232 lines
13 KiB
INI
Executable File
232 lines
13 KiB
INI
Executable File
**------------------------------------------------------------------------------------------------
|
|
* @header_start
|
|
* WebGrab+Plus ini for grabbing EPG data from TvGuide websites
|
|
* @Site: tvguide.com
|
|
* @MinSWversion: V1.1.1/56.27
|
|
* none
|
|
* @Revision 14 - [18/03/2017] Netuddki
|
|
* - Added option for Onscreen OR xmltv_ns Episode System
|
|
* - Fixed Showicons
|
|
* @Revision 13 - [24/07/2016] Blackbear199
|
|
* - remove index_start/stop modify
|
|
* @Revision 12 - [22/01/2015] francis De Paemeleere
|
|
* - adjust to changes of the site
|
|
* @Revision 11 - [16/01/2015] francis De Paemeleere
|
|
* - quick fix (index only)
|
|
* @Revision 10 - [29/06/2014] Jan van Straaten
|
|
* - added previousshown and repeat
|
|
* @Revision 9 - [08/06/2014] Ron
|
|
* - changed () to [] in channel creation (MePo problem)
|
|
* @Revision 8 - [02/05/2014] Francis De Paemeleere
|
|
* - adjust to the new timezone implementation of WG++
|
|
* @Revision 7 - [05/03/2014] Francis De Paemeleere
|
|
* - total rewrite of the code
|
|
* @Remarks:
|
|
* this is the base version
|
|
* @header_end
|
|
**------------------------------------------------------------------------------------------------
|
|
site {url=tvguide.com|timezone=America/New_York|maxdays=16.1|cultureinfo=en-US|charset=UTF-8|titlematchfactor=90|firstshow=2}
|
|
site {ratingsystem=MPAA}
|
|
*site {episodesystem=onscreen|} *Enable for Onscreen Episode System
|
|
site {episodesystem=xmltv_ns|} *Enable for xmltv_ns Episode System
|
|
|
|
urldate.format{datenumber|UNIX|0}
|
|
|
|
scope.range {(urlindex)|end}
|
|
index_temp_1.modify {substring(type=regex)|'config_site_id' "\(srvID([^)]*)\)"}
|
|
url_index.modify {replace|##svrID##|'index_temp_1'}
|
|
index_temp_1.modify {substring(type=regex)|'config_site_id' "SourceId:([^,]*)"}
|
|
url_index.modify {replace|##SourceId##|'index_temp_1'}
|
|
index_temp_1.modify {substring(type=regex)|'config_site_id' "Number:([^,]*)"}
|
|
url_index.modify {replace|##Number##|'index_temp_1'}
|
|
index_temp_1.modify {calculate(format=D0)|'config_timespan_days' 1 + 1440 *} * calculate how may minutes we want to get (so we only download the days, we want to see)
|
|
url_index.modify {replace|##Minutes##|'index_temp_1'}
|
|
end_scope
|
|
|
|
url_index{url|http://mobilelistings.tvguide.com/Listingsweb/ws/rest/airings/##svrID##/start/|urldate|/duration/##Minutes##?channelsourceids=##SourceId##%7C##Number##&formattype=json}
|
|
url_index.headers {customheader=Accept-Encoding=gzip,deflate}
|
|
|
|
index_showsplit.scrub {regex||"ProgramSchedule":.*?}}||}
|
|
|
|
index_start.scrub {regex||"StartTime"\s*:\s*((?:[^\s,])*)\s*,||}
|
|
index_stop.scrub {regex||"EndTime"\s*:\s*((?:[^\s,])*)\s*,||}
|
|
index_title.scrub {regex||"Title"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
index_subtitle.scrub {regex||"EpisodeTitle"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
index_temp_3.scrub {regex||"ProgramId"\s*:\s*((?:[^\s,])*)\s*,||}
|
|
index_temp_4.scrub {regex||"AiringAttrib"\s*:\s*(\d*)||} * binairy: 1= Live, 2=??,4=New, 8=??
|
|
* grab season and episode number
|
|
index_temp_7.scrub {regex||"SeasonNumber":([1-9]+)||}
|
|
index_temp_7.modify {addstart('index_temp_7' not "")|S}
|
|
index_temp_8.scrub {regex||"EpisodeNumber":"([1-9]+)||}
|
|
index_temp_8.modify {addstart('index_temp_8' not "")|E}
|
|
index_temp_8.modify {addstart('index_temp_7' not "")|'index_temp_7'}
|
|
index_episode.modify {set(pattern="S'S1'E'E1'")|'index_temp_8'}
|
|
|
|
scope.range {(indexshowdetails)|end}
|
|
index_title.modify {cleanup(style=jsondecode)}
|
|
index_subtitle.modify {cleanup(style=jsondecode)}
|
|
* remove subtitle from title
|
|
index_title.modify {remove(notnull type=string)|:'index_subtitle'}
|
|
|
|
* add flags according to airing attributes
|
|
index_temp_5.modify {calculate(format=D0)|'index_temp_4' 1 and}
|
|
index_temp_6.modify {addend('index_temp_5'=="1")| (live)}
|
|
index_temp_5.modify {calculate(format=D0)|'index_temp_4' 2 and}
|
|
index_temp_6.modify {addend('index_temp_5'=="2")| (repeat)}
|
|
index_temp_5.modify {calculate(format=D0)|'index_temp_4' 4 and}
|
|
index_temp_6.modify {addend('index_temp_5'=="4")| (new)}
|
|
* next line adds * to new shows, Ttile * = new shows, Title = "not new", 2 places
|
|
index_title.modify {addend('index_temp_5'=="4")| *}
|
|
index_temp_5.modify {calculate(format=D0)|'index_temp_4' 8 and}
|
|
index_temp_6.modify {addend('index_temp_5'=="8")| (cc)}
|
|
end_scope
|
|
|
|
index_urlshow.modify {clear}
|
|
index_urlshow.modify {addstart('index_temp_3' not="")|http://mapi.tvguide.com/listings/details?program='index_temp_3'}
|
|
index_urlshow.headers {customheader=Accept-Encoding=gzip,deflate} *to speedup the downloading of the detail pages
|
|
|
|
temp_1.scrub {regex||^.*?"seo_url"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
title.scrub {regex||^.*?"title"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
description.scrub {regex||^.*?"description"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
*description.scrub {single||||}
|
|
rating.scrub {regex||^.*?"rating"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
productiondate.scrub {regex||^.*?"release_year"\s*:\s*([+-]?\d*)||}
|
|
*productiondate.scrub {regex||^.*?"airdate"\s*:\s*([+-]?\d*)||}
|
|
*productiondate.modify {calculate(format=utcdate,MM/dd/yyyy)}
|
|
temp_2.scrub {regex||^.*?"type"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
temp_4.scrub {regex||^.*?"category_id"\s*:\s*([+-]?\d*)||} * genre ID
|
|
|
|
showicon.scrub {regex||"photos":\[[^]]*?\]||}
|
|
|
|
scope.range {(showdetails)|end}
|
|
title.modify {cleanup(style=jsondecode)}
|
|
description.modify {cleanup(style=jsondecode)}
|
|
rating.modify {cleanup(style=jsondecode)}
|
|
productiondate.modify {cleanup(style=jsondecode)}
|
|
temp_2.modify {cleanup(style=jsondecode)}
|
|
|
|
*remove subtitle from title
|
|
title.modify {remove(notnull type=string)|:'index_subtitle'}
|
|
|
|
temp_5.modify {calculate(format=D0)|'index_temp_4' 4 and}
|
|
*next line adds * to new shows, Title * = new shows, Title = "not new", 2 places
|
|
title.modify {addend('temp_5'=="4")| *}
|
|
|
|
actor.modify {replace|,|\|} * make actor multi a multi element
|
|
rating.modify {clear("None")}
|
|
description.modify {addend|'index_temp_6'}
|
|
|
|
category.modify {addend('temp_4' == "1")|##_##movie}
|
|
category.modify {addend('temp_4' == "2")|##_##sports}
|
|
category.modify {addend('temp_4' == "3")|##_##family}
|
|
category.modify {addend('temp_4' == "4")|##_##news}
|
|
category.modify {addend|##_##'temp_2'}
|
|
category.modify {replace|##_##|\|}
|
|
category.modify {remove|other}
|
|
*
|
|
previousshown.modify {substring(type=regex)|'description' "(\(repeat\))"}
|
|
previousshown.modify {replace(not "")|(repeat)|true}
|
|
* description.modify {remove(type=regex)|"(\(repeat\))"} *optional removes (repeat) from the description
|
|
premiere.modify {substring(type=regex)|'description' "(\(new\))"}
|
|
*premiere.modify {replace(not "")|(new)|true} *optional removes (new) from the description
|
|
description.modify {remove(type=regex)|"(\(new\))"}
|
|
description.modify {cleanup}
|
|
|
|
showicon.modify {substring(type=regex)|"url":"([^"]*)"} *get all the photos for this show
|
|
showicon.modify {substring(type=element)|2 1} *only get the third image (multi images are not yet supported by WG++)
|
|
showicon.modify {cleanup(style=jsondecode)}
|
|
end_scope
|
|
|
|
|
|
urlsubdetail.modify {clear}
|
|
urlsubdetail.modify {addstart('temp_1' not="")|'temp_1'cast}
|
|
urlsubdetail.modify {clear('temp_1' =="0")}
|
|
urlsubdetail.modify {cleanup(style=jsondecode)}
|
|
urlsubdetail.headers{customheader=Accept-Encoding=gzip,deflate} *to speedup the downloading of the detail pages
|
|
|
|
subdetail_temp_1.scrub {regex||(>\s*(?:Active)?\s*<[^>]*>\s*Cast\s*<.*$)||}
|
|
subdetail_temp_1.modify {remove(type=regex)|(>\s*(?:Former)?\s*<[^>]*>\s*Cast\s*<.*$)}
|
|
subdetail_actor.modify {substring(type=regex)|'subdetail_temp_1' "tvobject\-cast\-role\-actor[^>]*>([^<]*)"}
|
|
|
|
*** _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
|
|
** ##### TIMEZONE FILE CREATION (only to create the xxx-channel.xml file)
|
|
** this will create a .channels.xml file (channels by timezone) that will contain all the channels for all the supported timezones
|
|
** this can be used to generate a new tvguide.com_channels_byTimezone.xml
|
|
** @auto_xml_timezone_start
|
|
*url_index{url|http://mobilelistings.tvguide.com/Listingsweb/ws/rest/schedules/|subpage|/start/|urldate|/duration/1?ChannelFields=Name%2CFullName%2CNumber%2CSourceId&ScheduleFields=&formattype=json&disableChannels=}
|
|
*subpage.format {list|80001|80002|80003|80004|80005|80006}
|
|
*index_site_id.scrub {single||||}
|
|
*scope.range {(channellist)|end}
|
|
** ! remark: we loop from the back to the front!
|
|
*index_temp_4.modify {clear}
|
|
*index_temp_4.modify {addstart|80006}
|
|
*
|
|
*index_site_id.modify {replace|[\{"Channel":|\n(srvIDNNNN)} * "split" the full lising into timezone separate parts
|
|
*
|
|
*index_site_channel.modify {substring(type=regex)|'index_site_id' "(srvIDNNNN)\|"FullName":"([^"]*)"[^}]*"SourceId":\d*"}
|
|
*index_site_id.modify {substring(type=regex)|'index_site_id' "(srvIDNNNN)\|"FullName":"[^"]*"[^}]*"SourceId":(\d*)"}
|
|
*
|
|
*index_temp_1.modify {calculate(type=element format=F0)|'index_site_channel' #} *how many elements? Used as loop counter.
|
|
*index_temp_6.modify {clear}
|
|
*index_temp_5.modify {clear}
|
|
*index_temp_6.modify {addstart|'index_site_channel'} *copy original elemets in temp
|
|
*index_temp_5.modify {addstart|'index_site_id'} *copy original elemets in temp
|
|
*index_site_channel.modify {clear} *to be refilled later
|
|
*index_site_id.modify {clear} *to be refilled later
|
|
*loop {('index_temp_1' > "0" max=5000)|end}
|
|
*index_temp_1.modify {calculate(format=F0)|1 -} *decrease the loop counter
|
|
*index_temp_2.modify {substring(type=element)|'index_temp_6' 'index_temp_1' 1} *element to work on
|
|
*index_temp_3.modify {substring(type=element)|'index_temp_5' 'index_temp_1' 1} *element to work on
|
|
*
|
|
*index_site_channel.modify {addstart('index_temp_2' not== "srvIDNNNN")|##_####TIMEZONE##'index_temp_2'} *fill elements again , add a placeholder ##_## as separator
|
|
*index_site_id.modify {addstart('index_temp_2' not== "srvIDNNNN")|##_####SERVERID##Number:*,SourceId:'index_temp_3'} *fill elements again , add a placeholder ##_## as separator
|
|
*
|
|
*index_site_id.modify {replace('index_temp_2' == "srvIDNNNN")|##SERVERID##|(srvID'index_temp_4')} *after all channels are added, change the server id to the correct value
|
|
*index_site_channel.modify {replace('index_temp_2' == "srvIDNNNN")|##TIMEZONE##|##TIMEZONE'index_temp_4'##} *after all channels are added, change the server id to the correct value
|
|
*index_temp_4.modify {calculate('index_temp_2' == "srvIDNNNN" format=F0)|'index_temp_4' 1 -} *decrease the server id for the next time (80006, 80005, 80004, ...)
|
|
*
|
|
*end_loop
|
|
*index_site_channel.modify {replace|##TIMEZONE80001##|(Eastern)}
|
|
*index_site_channel.modify {replace|##TIMEZONE80002##|(Central)}
|
|
*index_site_channel.modify {replace|##TIMEZONE80003##|(Mountain)}
|
|
*index_site_channel.modify {replace|##TIMEZONE80004##|(Pacific)}
|
|
*index_site_channel.modify {replace|##TIMEZONE80005##|(Alaskan)}
|
|
*index_site_channel.modify {replace|##TIMEZONE80006##|(Hawaiian)}
|
|
*index_site_channel.modify {replace|##_##|\|}
|
|
*index_site_id.modify {replace|##_##|\|}
|
|
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
|
|
** replace in channels with [ ]
|
|
*index_site_channel.modify {replace|)|]}
|
|
*index_site_channel.modify {replace|(|[}
|
|
*end_scope
|
|
** @auto_xml_timezone_end
|
|
|
|
*** _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
|
|
** ##### PROVIDER FILE CREATION (only to create the xxx-channel.xml file)
|
|
**
|
|
** @auto_xml_provider_start
|
|
*url_index{url|http://mobilelistings.tvguide.com/Listingsweb/ws/rest/serviceproviders/zipcode/|channel|?formattype=json}
|
|
*url_index.headers {customheader=Accept-Encoding=gzip,deflate} *to speedup the downloading
|
|
*index_site_id.scrub {regex||"Id"\s*:\s*([+-]?\d*)||}
|
|
*index_site_channel.scrub {regex||"Name"\s*:\s*"([^"\\]*(?:\\.[^"\\]*)*)"||}
|
|
** @auto_xml_provider_end
|
|
|
|
|
|
*** _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
|
|
** ##### CHANNEL FILE CREATION (only to create the xxx-channel.xml file)
|
|
**
|
|
** @auto_xml_channel_start
|
|
*url_index{url|http://mobilelistings.tvguide.com/Listingsweb/ws/rest/schedules/|channel|/start/|urldate|/duration/1?ChannelFields=Name%2CFullName%2CNumber%2CSourceId&ScheduleFields=&formattype=json&disableChannels=}
|
|
*index_site_channel.scrub {regex||"FullName":"([^"]*)"[^}]*"SourceId":\d*||}
|
|
*index_site_id.scrub {regex||"FullName":"[^"]*"[^}]*("Number":"[^"]*"[^}]*"SourceId":\d*)||}
|
|
*scope.range {(channellist)|end}
|
|
*index_site_id.modify {remove(type=regex)|("Sort"\s*:\s*\d*\s*,*)}
|
|
*index_site_id.modify {remove|"}
|
|
*index_site_id.modify {addstart|(srvID'config_site_id')} *add the config site_id, so, we can keep this siteini generic (no need for the user to edit it)
|
|
*index_site_id.modify {cleanup(removeduplicates=equal,100 link="index_site_channel")}
|
|
*replace in channels with [ ]
|
|
*index_site_channel.modify {replace|)|]}
|
|
*index_site_channel.modify {replace|(|[}
|
|
*end_scope
|
|
** @auto_xml_channel_end
|