**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: gatotv.com
* @MinSWversion:
* @Revision 3 - [22/04/2016] 1NSdbZVbpZDX
*   - episode fix, added show details
* @Revision 2 - [05/01/2016] Francis De Paemeleere
*   - remove debug content
* @Revision 1 - [26/02/2015] Francis De Paemeleere
*   - remove new lines from title, ...
* @Revision 0 - [17/02/2015] Francis De Paemeleere
*   - creation
* @Remarks: currently index only (not much details on detail pages)
* @header_end
**------------------------------------------------------------------------------------------------

site {url=gatotv.com|timezone=America/Mexico_City|maxdays=7|cultureinfo=es-MX|charset=UTF-8|titlematchfactor=90|nopageoverlaps|firstshow=1}

urldate.format {datestring|yyyy-MM-dd}
url_index{url|http://www.gatotv.com/canal/|channel|/|urldate|}
url_index.headers 	  {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the index pages

index_showsplit.scrub {multi |tbl_EPG_row|>|</tr|</tr}

scope.range {(splitindex)|end}
index_showsplit.modify {replace|tbl_EPG_TimesColumnOutOfSchedule|tbl_EPG_TimesColumn}
index_showsplit.modify {replace | \| Episodio|-Episodio}
index_showsplit.modify {cleanup(removeduplicates=equal span=1)}
end_scope

index_start.scrub {regex||^.*?class="tbl_EPG_TimesColumn[^>]*>(.*?)</div>||}
index_stop.scrub {regex||^.*?class="tbl_EPG_TimesColumn[^>]*>.*?</div>.*?class="tbl_EPG_TimesColumn"[^>]*>(.*?)</div>||}

index_start.modify {replace|a. m.|am}
index_start.modify {replace|p. m.|pm}
index_stop.modify {replace|a. m.|am}
index_stop.modify {replace|p. m.|pm}

index_title.scrub {regex||^.*?class="div_program_title_on_channel"[^>]*>(.*?)</div>||}
index_subtitle.scrub {regex||^.*?class="div_episode_programa_on_channel"[^>]*>(.*?)</div>||}
index_showicon.scrub {regex||^.*?src=\"([^\"]*)\"||}
index_urlchannellogo.scrub {regex||^.*?class=\"div_MainPicture\"[^>]*>\s*<a[^>]*>[^/]*src=\"([^\"]*)\"||}

index_subtitle.modify {replace |Temporada |S}
index_subtitle.modify {replace |Episodio |Ep}
index_episode.scrub {single |div_episode_programa_on_channel">|<strong>|</strong>|</div>}
index_episode.modify {replace |Temporada |S}
index_episode.modify {replace |Episodio |Ep}

*index_temp_1.modify {substring(type=regex)|'index_subtitle' "\s*Temporada\s*(\d*)\s*"}
*index_temp_2.modify {substring(type=regex)|'index_subtitle' "\s*Episodio\s*(\d*)\s*"}
*index_subtitle.modify {remove(type=regex)|"\s*Temporada\s*\d*\s*"}
*index_subtitle.modify {remove(type=regex)|"\s*Episodio\s*\d*\s*"}
*index_subtitle.modify {remove(type=regex)|"<[^>]*>"}
*index_subtitle.modify {remove(type=regex)|"^\s*\!\?\!\?\!\s*$"} *| is converted to !?!?! by WG++
*index_subtitle.modify {remove(type=regex)|"^\s*$"}

* index_temp_1 = season
* index_temp_2 = episode
*index_temp_1.modify {calculate(not="" format=F0)|1 -}
*index_temp_2.modify {calculate(not="" format=F0)|1 -}
*index_episode.modify {clear}
*index_episode.modify {addend('index_temp_1' not="")|'index_temp_1'}
*index_episode.modify {addend|.}
*index_episode.modify {addend('index_temp_2' not="")|'index_temp_2'}
*index_episode.modify {addend|.}
*index_episode.modify {clear(="..")}

index_start.modify {remove(type=regex)|<[^>]*>}
index_stop.modify {remove(type=regex)|<[^>]*>}
index_subtitle.modify {remove(type=regex)|<[^>]*>}
index_title.modify {remove(type=regex)|<[^>]*>}
index_subtitle.modify {remove(type=regex)|<[^>]*>}

index_subtitle.modify {cleanup}
index_title.modify {cleanup}
index_subtitle.modify {cleanup}

scope.range {(indexshowdetails)|end}
index_urlshow.headers {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the detail pages
index_urlshow {url ||<a href="||"|}
end_scope
scope.range {(showdetails)|end}
title.scrub {single |itemprop="name">||</h1></div></td>|}
description.scrub {single|"summary">|"description">|</div></div>|}
actor.scrub {multi |itemprop="actors"|itemprop="name">|</span></span>|<span class="}
productiondate.scrub {regex ||(\d{4})<\/span><\/a>||}
category.scrub {multi |<span itemprop="genre"|nowrap" >|</span></a>|</table>}
category.scrub {multi |<strong>Tipo:|nowrap" >|</span>|</table>}
country.scrub {multi |Paises de Origen:|nowrap" >|</span></a>|</table>}
producer.scrub {multi |itemprop="producer"|nowrap" >|</span>|</table>}
composer.scrub {multi |<strong>Música:|nowrap" >|</span>|</table>}
rating.scrub {single |<strong>Clasificación:|nowrap" >|</span>|</table>}
writer.scrub {single |<strong>Basado en:|nowrap" >|</span>|</table>}
titleoriginal.scrub {single |<strong>Título en Idioma Original:|nowrap" >|</span>|</table>}
end_scope
**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*url_index{url|http://www.gatotv.com/guia_tv/completa}
*index_site_id.scrub {regex||class=\"\s*tbl_EPG_row[^>]*>(.*?)</tr>||}
*scope.range {(channellist)|end}
*index_site_channel.modify {addstart|'index_site_id'}
*index_site_id.modify {substring(type=regex)|<a [^>]*.*?href=\"([^\"]*)\"[^>]*title=\"[^\"]*\"[^>]*>}
*index_site_id.modify {remove|http://www.gatotv.com/canal/}
*index_site_channel.modify {substring(type=regex)|<a [^>]*.*?href=\"[^\"]*\"[^>]*title=\"([^\"]*)\"[^>]*>}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end