**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: entutele.com
* @MinSWversion: V1.1.1/54
* @Revision 3 - [13/11/2014] Jan van Straaten
*     - needs firstshow=1
* @Revision 2 - [04/11/2014] Francis De Paemeleere
*     - update to site changes + add more details
* @Revision 1 - [03/11/2014] Jan van Straaten
*     - timezone new style
* @Revision 0 - [21/03/2014] Steve Wildmore
*     - creation
* @Remarks:
* @header_end
**------------------------------------------------------------------------------------------------

site {url=entutele.com|timezone=America/Mexico_City|maxdays=15|cultureinfo=es-MX|charset=UTF-8|titlematchfactor=90|firstshow=1}
urldate.format {datestring|yyyy-MM-dd}
subpage.format{list|+06%3A00|+18%3A00}
url_index.headers {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the index pages

url_index{url|http://www.entutele.com/canal/|channel|/|urldate|subpage}
index_showsplit.scrub {multi|<table class="canal_horario">|<tr class=" ||</tbody>}
index_showsplit.modify {cleanup(removeduplicates=equal span=1)}

index_start.scrub {single|<th>||</th>|</th>}
index_title.scrub {single|class="_showinfo">||</a>|</a>}
index_subtitle.scrub {single|</h3>|class="_showinfo">|</a>|</a>}

scope.range {(indexshowdetails)|end}
* get premiere from title
index_premiere.modify {addstart('index_title'~"tag-estreno")|true}
* remove premiere tag from title
index_title.modify {remove(type=regex)|<[^>]*tag-estreno[^>]*>.*?</[^>]*>}

index_title.modify {cleanup(tags="<"">")}
index_title.modify {cleanup(tags="<"">")}
index_subtitle.modify {cleanup(tags="<"">")}
index_description.modify {cleanup(tags="<"">")}
end_scope

index_urlshow {url|http://www.entutele.com|class="vershow"|href="|">|">}
index_urlshow.headers {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the detail pages


title.scrub {single|class="show_desc"|<h2>|</h2>|</h2>}
*description.scrub {single|class="show_desc"|>|<div id="show_filtro"|<div id="show_filtro"}
description.scrub {regex||class="show_desc"[^>]*>(.*?)<[^>]*(?:id="recom"\|id="show_filtro")||}

scope.range {(showdetails)|end}
* get original title
titleoriginal.modify {substring(type=regex)|'description' "<h3[^>]*>(.*?)</h3>"}
titleoriginal.modify {remove(type=regex)|\s*Título original\s*:\s*}
titleoriginal.modify {remove(type=regex)|^(.*?")[^"]*(".*?)$}		* sometimes the original title is only between "" with other text around it
* remove original title from description
description.modify {remove(type=regex)|<h3[^>]*>(.*?)</h3>}

* remove title from description
description.modify {remove(type=regex)|<h2.*.</h2>}
* remove social media links from description
description.modify {remove(type=regex)|(<[^>]*class="social"[^>]*>.*?)<[^>]*class="tags"[^>]*>}
* get the categories
category.modify {substring(type=regex)|'description' "<p[^>]*class="tags"[^>]*>(.*?)</p>"}
category.modify {cleanup(tags="<"">")}
category.modify {replace|/|\|}
category.modify {remove(type=regex)|^(\s*).*?(\s*)$}
category.modify {cleanup(removeduplicates=equal)}
* remove categories from description
description.modify {remove(type=regex)|<p[^>]*class="tags"[^>]*>.*?</p>}

* get actors from description
actor.modify {substring(type=regex)|'description' "<[^>]*>Reparto:<[^>]*>(.*?)<"}
actor.modify {cleanup(tags="<"">")}
actor.modify {replace|,|\|}
description.modify {remove(type=regex)|(<[^>]*>Reparto:<[^>]*>.*?)<}

description.modify {cleanup(tags="<"">")}
end_scope

**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*scope.range {(channellist)|end}
*url_index{url|http://www.entutele.com/programacion/todos/}
*index_site_channel.scrub {multi|<tbody>\n|alt="|" class="canalimg" />|<h3>Qué es Entutele</h3>}
*index_site_id.scrub {multi|<tbody>\n|<a href="/canal/|">|<h3>Qué es Entutele</h3>}
*scope.range {(channellist)|end}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end