#This sample configuration file allows the Index Server
#Companion to retrieve the content from a website as well
as the SampleProject.mdb Microsoft Access database.

#Note that the setting name and the setting value MUST be
#separated by a space, an equals sign and another space.

##################################################
#                                                #
# General application configuration options      #
#                                                #
##################################################

#Name of the project

[ProjectName] = SampleProject

#Whether the Indexing Service Companion should create a log file

[CreateLogFile] = yes

#The output folder for the Indexing Service Companion log files
#Logs are saved with the filename <ProjectName>_YYYY-MM-DD HH-MM-SS.log
#The log file directory must actually exist, or the log file will not be created
#The log file directory should either be a full path, e.g.
#C:\logs\IndexServerCompanion
#or a relative path from the working directory that the Index Server Companion is
#run from, e.g.
#logs

[LogFileDir] = SampleProject\Logs

#The folder in which the Index Server Companion's Information Store is contained
#The folder name should either be a full path, e.g.
#C:\Programs\IndexServerCompanion\InfoStore
#or a relative path from the working directory that the Index Server Companion is
#run from, e.g.
#InfoStore

[InfoStoreDir] = SampleProject\InformationStore

#The folder in which the Index Server Companion should place the output files
#that are to be indexed by Index Server. Note that the output folder does not
#need to be accessible from the web
#The folder name should either be a full path, e.g.
#D:\Inetpub\IndexServerFiles\mywebsite
#or a relative path from the working directory that the Index Server Companion is
#run from, e.g.
#output

[OutputDir] = SampleProject\Output

#If set to 'yes' then the script will output its status to the command console

[Verbose] = yes

#If a filename is specified using the TableOfContentsPage configuration option
#then a basic table of contents page is produced for the website that is crawled
#by the Index Server Companion. To get the most out of this feature, it is important
#that the website contains accurate HTML title tags.

#[TableOfContentsPage] = C:\temp\TableOfContents.html

#This experimental feature extracts content from all of the HTML files retrieved
#by the web crawling process then creates a summary page from the content.

#[SummaryPage] = C:\temp\Summary.html

##################################################
#                                                #
# Website data extraction configuration options  #
#                                                #
##################################################

#The URL that the web robot should start from when indexing pages on the web server
#The web robot can normally start from the home page of a site, although it is often
#better to let it start at a page which has the largest possible number of links to
#the rest of the pages within a site. A table of contents page (if present) is often
#a good place to start.

[StartURL] = http://www.aspalliance.com/brettb/Default.asp

#Use a base URL if you only want a particular part of a site to be crawled

[BaseURL] = http://www.aspalliance.com/brettb/

#Web robots sometimes have problems in visiting all of the URLs in a site
#so this configuration option will enable the Index Server Companion to
#explore the site from more than one start URL. There is no limit to the 
#number of AdditionalURL configuration options added, but they must reside on
#the same website as specified in the StartURL configuration option.

[AdditionalURL] = http://www.aspalliance.com/brettb/What'sNew.aspx

#The value to be used for the HTTP_USER_AGENT HTTP variable by the
#Index Server Companion. Note that when you are using a web crawler
#on third party websites, it is considered best practice to include
#your email address in the User Agent variable so that the administrator
#of the site can contact should problems arise.

[UserAgent] = Index Server Companion 1.4 (admin@server.com)

#If set to 'yes' then the web crawler will avoid indexing certain files according to
#instructions found in the site's robots.txt file in accordance with the 
#Robots Exclusion Standard specification described at
#http://www.robotstxt.org/wc/norobots.html
#Unless you are crawling your own website, you are strongly advised to leave this
#configuration option set to 'yes'.

[UseRobotsTextFile] = yes

#If set to 'yes' then the web crawler will avoid indexing and/or following
#links from pages according to the contents of a 'robots' meta tag. Unlike
#robots.txt files, the 'robots' meta tag is page specific. The two commands
#understood by the Indexing Service Companion are 'noindex' and 'nofollow'.

[UseRobotsMetaTag] = yes

#The IgnoreURLsString option is useful if you are crawling a site that does not
#have a robots.txt file or you are unable to modify the file. It contains a Perl
#regular expression that if matched in a URL will prevent the Index Server
#Companion from retrieving or following links from that URL.
#The regular expression is not case sensitive. 

#[IgnoreURLsString] = test|testing

#If set to 'yes' then the web robot will treat URLs with different QueryStrings
#as being distinct URLs. This feature is useful for indexing content from
#custom web applications, but be aware that for normal websites it will lead to
#duplicate entries in the search results.

[UseURLQueryStrings] = no

#If set to 'yes' then the Index Server Companion will purge the details
#of visits to URLs and databases from the information store and delete all of
#the pages stored on disk. As such this can be used to reset the project.

[ResetProject] = no

#If CrawlType is set to 'incremental' then only pages that have changed are saved
#to disk. If set to 'full' then all of the pages are updated, regardless of whether
#the content has changed.

[CrawlType] = incremental

#The number of seconds the web crawler waits between each request to a web server
#If extracting content from a remote site, set this to a large value to avoid
#upsetting the server's administrator, and also to prevent bandwidth problems

[SleepTime] = 4

#Number of seconds before a request to a website should timeout

[TimeOutTime] = 25

#The maximum size of content of a single file retrieved by the web robot (in Kilobytes)

[MaxURLSize] = 1024

#The maximum number of URLs that will be retrieved by the web robot
#It is advisable to set this value so that an unattended web robot will
#not accidentally retrieve a large number of URLs and fill all available
#disk space

[MaxNumberOfURLs] = 4096

#A list of URL extensions that the web crawler should save content from
#each should be separated by a single space. Default options are .htm, .html,
#.asp, .aspx, .jsp, .php and .cfm
#Note that binary files such as PDF documents should be specified under
#the FileExtensions option

[URLExtensions] = .htm .html .asp .aspx .jsp .php .cfm

#A list of file extensions that the web crawler should save content from
#each should be separated by a single space. Default options are .doc and .pdf
#Note that Index Server doesn't index Adobe Acrobat PDF files unless you install
#the IFilter (from the Adobe website)

[FileExtensions] = .doc .pdf .rtf

#If set to yes, then the HTML <title> tag of files saved from the web crawl
#will be modified to the format:
#ISC_URL=<url>\t<existingtitle>
#Where \t is a tab character
#This allows programatic access to the file's original URL in search results
#returned by the Indexing Service without having to modify Indexing Service
#properties (for which administrative access to the server is required).

[AddURLToTitle] = no


#If you are indexing content from a case sensitive web server then this setting
#must be set to 'yes', otherwise set it to 'no'.

[CaseSensitiveServer] = no

##################################################
#                                                #
# Database data extraction configuration options #
#                                                #
##################################################

#If set to yes, then the HTML <title> tag of all files saved from database rows
#will be modified to the format:
#ISC_Table=<tablename>\tISC_KeyField=<keyfield>\tISC_RowNumber=<rownumber>\t<existingtitle>
#Where \t is a tab character
#This allows programatic access to the table's name, primary key field
#and row number in search results returned by the Indexing Service without
#having to modify Indexing Service properties (for which administrative
#access to the server is required).

[AddRowToTitle] = no

#If set to 'yes' then all of pages produced from the database rows will be refreshed

[RefreshAllRows] = no

#The following will extract the data from the q_courses Query of the SampleProject Access 2000 database

#Each database table uses the following mandatory configuration options:
# DSN = connection string
# Table = table name
# KeyField = primary key field of the table
# AllowFields = table fields to retrieve
#
#Each database table also uses the following optional configuration options:
#
# TitleField = table field containing the row's title
# DescriptionField = table field containing the row's description
#
#Each database table must have a unique number in this configuration file
#For further details, consult the Indexing Service Companion's product documentation

#ODBC Connection string for the database containing the specific table.

[DataTable_1_DSN] = Provider=Microsoft.Jet.OLEDB.4.0;Data Source=Provider=Microsoft.Jet.OLEDB.4.0;Data Source=SampleProject\SampleProject.mdb;Persist Security Info=False;

#Name of the database table. Note that it is possible to specify the database name
#and the table name in the format <database>..<table> used by SQL Server and other
#relational databases.

[DataTable_1_Table] = q_courses

#Primary key field for this table. This field must be unique. Composite keys are
#not presently supported

[DataTable_1_KeyField] = CourseID

#A list of database table fields that need to be indexed. A single '*' means that
#all of the fields in the table will be indexed.

[DataTable_1_AllowFields] = *

#An optional configuration option that specifies the field that should be used
#for the row's title. This is used in the HTML <title> tag for the row,
#and is useful for when creating pages displaying search results.

[DataTable_1_TitleField] = CourseName

#An optional configuration option that specifies the field that should be used
#for the row's description. This is used in the HTML <description> tag for the row,
#and is useful for when creating pages displaying search results.

[DataTable_1_DescriptionField] = CourseDescription

#The following will extract the data from the t_tutors table of the SampleProject Access 2000 database

[DataTable_2_DSN] = Provider=Microsoft.Jet.OLEDB.4.0;Data Source=Provider=Microsoft.Jet.OLEDB.4.0;Data Source=SampleProject\SampleProject.mdb;Persist Security Info=False;
[DataTable_2_Table] = t_tutors
[DataTable_2_KeyField] = TutorID
[DataTable_2_AllowFields] = TutorID, TutorName, TutorSubjects, TutorBiography
[DataTable_2_TitleField] = TutorName
[DataTable_2_DescriptionField] = TutorBiography