home *** CD-ROM | disk | FTP | other *** search
- <?xml version="1.0" encoding="UTF-8"?>
- <robot_Manager steps="195">
- <web_site use_ftp="0">
- <loc_local>
- <path>D:\_Applications_\Robot-Manager\Sample</path>
- <compression>0</compression>
- </loc_local>
- <loc_ftp>
- <server></server>
- <port>21</port>
- <user_name></user_name>
- <password></password>
- <passive>0</passive>
- <path></path>
- <compression>0</compression>
- </loc_ftp>
- </web_site>
- <access_log capture_method="local">
- <loc_local>
- <path>D:\_Applications_\Robot-Manager\Web.log</path>
- <compression>0</compression>
- </loc_local>
- <loc_ftp>
- <server></server>
- <port>21</port>
- <user_name></user_name>
- <password></password>
- <passive>0</passive>
- <path></path>
- <compression>0</compression>
- </loc_ftp>
- <loc_telnet>
- <host></host>
- <port>23</port>
- <user_name></user_name>
- <password></password>
- <path></path>
- <compressed>0</compressed>
- <prompts>
- <login>ogin:</login>
- <password>assword:</password>
- <command>]$</command>
- </prompts>
- <commands>
- <robots>grep -i '/robots.txt' %PATH%</robots>
- <pages>grep '%ROBOT%' %PATH%</pages>
- <robots_comp>gunzip -c %PATH% | grep -i '/robots.txt'</robots_comp>
- <pages_comp>gunzip -c %PATH% | grep '%ROBOT%'</pages_comp>
- </commands>
- </loc_telnet>
- <spider_logs>
- <parsed>1</parsed>
- <entry_size>9</entry_size>
- <date_index>3</date_index>
- <spider_index>8</spider_index>
- <page_index>4</page_index>
- <remote_ip_index>0</remote_ip_index>
- <error_code_index>5</error_code_index>
- <spider_type>user-agent</spider_type>
- <page_type>request-line</page_type>
- <date_type>apache</date_type>
- <epressions>
- <apache_date>^(?:31|[123]0|[012]?[1-9])[-/][A-Z][a-z]{2}[-/](?:19|20)(?:[0-9]{2})?:(?:[01][0-9]|2[0-3]):[0-5][0-9]:[0-5][0-9]\s[-+\s][0-9]{1,4}$</apache_date>
- <iis_date>^(?:19|20)[0-9]{2}[-/](?:0[1-9]|1[012])[-/](?:31|[123]0|[012]?[1-9])$</iis_date>
- <us_euro_date>^(?:31|[123]0|[012]?[1-9])[-/](?:0[1-9]|1[012])[-/](?:19|20)[0-9]{2}$</us_euro_date>
- <user_agent>^Mozilla/[0-9]\.[0-9].*$</user_agent>
- <remote_host>^[-a-zA-Z]+(?:\.[-a-zA-Z0-9]+)*\.(?:com|edu|gov|int|mil|net|org|biz|info|name|museum|coop|aero|[a-zA-Z][a-zA-Z])$</remote_host>
- <remote_ip>^(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-5][0-5])\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-5][0-5])\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-5][0-5])\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-5][0-5])$</remote_ip>
- <request_line>^(?:GET|POST|HEAD)\s/.*\sHTTP/1\.[01]$</request_line>
- <filename>^/.*</filename>
- <error_code>(?:^10[01]$)|(?:^20[0-6]$)|(?:^30[0-7]$)|(?:^4(?:0[0-9]|1[0-7])$)|(?:^50[0-5]$)</error_code>
- </epressions>
- <logs>
- </logs>
- </spider_logs>
- </access_log>
- <paths>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\French\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\French\about.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\French\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\German\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\German\about.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\German\vssver.scc"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\about.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\About\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\French\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\French\contact.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\French\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\German\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\German\contact.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\German\vssver.scc"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\contact.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Contact\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Faq\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Faq\faq.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Faq\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\FakeImage01.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\FakeImage02.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\FakeImage03.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\FakeImage04.gif"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\FakeImage01.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\FakeImage02.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\FakeImage03.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\FakeImage04.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\French\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\FakeImage01.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\FakeImage02.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\FakeImage03.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\FakeImage04.gif"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\German\vssver.scc"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Images\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Products\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Products\order-page.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Products\product01.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Products\product02.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Products\vssver.scc"/>
- <path googlebot="" item_type="1" robots="" value="D:\_Applications_\Robot-Manager\Sample\Resource\"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Resource\affiliation.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Resource\publication.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Resource\resource.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\Resource\vssver.scc"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\index.html"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\robots.txt"/>
- <path googlebot="" item_type="16" robots="" value="D:\_Applications_\Robot-Manager\Sample\vssver.scc"/>
- </paths>
- <spiders>
- <spider disallow="0" name="ADSA Research Group" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Abacho" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Acoon" parent="" selected="1">
- <disallow path="/About/French/"/>
- <disallow path="/About/about.html"/>
- <disallow path="/Contact/French/"/>
- <disallow path="/Contact/contact.html"/>
- <disallow path="/Faq/faq.html"/>
- <disallow path="/Images/"/>
- <disallow path="/Products/order-page.html"/>
- </spider>
- <spider disallow="0" name="All Spiders" parent="" selected="1">
- <disallow path="/About/"/>
- <disallow path="/Contact/"/>
- <disallow path="/Faq/"/>
- <disallow path="/Images/"/>
- <disallow path="/Products/order-page.html"/>
- <disallow path="/Resource/"/>
- </spider>
- <spider disallow="0" name="AllThatNet" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Alta Vista" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Anzwers" parent="" selected="0">
- </spider>
- <spider disallow="0" name="AustLII" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Business.com" parent="" selected="0">
- </spider>
- <spider disallow="0" name="CMC/0.01" parent="e-collector" selected="1">
- </spider>
- <spider disallow="0" name="DeepIndex" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Direct Hit Grabber" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Entire Web" parent="" selected="0">
- </spider>
- <spider disallow="0" name="EuroSeek" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Excite" parent="" selected="0">
- </spider>
- <spider disallow="0" name="FAST/AllTheWeb" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Fireball" parent="" selected="0">
- </spider>
- <spider disallow="0" name="GenDoor" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Gigabot" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Goo" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Google" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Google Image" parent="e-collector" selected="1">
- </spider>
- <spider disallow="0" name="Griffon" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Hämähäkki" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Industry Central" parent="" selected="0">
- </spider>
- <spider disallow="0" name="InfoSeek.de" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Ingrid" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Inktomi" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Innerprise" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Internet Cruiser" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Kvasir" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Legs" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Lets Find It Now!" parent="" selected="0">
- </spider>
- <spider disallow="0" name="LinkAlarm" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Lisa" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Lycos" parent="" selected="0">
- </spider>
- <spider disallow="0" name="MPRM Group Limited" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Mirago" parent="" selected="0">
- </spider>
- <spider disallow="0" name="NetMechanic" parent="" selected="0">
- </spider>
- <spider disallow="0" name="NetScoop" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Northern Light" parent="" selected="0">
- </spider>
- <spider disallow="0" name="ODiN" parent="" selected="0">
- </spider>
- <spider disallow="0" name="OMEGA Find" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Openfind" parent="" selected="0">
- </spider>
- <spider disallow="0" name="PlanetSearch" parent="" selected="0">
- </spider>
- <spider disallow="0" name="PolyBOT" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Pompos" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Portal Juice" parent="" selected="0">
- </spider>
- <spider disallow="0" name="RUTGERS" parent="" selected="0">
- </spider>
- <spider disallow="0" name="ScoutAbout" parent="" selected="0">
- </spider>
- <spider disallow="0" name="SearchUK" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Seven Twentyfour" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Speedy" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Suchmaschine21" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Thunderstone" parent="" selected="0">
- </spider>
- <spider disallow="0" name="TopicLink" parent="" selected="0">
- </spider>
- <spider disallow="0" name="TurnitinBOT" parent="" selected="0">
- </spider>
- <spider disallow="0" name="VietGATE" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Wayback Machine" parent="" selected="0">
- </spider>
- <spider disallow="0" name="WhoWhere?" parent="" selected="0">
- </spider>
- <spider disallow="0" name="WholeWeb" parent="" selected="0">
- </spider>
- <spider disallow="0" name="WiseGuys" parent="" selected="0">
- </spider>
- <spider disallow="0" name="WiseNut" parent="" selected="0">
- </spider>
- <spider disallow="0" name="Zeus" parent="" selected="0">
- </spider>
- <spider disallow="1" name="e-collector" parent="" selected="1">
- </spider>
- <spider disallow="0" name="iaNett.com" parent="" selected="0">
- </spider>
- <spider disallow="0" name="kensaku.jp" parent="" selected="0">
- </spider>
- <spider disallow="0" name="mopilot.com" parent="" selected="0">
- </spider>
- <spider disallow="0" name="nathan" parent="" selected="0">
- </spider>
- <spider disallow="0" name="newscan" parent="" selected="0">
- </spider>
- <spider disallow="0" name="whatUseek" parent="" selected="0">
- </spider>
- </spiders>
- </robot_Manager>
-