
retrieving revision 2.1
retrieving revision 2.2
diff -u -r2.1 -r2.2
--- robots.cfg	8 Mar 2007 15:03:01 -0000	2.1
+++ robots.cfg	8 Mar 2007 15:40:35 -0000	2.2
@@ -1,36 +1,158 @@
-# $Id: robots.cfg,v 2.1 2007/03/08 15:03:01 kwalsh Exp $
-
 RobotUA <<EOR
-    ATN_Worldwide, AltaVista, Arachnoidea, Aranha, Architext, Argus, Ask,
-    Atomz, BackRub, Bookdog, BookmarkSync, Builder, CFNetwork, CMC, Contact,
-    Creep, Digital*Integrity, Directory, EZResult, Excite, FavOrg, Ferret,
-    Fireball, GoogleBot, Google-Sitemaps, GetRight, Gromit, Gulliver, Harvest,
-    Hubater, H?m?h?kki, INGRID, IncyWincy, Jack, JPluck, KIT*Fireball, Kototoi,
-    Leech, LWP, Lycos, Mediapartners, MegaSheep, Mercator, MimeLive, Miva,
-    Nazilla, NetMechanic, NetScoop, Nutch, Ocelli, ParaSite, Pokey, Pompos,
-    Refiner, RoboDude, Rover, Rutgers, Scooter, Slurp, Snappy, Snoopy, Spyder,
-    T-H-U-N-D-E-R-S-T-O-N-E, Toutatis, Tv*Merc, Valkyrie, Voyager,
-    W3C_Validator, Walker, WhizBang, Wire, Wombat, WordPress, Yahoo, Yandex,
-    ZyBorg, adressendeutschland, archive, appie, agent, asterias, bot, ccubee,
-    cfetch, contact, crawl, collector, complex_network_group, dogpile, fido,
-    find, gazz, gonzo, grab, griffon, holmes, index, larbin, legs, locator,
-    marvin, mirago, moget, newscan, ozelot, pagebull, retrieve, search, seek,
-    speedy, silk, sna, spider, suke, swish, tarantula, topiclink, urllib,
-    voyager, wget, whowhere, winona, worm, wwwster, xtreme,
+    ATN_Worldwide,
+    AltaVista,
+    Arachnoidea,
+    Aranha,
+    Architext,
+    Argus,
+    Ask,
+    Atomz,
+    BackRub,
+    Bookdog,
+    BookmarkSync,
+    Builder,
+    CFNetwork,
+    CMC,
+    Contact,
+    Creep,
+    Digital*Integrity,
+    Directory,
+    EZResult,
+    Excite,
+    FavOrg,
+    Ferret,
+    Fireball,
+    GetRight,
+    Google-Sitemaps,
+    GoogleBot,
+    Gromit,
+    Gulliver,
+    H?m?h?kki,
+    Harvest,
+    Hubater,
+    INGRID,
+    IncyWincy,
+    JPluck,
+    Jack,
+    KIT*Fireball,
+    Kototoi,
+    LWP,
+    Leech,
+    Lycos,
+    Mediapartners,
+    MegaSheep,
+    Mercator,
+    MimeLive,
+    Miva,
+    Nazilla,
+    NetMechanic,
+    NetScoop,
+    Nutch,
+    Ocelli,
+    ParaSite,
+    Pokey,
+    Pompos,
+    Refiner,
+    RoboDude,
+    Rover,
+    Rutgers,
+    Scooter,
+    Slurp,
+    Snappy,
+    Snoopy,
+    Spyder,
+    T-H-U-N-D-E-R-S-T-O-N-E,
+    Toutatis,
+    Tv*Merc,
+    Valkyrie,
+    Voyager,
+    W3C_Validator,
+    Walker,
+    WhizBang,
+    Wire,
+    Wombat,
+    WordPress,
+    Yahoo,
+    Yandex,
+    ZyBorg,
+    adressendeutschland,
+    agent,
+    appie,
+    archive,
+    asterias,
+    bot,
+    ccubee,
+    cfetch,
+    collector,
+    complex_network_group,
+    contact,
+    crawl,
+    dogpile,
+    fido,
+    find,
+    gazz,
+    gonzo,
+    grab,
+    griffon,
+    holmes,
+    index,
+    larbin,
+    legs,
+    locator,
+    marvin,
+    mirago,
+    moget,
+    newscan,
+    ozelot,
+    pagebull,
+    retrieve,
+    search,
+    seek,
+    silk,
+    sna,
+    speedy,
+    spider,
+    suke,
+    swish,
+    tarantula,
+    topiclink,
+    urllib,
+    voyager,
+    wget,
+    whowhere,
+    winona,
+    worm,
+    wwwster,
+    xtreme,
 EOR
 
 RobotIP <<EOR
-    202.9.155.123,      204.152.191.41,         208.146.26.19,
-    208.146.26.233,     209.185.141.209,        209.185.141.211,
-    209.202.148.36,     209.202.148.41,         216.200.130.207,
-    216.35.103.6?,      216.35.103.70,
+    202.9.155.123,
+    204.152.191.41,
+    208.146.26.19,
+    208.146.26.233,
+    209.185.141.209,
+    209.185.141.211,
+    209.202.148.36,
+    209.202.148.41,
+    216.200.130.207,
+    216.35.103.6?,
+    216.35.103.70,
 EOR
 
 RobotHost <<EOR
-    *.ask.com,          *.crawler*.com,         *.csccorporatedomains.com,
-    *.excite.com,       *.analys.google.com,    *.googlebot.com,
-    *.infoseek.com,     *.inktomi.com,          *.inktomisearch.com,
-    *.lycos.com,        msnbot.msn.com,         *.pa-x.dec.com,
+    *.ask.com,
+    *.crawler*.com,
+    *.csccorporatedomains.com,
+    *.excite.com,
+    *.analys.google.com,
+    *.googlebot.com,
+    *.infoseek.com,
+    *.inktomi.com,
+    *.inktomisearch.com,
+    *.lycos.com,
+    msnbot.msn.com,
+    *.pa-x.dec.com,
     add-url.altavista.com,
     westinghouse-rsl-com-usa.NorthRoyalton.cw.net,
 EOR








More information about the interchange-cvs mailing list