**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: schedulesdirect.org
* @MinSWversion: V1.1.1/54
* @Revision 1 - [23/10/2014] Jan van Straaten
*   - adapted site changes
* @Revision 0 - [31/08/2013] Jan van Straaten / Francis De Paemeleere
*   - creation
* @Remarks: You need a login and password for this site
* @header_end
**------------------------------------------------------------------------------------------------

site {url=schedulesdirect.org|timezone=UTC|maxdays=16.1|cultureinfo=en-GB|charset=UTF-8|titlematchfactor=90|keepindexpage|firstshow=1}
site {ratingsystem=MPAA|subtitlestype=teletext|episodesystem=onscreen}
url_index {url|http://dd.schedulesdirect.org/schedulesdirect/tvlistings/xtvdService}
url_index.headers {method=SOAP}
url_index.headers {customheader=SOAPAction=urn:tvDataDelivery#download}
url_index.headers {customheader=Accept-Encoding=gzip,deflate}
*url_index.headers {host=dd.schedulesdirect.org}
* I put my credentials in the following line...  I did notice that there was an asteric at the beginning that I had to remove or else I would get an authentication error.
url_index.headers {credentials=xxx,xxx}
*
url_index.headers {accept=text/xml|contenttype=text/xml;charset="utf-8"}
url_index.headers {postdata='index_variable_element'}

scope.range {(urlindex)|end}
** timespan calculation to enable to add the requested timespan from the config
index_variable_element.modify {calculate(format=F1)|'config_timespan_days' 1 +} * add 1 day because config_timespan_days is 0 based
index_variable_element.modify {calculate(format=timespan,hours)} * convert to the proper timespan string required for index_temp_2
index_temp_1.modify {calculate(format=date,yyyy-MM-dd)|'urldate'}
index_temp_2.modify {calculate(format=date,yyyy-MM-dd)|'urldate' 'index_variable_element' +}
index_variable_element.modify {clear} * clear the timespan value
index_variable_element.modify {addstart|<soapenv:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:urn="urn:tvDataDelivery"><soapenv:Header/><soapenv:Body><urn:download soapenv:encodingStyle="http://schemas.xmlsoap.org/soap/encoding/"><startTime xsi:type="xsd:string">'index_temp_1'T00:00:00Z</startTime><endTime xsi:type="xsd:string">'index_temp_2'T00:00:00Z</endTime></urn:download></soapenv:Body></soapenv:Envelope>}
end_scope

index_showsplit.scrub {multi||||} * copies the whole index page
scope.range {(splitindex)|end}
index_temp_1.modify {addstart|'index_showsplit'}  * contains the whole xml file
index_variable_element.modify {clear}
index_variable_element.modify {addstart|'config_site_id'}
index_showsplit.modify {substring(type=regex)|(<schedule [^>]* station=\''index_variable_element'\' [^>]*>)}
index_showsplit.modify {cleanup(removeduplicates=equal,100)}
index_variable_element.modify {clear}
index_variable_element.modify {addstart|'index_temp_1'}  * contains the whole xml file
end_scope
**
index_start.scrub {single|time='|T|Z'|Z'}
index_duration.scrub {single|duration='|PT|M'|M'}
index_temp_5.scrub {single|program='||'|'}
index_videoquality.scrub {single|hdtv='||'|'}
index_videoquality.modify {replace(not="")|'index_videoquality'|HDTV}

index_subtitles.scrub {single|closeCaptioned='||'|'}
index_subtitles.modify {replace(not="")|'index_subtitles'|true}

scope.range {(indexshowdetails)|end}
index_start.modify {calculate(format=utctime)}
index_duration.modify {replace|H|:}

** get the programs part
index_temp_4.modify {substring(type=regex)|'index_variable_element' "^.*<program id=\''index_temp_5'\'>(.*?)</program>"}
index_title.modify          {substring(type=regex)|'index_temp_4' "<title>([^<]*)"}
index_subtitle.modify       {substring(type=regex)|'index_temp_4' "<subtitle>([^<]*)"}
index_description.modify    {substring(type=regex)|'index_temp_4' "<description>([^<]*)"}
index_rating.modify         {substring(type=regex)|'index_temp_4' "<mpaaRating>([^<]*)"}
index_temp_2.modify         {substring(type=regex)|'index_temp_4' "<advisory>([^<]*)</advisory>"}
index_rating.modify         {addend|\|'index_temp_2'} *advisory added to rating
index_productiondate.modify {substring(type=regex)|'index_temp_4' "<year>([^<]*)"}
index_episode.modify        {substring(type=regex)|'index_temp_4' "<syndicatedEpisodeNumber>([^<]*)"}
index_starrating.modify     {substring(type=regex)|'index_temp_4' "<starRating>(\**)[\+]*</starRating>"}  * full stars
index_temp_1.modify         {substring(type=regex)|'index_temp_4' "<starRating>.*(\+)</starRating>"}      * half star
index_starrating.modify     {calculate(not="" type=char format=F0)|#}
index_starrating.modify     {addend('index_temp_1' not="")|.5}
index_starrating.modify     {addend(not="")| / 4}
index_category.modify       {substring(type=regex)|'index_temp_4' "<showType>([^<]*)"}

* get the productionCrew part
index_temp_4.modify {substring(type=regex)|'index_variable_element' "^.*<crew program=\''index_temp_5'\'>(.*?)</crew>"}
index_actor.modify          {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Actor</role>(.*?)</member>"}
index_actor.modify          {cleanup(tags="<"">")}
index_temp_1.modify         {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Guest Star</role>(.*?)</member>"}
index_temp_1.modify         {cleanup(tags="<"">")}
index_temp_1.modify         {addend(not "")| (Guest Star)}
index_actor.modify          {addend('index_temp_1' not "")|'index_temp_1'\|}
index_actor.modify          {cleanup(removeduplicates)}
index_presenter.modify      {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Host</role>(.*?)</member>"}
index_presenter.modify      {cleanup(tags="<"">")}
index_director.modify       {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Director</role>(.*?)</member>"}
index_director.modify       {cleanup(tags="<"">")}
index_producer.modify       {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Producer</role>(.*?)</member>"}
index_producer.modify       {cleanup(tags="<"">")}
index_temp_1.modify         {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Executive Producer</role>(.*?)</member>"}
index_temp_1.modify         {cleanup(tags="<"">")}
index_temp_1.modify         {addend(not "")| (Executive Producer)}
index_producer.modify       {addstart('index_temp_1' not="")|'index_temp_1'\|}
index_producer.modify       {cleanup(removeduplicates)}
index_writer.modify         {substring(type=regex)|'index_temp_4' "<member>[^<]*<role>Writer</role>(.*?)</member>"}
index_writer.modify         {cleanup(tags="<"">")}
* get the genres part
index_temp_4.modify {substring(type=regex)|'index_variable_element' "^.*<programGenre program=\''index_temp_5'\'>(.*?)</programGenre>"}
index_temp_1.modify       {substring(type=regex)|'index_temp_4' "<genre>.*?<class>(.*?)</class>"}
index_category.modify     {addstart('index_temp_1' not= "")|'index_temp_1'\|}
end_scope

**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*index_site_id.scrub  {regex||(<station .*?</station>)||}
*scope.range {(channellist)|end}
*index_site_channel.modify {substring(type=regex)|'index_site_id' "<name>(.*?)</name>"}
*index_site_id.modify {substring(type=regex)|'index_site_id' "<station id=\'([0-9]*)\'>"}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end