**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: tvguide.dk
* @MinSWversion: 1.1.1/56.26
*   none
* @Revision 6 - [27/06/2016] Blackbear199
*   adapted for version 56.26 season/episode implimentation
* @Revision 5 - [19/06/2016] Blackbear199
*   fix only 4 days epg
* @Revision 4 - [13/06/2016] Blackbear199
*   rewrite
* @Revision 3 - [25/11/2011] Jan van Straaten
*   removed links from description
* @Revision 2 - [] 
*   new showdetail scrubbing, needs 1.0.7
* @Revision 1 - [] 
*   adapted for V1.0.5
* @Remarks:
*   WebGrab 56.26 needed for new season/index_episode implimentation
* @header_end
**------------------------------------------------------------------------------------------------

site {url=tvguide.dk|timezone=UTC+01:00|maxdays=8.1|cultureinfo=da-DK|charset=ISO-8859-1|titlematchfactor=90|ratingsystem=DK|episodesystem=onscreen}
*
url_index{url|http://www.tvguide.dk/kanaler/|channel|}
url_index.headers {customheader=Accept-Encoding=gzip,deflate}
urldate.format {datestring|dd-MM-yyyy} *not used
*
index_showsplit.scrub {multi(include="<a title=")|<h1 class="program-heading"|<tr>|</tr>|</td><td bgcolor="#cacaca">}
*
scope.range{(indexshowdetails)|end}
index_start.scrub {single|class="time"|>|</td>|</td>}
index_start.modify {remove(type=regex)|<.+?>}
*
index_title.scrub {single|<a title="|">|</a>|</td>}
index_title.modify {remove(type=regex)|<br>[^<]*}
*
index_episode.modify {substring(type=regex pattern="'S1' ('E1')""'S1' ('E1':'Et1')""('E1':'Et1')""('E1')")|'index_title' "((?:\s\d{1,3}\s)?\((?:\d+:)?\d+\))$"} *season/index_episode from title Sx (Ex),Sx (Ex:Etx),(Ex:Etx),(Ex)
index_title.modify {remove(type=regex)|\s*\d*\s\(.+?\)$} * remove season/episode info from title
end_scope  
*
index_urlshow {url|http://www.tvguide.dk|href="||"|"}
index_urlshow.headers {customheader=Accept-Encoding=gzip,deflate}
*
scope.range{(showdetails)|end}
title.scrub {single|<h1 class='program-heading'>||</h1>|</h1>}
*
title.modify {remove(type=regex)|\s*\d*\s\(.+?\)$} * remove season/episode info from title
*
description.scrub {single|<td colspan="3" valign="top" class="news">||</div></td>|</div></td>}
description.modify {remove(type=regex)|<h2.+?<\/h2>}
description.modify {remove(type=regex)|<div.+?\'>}
description.modify {remove(type=regex)|<script.+?<\/script>}
description.modify {remove(type=regex)|<img.+?\"*>}
description.modify {remove(type=regex)|<!--.+?-->}
description.modify {remove(type=regex)|<br>&nbsp}
*
category.modify {substring(type=regex)|'description' "<b>Genre\s:</b>\s.+?<br>"}
description.modify {remove('category' not "")|'category'}
category.modify {substring(type=regex)|"</b>\s(?:\/?([^\/]*))*<br>"}
*
writer.modify {substring(type=regex)|'description' "Manuskript:\s.+?\s*<br>"} 
description.modify {remove('writer' not "")|'writer'}
writer.modify {substring(type=regex)|"Manuskript:\s(.+?)\.\s*<br>"
*
description.modify {remove(type=regex)|<b>Season\s:</b>\s.+?<br>} * remove season from description
description.modify {remove(type=regex)|<b>Episode\s:</b>\s.+?<br>} * remove index_episode from description
*
productiondate.modify {substring(type=regex)|'description' "<b>Year\s:</b>\s\d+<br>"}
description.modify {remove('productiondate' not "")|'productiondate'}
productiondate.modify {substring(type=regex)|"\d{4}"}
*
temp_1.modify {substring(type=regex)|'description' "Tilrettelæggelse:\s.+?<br>"} *organization?
description.modify {remove('temp_1' not "")|'temp_1'}
*
temp_2.modify {substring(type=regex)|'description' "Instruktion:\s.+?<br>"} *Instruction?
description.modify {remove('temp_2' not "")|'temp_2'}
*
temp_3.modify {substring(type=regex)|'description' "<b>Teaser\s:<\/b>\s.+?<br>"} *Teaser?
description.modify {remove('temp_3' not "")|'temp_3'}
*temp_3.modify {clear(not~ ", ")}
temp_3.modify {substring('temp_3' not "" type=regex)|"<\/b>\s(.+?)<br>"}
*temp_3.modify {replace('temp_3' not "")|,|\|} *make multi
*country.modify {substring('temp_3' not "" type=element)|'temp_3' 0 1}
subtitle.modify {addstart('temp_3' not "")|'temp_3'}
*
description.modify {remove(type=regex)|Sendt\sførste\sgang\s\d{2}\.\d{2}\.\d{2}<br>}
*
presenter.modify {substring(type=regex)|'description' "Vært:\s.+?<br>"} *actor
description.modify {remove('presenter' not "")|'presenter'}
presenter.modify {substring('presenter' not "" type=regex)|"<br>Vært:(.+?)"}
*
actor.modify {substring(type=regex)|'description' "<strong>.+?</strong>"} *actor
description.modify {remove('actor' not "")|'actor'}
actor.modify {substring('actor' not "" type=regex)|"<strong>Medvirkende:\s(.+?),</strong>"}
actor.modify {replace('actor' not "")|,|\|} *make Multi
actor.modify {remove('actor' not "" type=regex)|\s\(.+?\)}
*
actor.modify {substring('actor' "" type=regex)|'description' "(<br>.+?:\s.+?\.)*"} *actor
actor.modify {remove('actor' ~ "<br>")|\|}
description.modify {remove('actor' ~ "<br>")|'actor'}
actor.modify {substring('actor' ~ "<br>" type=regex)|"<br>.+?:(.+?)\."}
*
description.modify {remove(type=regex)|<.+?>}
description.modify {remove| (t)}
description.modify {remove|...}
description.modify {cleanup}
description.modify {clear('title')}
end_scope
*

*
**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*index_site_channel.scrub {multi|<table id="channels_selectors"><tr><td><select style='width:155px'>|">|</option>|</option></select></td></tr></table>}
*index_site_id.scrub {multi|<table id="channels_selectors"><tr><td><select style='width:155px'>|<option value="|">|</option></select></td></tr></table>}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
** @auto_xml_channel_end