**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from Finnish Yle Areena. Works for all free to air channels.
* @Site: areena.yle.fi
* @MinSWversion: v3.1
* @Revision 3 - [28/07/2023] Mat8861
* @Revision 2 - [24/12/2021]
* @Revision 1 - [16/07/2017]
*	- creation
* @Remarks:
* @header_end
**------------------------------------------------------------------------------------------------
site {url=areena.yle.fi|timezone=Europe/Helsinki|maxdays=7|cultureinfo=fi-FI|charset=UTF-8|titlematchfactor=90|ratingsystem=MEKU}
url_index{url|https://areena.api.yle.fi/v1/ui/schedules/|channel|/|urldate|.json?&language=fi&v=10&client=yle-areena-web&offset=0&limit=100&isInEU=true&app_id=areena-web-items&app_key=v9No1mV0omg2BppmDkmDL6tGKw1pRFZt}
url_index.headers {accept=text/html,application/xhtml+xml,application/xml|contenttype=text/html}
url_index.headers {customheader=Accept-Encoding=gzip,deflate}
urldate.format {datestring|yyyy-MM-dd}
*Showsplit
index_variable_element.modify {set|'config_site_id'}
index_urlchannellogo.scrub {single(includeblock="aria-label="'index_variable_element'")|class="channel-header__logo "|style="background-image: url('|')|></div></a>}
index_showsplit.scrub {regex||\{"title":".*?"type":"[^"]*"\}||}
*Start and stop times
index_start.scrub {regex||"raw":"(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2})\+\d+:\d+",||}
*Title and rating
index_title.scrub {regex||"title":"([^"]*)",||}
index_rating.modify {substring(type=regex)|'index_title' \((S?\d{0,2})\)$} *Get rating from program title
index_title.modify {remove(type=regex)| \(S?\d{0,2}\)} *Remove rating from program title
index_title.modify {remove(type=regex)| \d+\. kausi$} *Remove season number from program title (Sub,Ava,MTV3)
index_category.modify {addend('index_title' ~ "Elokuva: ")|Elokuva} *Mark movies based on title
index_category.modify {addend('index_title' ~ "kino")|Elokuva} *Mark movies based on title
index_category.modify {addend('index_title' ~ "Kotikatsomo: ")|Elokuva} *Mark movies based on title
index_category.modify {addend('index_title' ~ "Leffa: ")|Elokuva} *Mark movies based on title
index_title.modify {remove(type=regex)|^(?i)([\w-]*)(elokuva\|jännäri\|kino\|komedia\|kotikatsomo\|leffa\|perjantai\|putki\|trilleri)(: )} *Remove nonsense from the start of program names
*Description
index_description.scrub {regex||"description":"(.*?)","||}
index_description.modify {remove(type=regex)|(?<=[\?!])\.} *Remove dot after ? or !
index_description.modify {remove(type=regex)|\s+$} *Remove extra spaces
index_description.modify {replace(type=regex)|\s{2,}| } *Remove extra spaces
index_description.modify {replace(type=regex)|(?<=\d+\. )tuotantokausi|kausi} * Tuotantokausi -> kausi
index_description.modify {replace(type=regex)|(?:Kausi \d+([,.\s]+\|[,.\s]+[Oo]sa \|[,.\s]+jakso ))(?:\d+)|. Jakso } *Kausi 1, 1/10 or Kausi 1, osa 1/10 or Kausi 1, jakso 1/10 -> Kausi 1. Jakso 1/10.
index_description.modify {replace(type=regex)|(?<=\d+\. kausi)([,\s]+\|, osa )(?=\d+)|. Jakso } *1. kausi, 1/10 -> 1. kausi. Jakso 1/10.
index_description.modify {addend('index_description' = "")|'index_title'} *Add title to description if description is empty
*Showicon
index_showicon.scrub {regex||<a href="/([^"]+)" class="schedule-card__link"||} *Areena url for YLE programs
index_showicon.modify {addstart('index_showicon' not = "")|http://a5.images.cdn.yle.fi/image/upload/w_400,h_225,c_thumb/v42/13-} *Set size for icon with w_xxx and h_xxx
index_showicon.modify {addend('index_showicon' not = "")|.jpg}
*Season and episode numbers from description
index_episode.modify {substring(pattern="S'S1' 'E1'/'Et1' ""E'E1'/'Et1'.""S'S1', E'E1'""S'S1'. E'E1'/'Et1'.""E'E1'/'Et1'.""P'P1'/'Pt1'.""P'P1'" type=regex)|'index_description' "([Oo]sa \d+(?:\.)?[Kk]ausi \d+(?:\.) [Jj]akso \d+(?:\/\d+)?(?:\.)\|[Kk]ausi \d+(?:\.) [Jj]akso \d+(?:\/\d+)?(?:\.)\|\d+\. kauden\|[Kk]ausi \d+\.\|[Kk]ausi \d+, [Oo]sa \d+\|Kausi \d+, \d+\/\d+\|Jakso \d+:)"}
index_temp_1.modify{substring(type=regex)|'index_description' "^\d+/\d+\."}
index_temp_2.modify{substring(type=regex)|'index_description' "([Oo]sa \d+(?:\.)\|[Oo]sa \d+\/\d+\.)"}
index_episode.modify{addend('index_temp_1' not "")|E'index_temp_1'}
index_episode.modify{addend('index_temp_2' not "")|'index_temp_2'}
index_episode.modify {replace(type=regex)|[Kk]ausi|S}
index_episode.modify {replace(type=regex)|[[Jj]akso|E}
index_episode.modify {replace(type=regex)|[Oo]sa|P}
index_description.modify {remove(type=regex)|"([Kk]ausi \d+(?:\.) [Jj]akso \d+(?:\/\d+)?(?:\.)\|\d+\. kauden\|[Kk]ausi \d+\.\|[Kk]ausi \d+, [Oo]sa \d+\|Kausi \d+, \d+\/\d+\|Jakso \d+: )"}
index_description.modify {remove(type=regex)|"^\d+/\d+\."}
index_description.modify {remove(type=regex)|"([Oo]sa \d+\.\|[Oo]sa \d+\/\d+\.)"}
index_description.modify {cleanup}
**  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _  _
**      #####  CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
**
** @auto_xml_channel_start
*url_index {url|https://areena.yle.fi/_next/data/47wunL_GJDr5rppBkLq5w/fi/tv/opas.json?path=tv}
*index_site_id.scrub {regex||\{"content":\[\{"source":\{"uri":"https:\/\/areena\.api\.yle\.fi\/v1\/ui\/schedules\/([^\/]*)/\d{4}-\d{2}-\d{2}\.json||}
*index_site_channel.scrub {regex||\{"content":\[\{"source":\{"uri":"https:\/\/areena\.api\.yle\.fi\/v1\/ui\/schedules\/[^\/]*/\d{4}-\d{2}-\d{2}\.json.*?"title":"([^"]*)","type":"list"\}\]||}
*scope.range {(channellist)|end}
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
*end_scope
** @auto_xml_channel_end