**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: rtm.gov.my
* @MinSWversion:
* @Revision 0 - [11/08/2014] Francis De Paemeleere
*   - creation
* @Remarks:
* @header_end
**------------------------------------------------------------------------------------------------

site {url=rtm.gov.my|timezone=Asia/Kuala_Lumpur|maxdays=1|cultureinfo=ms-MY|charset=UTF-8|titlematchfactor=90|keepindexpage}

url_index{url|http://live.rtm.gov.my/epg/}
url_index.headers 	  {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the index pages

index_showsplit.scrub {multi||||}

scope.range {(urlindex)|end}
index_variable_element.modify {clear}
index_variable_element.modify {addend|'config_site_id'}
end_scope

scope.range {(datelogo)|end}
index_urlchannellogo.scrub {regex||src="([^"]*)"[^>]*title="'index_variable_element'"[^>]*class="tl_location_image"||}
end_scope

scope.range {(splitindex)|end}
index_temp_6.modify {addend|'index_showsplit'} * full index_page
index_showsplit.modify {substring(type=regex)|'index_showsplit' "title="'index_variable_element'"[^>]*class="tl_location_image"(.*?)class="tl_location_image""}
index_showsplit.modify {substring(type=regex)|class="tl_event"(.*?)</a}

index_temp_1.modify {clear}
loop {(each 'index_temp_5' in 'index_showsplit' max=3000)|end}
index_temp_4.modify {clear}
index_temp_2.modify {clear}
index_temp_2.modify {substring(type=regex)|'index_temp_5' "data-event="(\d*)""}
index_temp_4.modify {substring(""not='index_temp_2' type=regex)|'index_temp_6' "(class="tl_event_details"[^>]*data-event="'index_temp_2'".*?class="tl_description_bottom")"}
index_temp_1.modify {addend(""not='index_temp_2')|'index_temp_5'_DEATILS_</div>'index_temp_4'###_###}
end_loop
index_showsplit.modify {clear}
index_showsplit.modify {addstart|'index_temp_1'}
index_showsplit.modify {replace|###_###|\|}
index_showsplit.modify {remove(type=regex)|<[^>]*class="tl_description_bottom"$}

* now we have to sort the listing (why oh why!)
index_showsplit.modify {sort(ascending,string)}
sort_by.scrub {regex(target="index_showsplit")||data-start="([^"]*)||}
sort_by.modify {calculate(target="index_showsplit" format=time,unix)}
end_scope

index_start.scrub {regex||data-start="([^"]*)||}

index_title.scrub {regex||class="tl_description_header_title"[^>]*>([^<]*)||}
index_category.scrub {regex||<strong>Genre:[^>]*?>([^<]*)||}
index_subtitle.scrub {regex||class="tl_description_header_subtitle"[^>]*?>([^<]*)||}
index_description.scrub {regex||^.*</div>(.*?)$||}
index_showicon.scrub {regex||class="tl_event_image".*? src="([^"]*)||}

index_description.modify {remove(type=regex)||<img[^>]*>||} * remove any images in the desciption
index_description.modify {cleanup(tags="<"">")}
index_category.modify {remove|N/A}
index_showicon.modify {addstart('index_showicon'not="")|http://live.rtm.gov.my/epg/}


**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*index_site_channel.scrub {regex||<img [^>]*title="([^"]*)"[^>]*class="tl_location_image"[^>]*>||}
*index_site_id.scrub {regex||<img [^>]*title="([^"]*)"[^>]*class="tl_location_image"[^>]*>||}
*scope.range {(channellist)|end}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end