**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: xin.msn.com
* @MinSWversion: V1.1.1/54
* @Revision 0 - [11/01/2015] Francis De Paemeleere
*   - creation
* @Remarks:
* @header_end
**------------------------------------------------------------------------------------------------

site {url=xin.msn.com|timezone=Asia/Singapore|maxdays=14.1|cultureinfo=en-US|charset=UTF-8|titlematchfactor=90|nopageoverlaps}

urldate.format {daycounter|0}
url_index{url|http://tvguide.xinmsnent.mediacorp.sg/starterkit/servlet/xintv/tvGuide?mcTvGuideId=1344396&number=0&timezone=%2B08%3A00&region=|channel|&tvGuideType=tvguide+week+schedule}
url_index.headers 	  {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the index pages

index_showsplit.scrub {regex||"pname".*?\}||}

scope.range {(splitindex)|end}
index_showsplit.modify {cleanup(removeduplicates=equal span=1)}
end_scope

index_start.scrub 		{regex||^.*?"showTimeInMillisecond"\s*:\s*([+-]?\d*)||}
index_stop.scrub 		{regex||^.*?"endTime"\s*:\s*([+-]?\d*)||}
index_title.scrub 		{regex||^.*?"pname"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
index_description.scrub {regex||^.*?"description"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
index_subtitle.scrub 	{regex||^.*?"episode"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}

scope.range {(indexshowdetails)|end}
index_start.modify      {calculate(format=utctime)}
index_stop.modify       {calculate(format=utctime)}

index_title.modify 		{cleanup(style=jsondecode)}
index_subtitle.modify 	{cleanup(style=jsondecode)}
index_description.modify{cleanup(style=jsondecode)}

*extract HD quality from titlematchfactor
index_videoquality.modify {substring(type=regex)|'index_title' "\s*\(\s*(HD)\s*\)$"}
index_title.modify {remove(type=regex)|"(\s*\(\s*HD\s*\))$"}

* extract PG info from subtitle
index_rating.modify {substring(type=regex)|'index_subtitle' "\s*\(\s*(PG[^\)]*)\s*\)\s*"}
index_subtitle.modify {remove(type=regex)|"(\s*\(\s*PG[^\)]*\s*\)\s*)"}

* extract cast from description
index_actor.modify 		{substring(type=regex)|'index_description' "\s*Cast[s]?\s*:(?:\s*([^,;]*)[,;])*\s*([^,;]*)\s*."}
index_description.modify {remove(type=regex)|"(\s*Cast[s]?\s*:(?:\s*[^,;]*[,;])*\s*[^,;]*\s*.)"}

index_producer.modify 	{substring(type=regex)|'index_description' "\s*Producer[s]?\s*:(?:\s*([^,;]*)[,;])*\s*([^,;]*)\s*."}
index_description.modify {remove(type=regex)|"(\s*Producer[s]?\s*:(?:\s*[^,;]*[,;])*\s*[^,;]*\s*.)"}
end_scope

*index_urlshow {url|}
index_urlshow.headers {customheader=Accept-Encoding=gzip,deflate}     * to speedup the downloading of the detail pages

**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*url_index{url|http://tvguide.xinmsnent.mediacorp.sg/starterkit/servlet/page/xintv/guide}
*index_site_id.scrub {regex||<select[^>]*id="tvScheullTimeZone"[^>]*>\s*(<option[^>]*value=".*?"[^>]*>.*?</option>\s*)*||}
*scope.range {(channellist)|end}
*index_site_channel.modify {addstart|'index_site_id'}
*index_site_channel.modify {substring(type=regex)|<option[^>]*value=".+?"[^>]*>(.+?)</option>}
*index_site_id.modify {substring(type=regex)|<option[^>]*value="(.+?)"[^>]*>.+?</option>}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end