Schedules direct channels.xml generation

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=myusername,mypassword}
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|'index_temp_1'T00:00:00Z'index_temp_3'T00:00:00Z}
end_scope

index_showsplit.scrub {regex||||} * 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' "^.*?(.*?)"} * contains all programs
global_temp_1.modify {replace|title>|t>}
global_temp_1.modify {replace|subt>|st>}
global_temp_1.modify {replace||}
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' "^.*?(.*?)"} * 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>A}
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' "^.*?(.*?)"} * 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|(.*?)"} * contains all shows we need
index_temp_2.modify {substring(type=regex)|(]* 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' "^.*?

(.*?)

"}
index_title.modify {substring(type=regex)|'index_temp_4' "([^([^([^([^([^([^([^(\**)[\+]*"} * full stars
index_temp_1.modify {substring(type=regex)|'index_temp_4' ".*(\+)"} * 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' "([^(.*?)"}
index_actor.modify {substring(type=regex)|'index_temp_4' "[^A(.*?)"}
index_actor.modify {cleanup(tags="")}
*index_temp_1.modify {substring(type=regex)|'index_temp_4' "[^Guest Star(.*?)"}
*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' "[^Host(.*?)"}
index_presenter.modify {cleanup(tags="")}
index_director.modify {substring(type=regex)|'index_temp_4' "[^Director(.*?)"}
index_director.modify {cleanup(tags="")}
index_producer.modify {substring(type=regex)|'index_temp_4' "[^Producer(.*?)"}
index_producer.modify {cleanup(tags="")}
index_producer.modify {substring(type=regex)|'index_temp_4' "[^Executive Producer(.*?)"}
index_producer.modify {cleanup(tags="")}
*index_temp_1.modify {substring(type=regex)|'index_temp_4' "[^Executive Producer(.*?)"}
*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' "[^Writer(.*?)"}
index_writer.modify {cleanup(tags="")}
* get the genres part
index_temp_4.modify {substring(type=regex)|'global_temp_3' "^.*?(.*?)"}
index_temp_1.modify {substring(type=regex)|'index_temp_4' ".*?(.*?)"}
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||()||}
scope.range {(channellist)|end}
index_site_channel.modify {substring(type=regex)|'index_site_id' "(.*?)"}
index_site_id.modify {substring(type=regex)|'index_site_id' ""}
index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
end_scope
* @auto_xml_channel_end