153 lines
9.1 KiB
INI
Executable File
153 lines
9.1 KiB
INI
Executable File
**------------------------------------------------------------------------------------------------
|
|
* @header_start
|
|
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
|
|
* @Site: schedulesdirect.org
|
|
* @MinSWversion: V1.1.1/56.6
|
|
* @Revision 3 - [15/11/2015] Jan van Straaten
|
|
* - remove of faulty credits role solution
|
|
* @Revision 2 - [24/10/2015] Francis De Paemeleere
|
|
* - speedup parsing (tested with V1.56.6)
|
|
* @Revision 1 - [23/10/2014] Jan van Straaten
|
|
* - adapted site changes
|
|
* @Revision 0 - [31/08/2013] Jan van Straaten / Francis De Paemeleere
|
|
* - creation
|
|
* @Remarks: You need a login and password for this site
|
|
* @header_end
|
|
**------------------------------------------------------------------------------------------------
|
|
|
|
site {url=schedulesdirect.org|timezone=UTC|maxdays=16.1|cultureinfo=en-US|charset=UTF-8|titlematchfactor=90|keepindexpage|firstshow=1}
|
|
site {ratingsystem=MPAA|subtitlestype=teletext|episodesystem=onscreen}
|
|
url_index {url|http://dd.schedulesdirect.org/schedulesdirect/tvlistings/xtvdService}
|
|
url_index.headers {method=SOAP}
|
|
url_index.headers {customheader=SOAPAction=urn:tvDataDelivery#download}
|
|
url_index.headers {customheader=Accept-Encoding=gzip,deflate}
|
|
*
|
|
*url_index.headers {credentials=ENTER_USERNAME,ENTER_PASSWORD}
|
|
url_index.headers {credentials=pedrobmat,bmatbmat}
|
|
*
|
|
url_index.headers {accept=text/xml|contenttype=text/xml;charset="utf-8"}
|
|
url_index.headers {postdata='index_variable_element'}
|
|
|
|
scope.range {(urlindex)|end}
|
|
** timespan calculation to enable to add the requested timespan from the config
|
|
index_variable_element.modify {calculate(format=F1)|'config_timespan_days' 1 +} * add 1 day because config_timespan_days is 0 based
|
|
index_variable_element.modify {calculate(format=timespan,hours)} * convert to the proper timespan string required for index_temp_3
|
|
index_temp_1.modify {calculate(format=date,yyyy-MM-dd)|'urldate'}
|
|
index_temp_3.modify {calculate(format=date,yyyy-MM-dd)|'urldate' 'index_variable_element' +}
|
|
index_variable_element.modify {clear} * clear the timespan value
|
|
index_variable_element.modify {addstart|<soapenv:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:urn="urn:tvDataDelivery"><soapenv:Header/><soapenv:Body><urn:download soapenv:encodingStyle="http://schemas.xmlsoap.org/soap/encoding/"><startTime xsi:type="xsd:string">'index_temp_1'T00:00:00Z</startTime><endTime xsi:type="xsd:string">'index_temp_3'T00:00:00Z</endTime></urn:download></soapenv:Body></soapenv:Envelope>}
|
|
end_scope
|
|
|
|
index_showsplit.scrub {regex||<xtvd.*?</xtvd>||} * copies the whole index page
|
|
scope.range {(splitindex)|end}
|
|
* now break up the large chuck into 3 smaller chucks, to speedup parsing
|
|
index_variable_element.modify {clear}
|
|
|
|
global_temp_1.modify {substring(type=regex)|'index_showsplit' "^.*?<programs>(.*?)</programs>"} * contains all programs
|
|
global_temp_1.modify {replace|title>|t>}
|
|
global_temp_1.modify {replace|subt>|st>}
|
|
global_temp_1.modify {replace|<program id=|<p id=}
|
|
global_temp_1.modify {replace|</program>|</p>}
|
|
global_temp_1.modify {replace|syndicatedEpisodeNumber>|sEN>}
|
|
global_temp_1.modify {replace|description>|d>}
|
|
global_temp_1.modify {replace|originalAirDate>|oAD>}
|
|
global_temp_1.modify {replace|showType>|sT>}
|
|
global_temp_1.modify {replace|series>|s>}
|
|
|
|
** SPEEDUP option: if you don't need production/crew/cast info, just comment out next line
|
|
global_temp_2.modify {substring(type=regex)|'index_showsplit' "^.*?<productionCrew>(.*?)</productionCrew>"} * contains all productionCrew
|
|
global_temp_2.modify {replace|name>|>}
|
|
global_temp_2.modify {replace|given>|g>}
|
|
global_temp_2.modify {replace|sur>|s>}
|
|
global_temp_2.modify {replace|member>|m>}
|
|
global_temp_2.modify {replace|role>|r>}
|
|
global_temp_2.modify {replace|r>Actor</r|r>A</r}
|
|
global_temp_2.modify {replace|program=|p=}
|
|
|
|
** SPEEDUP option: if you don't need extra genre info, just comment out next line
|
|
global_temp_3.modify {substring(type=regex)|'index_showsplit' "^.*?<genres>(.*?)</genres>"} * contains all programs
|
|
global_temp_3.modify {replace|genre>|g>}
|
|
global_temp_3.modify {replace|class>|c>}
|
|
global_temp_3.modify {replace|relevance>|r>}
|
|
global_temp_3.modify {replace|programGenre>|pG>}
|
|
global_temp_3.modify {replace|<programGenre program=|<pG p=}
|
|
|
|
index_temp_2.modify {substring(type=regex)|'index_showsplit' "^.*?<schedules>(.*?)</schedules>"} * contains all shows we need
|
|
index_temp_2.modify {substring(type=regex)|(<schedule [^>]* station=\''config_site_id'\' [^>]*>)}
|
|
index_temp_2.modify {cleanup(removeduplicates=equal,100)}
|
|
index_showsplit.modify {set|'index_temp_2'}
|
|
|
|
end_scope
|
|
**
|
|
index_start.scrub {regex||time='[^\']*?T(\d{2}:\d{2}):\d{2}Z'||}
|
|
index_duration.scrub {regex||duration='PT(\d*H\d*)M||}
|
|
index_temp_5.scrub {regex||program='([^\']*)||}
|
|
index_videoquality.scrub {regex||hdtv='([^\']*)||}
|
|
index_videoquality.modify {replace(not="")|'index_videoquality'|HDTV}
|
|
|
|
index_subtitles.scrub {regex||closeCaptioned='([^\']*)||}
|
|
index_subtitles.modify {replace(not="")|'index_subtitles'|true}
|
|
|
|
scope.range {(indexshowdetails)|end}
|
|
index_start.modify {calculate(format=utctime)}
|
|
index_duration.modify {replace|H|:}
|
|
|
|
** get the programs part
|
|
index_temp_4.modify {substring(type=regex)|'global_temp_1' "^.*?<p id=\''index_temp_5'\'>(.*?)</p>"}
|
|
index_title.modify {substring(type=regex)|'index_temp_4' "<t>([^<]*)"}
|
|
index_subtitle.modify {substring(type=regex)|'index_temp_4' "<st>([^<]*)"}
|
|
index_description.modify {substring(type=regex)|'index_temp_4' "<d>([^<]*)"}
|
|
index_rating.modify {substring(type=regex)|'index_temp_4' "<mpaaRating>([^<]*)"}
|
|
index_temp_3.modify {substring(type=regex)|'index_temp_4' "<advisory>([^<]*)"}
|
|
index_rating.modify {addend|\|'index_temp_3'} *advisory added to rating
|
|
index_productiondate.modify {substring(type=regex)|'index_temp_4' "<year>([^<]*)"}
|
|
index_episode.modify {substring(type=regex)|'index_temp_4' "<sEN>([^<]*)"}
|
|
index_starrating.modify {substring(type=regex)|'index_temp_4' "<starRating>(\**)[\+]*</starRating>"} * full stars
|
|
index_temp_1.modify {substring(type=regex)|'index_temp_4' "<starRating>.*(\+)</starRating>"} * half star
|
|
index_starrating.modify {calculate(not="" type=char format=F0)|#}
|
|
index_starrating.modify {addend('index_temp_1' not="")|.5}
|
|
index_starrating.modify {addend(not="")| / 4}
|
|
index_category.modify {substring(type=regex)|'index_temp_4' "<sT>([^<]*)"}
|
|
|
|
* get the productionCrew part
|
|
index_temp_4.modify {substring(type=regex)|'global_temp_2' "^.*?<crew p=\''index_temp_5'\'>(.*?)</crew>"}
|
|
index_actor.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>A</r>(.*?)</m>"}
|
|
index_actor.modify {cleanup(tags="<"">")}
|
|
*index_temp_1.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Guest Star</r>(.*?)</m>"}
|
|
*index_temp_1.modify {cleanup(tags="<"">")}
|
|
*index_temp_1.modify {addend(not "")| (Guest Star)}
|
|
*index_actor.modify {addend('index_temp_1' not "")|'index_temp_1'\|}
|
|
index_actor.modify {cleanup(removeduplicates)}
|
|
index_presenter.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Host</r>(.*?)</m>"}
|
|
index_presenter.modify {cleanup(tags="<"">")}
|
|
index_director.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Director</r>(.*?)</m>"}
|
|
index_director.modify {cleanup(tags="<"">")}
|
|
index_producer.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Producer</r>(.*?)</m>"}
|
|
index_producer.modify {cleanup(tags="<"">")}
|
|
index_producer.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Executive Producer</r>(.*?)</m>"}
|
|
index_producer.modify {cleanup(tags="<"">")}
|
|
*index_temp_1.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Executive Producer</r>(.*?)</m>"}
|
|
*index_temp_1.modify {cleanup(tags="<"">")}
|
|
*index_temp_1.modify {addend(not "")| (Executive Producer)}
|
|
*index_producer.modify {addstart('index_temp_1' not="")|'index_temp_1'\|}
|
|
index_producer.modify {cleanup(removeduplicates)}
|
|
index_writer.modify {substring(type=regex)|'index_temp_4' "<m>[^<]*<r>Writer</r>(.*?)</m>"}
|
|
index_writer.modify {cleanup(tags="<"">")}
|
|
* get the genres part
|
|
index_temp_4.modify {substring(type=regex)|'global_temp_3' "^.*?<pG p=\''index_temp_5'\'>(.*?)</pG>"}
|
|
index_temp_1.modify {substring(type=regex)|'index_temp_4' "<g>.*?<c>(.*?)</c>"}
|
|
index_category.modify {addstart('index_temp_1' not= "")|'index_temp_1'\|}
|
|
end_scope
|
|
|
|
** _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
|
|
** ##### CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
|
|
**
|
|
** @auto_xml_channel_start
|
|
*index_site_id.scrub {regex||(<station .*?</station>)||}
|
|
*scope.range {(channellist)|end}
|
|
*index_site_channel.modify {substring(type=regex)|'index_site_id' "<name>(.*?)</name>"}
|
|
*index_site_id.modify {substring(type=regex)|'index_site_id' "<station id=\'([0-9]*)\'>"}
|
|
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
|
|
*end_scope
|
|
** @auto_xml_channel_end
|