**------------------------------------------------------------------------------------------------
* @header_start
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
* @Site: rai.it
* @MinSWversion: V0
* none
* @Revision 0 - [11/08/2011] Jan van Straaten
* none
* @Remarks:
* none
* @header_end
**------------------------------------------------------------------------------------------------
site {url=rai.it|timezone=UTC+01:00|maxdays=6|cultureinfo=it-IT|charset=UTF-8|titlematchfactor=90|episodesystem=onscreen}
*site {ratingsystem=IT|grabengine=|firstshow=0|firstday=0000000}
url_index{url()|http://www.rai.it/dl/portale/html/palinsesti/guidatv/static/|channel|_|urldate|.html}
urldate.format {datestring|yyyy_MM_dd}
*subpage.format {number||1|}
index_showsplit.scrub {multi|
|}
*
*title.scrub {single()||||} * this site has no consistent title in the detail page!!
subtitle.scrub {single||
|
|
}
description.scrub {single(separator=" />""\">" exclude="
|
|
|}
description.scrub {single(separator=" />""\">" exclude="
![]()
|
|
|}
category.scrub {single|
|Genere: |
|}
titleoriginal.scrub {single|
|Titolo originale: |
|}
producer.scrub {single|
|Produzione: |
|}
director.scrub {single(separator="Cast" include=first)|
|Regia: |
|}
actor.scrub {single|
|Cast: |
|}
productiondate.scrub {single|
|Anno: |
|}
*
*index_description.modify {addstart("")|nessun dettaglio}
*index_description.modify {remove('index_urlshow' not "")|'index_description'}
*
* the following extracts the episode from a title like .. Art alive Ep 42 .. and removes the Ep part from it:
index_title.modify {replace|ep.|ep. } * add space to ep. in case ep.52 (fails to extract the ep number without the space!)
index_title.modify {replace|Ep.|Ep. }
index_title.modify {replace| | }
index_temp_1.modify {calculate('index_title' ~ "Ep " format=F0)|'index_title' 1 *} * extract the Ep number
index_temp_1.modify {calculate('index_title' ~ "ep " format=F0)|'index_title' 1 *} * extract the Ep number
index_temp_1.modify {calculate('index_title' ~ "Ep." format=F0)|'index_title' 1 *} * extract the Ep number
index_temp_1.modify {calculate('index_title' ~ "ep." format=F0)|'index_title' 1 *} * extract the Ep number
index_episode.modify {replace|'index_episode'|Ep. 'index_temp_1'}
index_title.modify {remove| Ep 'index_temp_1'}
index_title.modify {remove| Ep. 'index_temp_1'}
index_title.modify {remove| ep 'index_temp_1'}
index_title.modify {remove| ep. 'index_temp_1'}
*
* episode can contain subtitle like: Trambusto nel bosco Ep 25
index_temp_2.modify {calculate(format=F0)|'index_episode' " " #} * count the words
index_temp_1.modify {calculate(format=F0)|'index_episode' 1 *} * extract the episode num
index_subtitle.modify {addstart('index_temp_2' > "3")|'index_episode'}
index_subtitle.modify {remove| Ep 'index_temp_1'}
index_subtitle.modify {remove| Ep. 'index_temp_1'}
index_subtitle.modify {remove| ep 'index_temp_1'}
index_subtitle.modify {remove| ep. 'index_temp_1'}
index_episode.modify {replace|'index_episode'|Ep. 'index_temp_1'}
*
index_temp_1.modify {replace|'index_temp_1'|'index_title'}
index_temp_1.modify {remove| 2a serie}
index_subtitle.modify {replace(~ 'index_temp_1')|'index_subtitle'|} * removes title without the 2a serie addition
index_subtitle.modify {remove|"}
*
title.modify {addstart|'index_title'} * no reliable title in detail page!!
description.modify {remove|Titolo originale: 'titleoriginal'}
description.modify {remove|Genere: 'category'}
description.modify {remove|Produzione: 'producer'}
description.modify {remove|Regia: 'director'}
description.modify {remove|Cast: 'actor'}
description.modify {remove|Anno: 'productiondate'}
description.modify {cleanup}
description.modify {replace| | }
description.modify {remove|