The branch, eden has been updated
via 3864104391e77243cb7d8a90af6d9aec35d226e9 (commit)
from 35fd4974d7740a474cc0feacc6cb4d7c52555fc8 (commit)
- Log -----------------------------------------------------------------
http://xbmc.git.sourceforge.net/git/gitweb.cgi?p=xbmc/scrapers;a=commit;h=3864104391e77243cb7d8a90af6d9aec35d226e9
commit 3864104391e77243cb7d8a90af6d9aec35d226e9
Author: olympia <[email protected]>
Date: Sat Apr 21 22:05:01 2012 +0200
[metadata.imdb.com] updated to version 2.5.1
diff --git a/metadata.common.imdb.com/addon.xml
b/metadata.common.imdb.com/addon.xml
index 59a4302..994add2 100644
--- a/metadata.common.imdb.com/addon.xml
+++ b/metadata.common.imdb.com/addon.xml
@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<addon id="metadata.common.imdb.com"
name="IMDB common scraper functions"
- version="2.1.9"
+ version="2.2.0"
provider-name="Team XBMC">
<requires>
<import addon="xbmc.metadata" version="1.0"/>
diff --git a/metadata.common.imdb.com/changelog.txt
b/metadata.common.imdb.com/changelog.txt
index a19b89e..6f98721 100644
--- a/metadata.common.imdb.com/changelog.txt
+++ b/metadata.common.imdb.com/changelog.txt
@@ -1,3 +1,7 @@
+[B]2.2.0[/B]
+- factored out GetIMDBAKATitlesById
+- factored out scraping certifications
+
[B]2.1.9[/B]
- fixed: plot when contains html links (once again)
diff --git a/metadata.common.imdb.com/imdb.xml
b/metadata.common.imdb.com/imdb.xml
index 5633908..5695458 100644
--- a/metadata.common.imdb.com/imdb.xml
+++ b/metadata.common.imdb.com/imdb.xml
@@ -51,7 +51,7 @@
<RegExp input="$$1" output="\1" dest="6">
<expression noclean="1"><table
class="cast_list">(.*?)</table></expression>
</RegExp>
- <RegExp input="$$6"
output="<actor><thumb>\2_SX512_SY512_\3</thumb><name>\1</name><role>\5</role></actor>"
dest="7">
+ <RegExp input="$$6"
output="<actor><thumb>\2_SX1024_SY1024_\3</thumb><name>\1</name><role>\5</role></actor>"
dest="7">
<expression repeat="yes" clear="yes" trim="3,4"
noclean="1,2"><noscript><img
\n[^a]*alt="([^"]*)"[^"]*"[^"]*"[^s]*src="(?:([^"]*\.)[^"]*(\.jpg))[^>]*.*?ter">[^>]*>\n\s*(<[^>]*>)?([^<\(]*)?</expression>
</RegExp>
<RegExp input="$$6"
output="<actor><thumb></thumb><name>\1</name><role>\3</role></actor>"
dest="7+">
@@ -131,7 +131,7 @@
<RegExp input="$$1" output="\1" dest="6">
<expression noclean="1"><table
class="cast">(.*?)</table></expression>
</RegExp>
- <RegExp input="$$6"
output="<actor><thumb>\1_SX512_SY512_\2</thumb><name>\3</name><role>\5</role></actor>"
dest="7">
+ <RegExp input="$$6"
output="<actor><thumb>\1_SX1024_SY1024_\2</thumb><name>\3</name><role>\5</role></actor>"
dest="7">
<expression repeat="yes" clear="yes"
fixchars="3,5" trim="3,5" noclean="1,2"><img
src="(?:([^"]*\.)[^"]*(\.jpg))?[^>]*[^"]*"nm"><a
href="[^"]*[^>]*>([^<]*)<[^"]*"ddd">([^<]<)?[^"]*"char">(.*?)</td></expression>
</RegExp>
<RegExp input="$$7"
output="<actor><thumb>\1</thumb>\2</actor>" dest="2+">
@@ -211,4 +211,137 @@
<expression noclean="1" />
</RegExp>
</ParseIMDBThumbs>
+
+ <GetIMDBUSACert dest="5">
+ <RegExp input="$$1" output="<details><url
cache="$$1-main.html"
function="ParseIMDBUSACert">http://akas.imdb.com/title/$$1/</url></details>"
dest="5">
+ <expression noclean="1" />
+ </RegExp>
+ </GetIMDBUSACert>
+ <ParseIMDBUSACert dest="5">
+ <RegExp input="$$1"
output="<details><mpaa>$INFO[certprefix]\1</mpaa></details>"
dest="5">
+ <expression>MPAA</a>\)</h4>\n?<span
itemprop="contentRating">Rated\s([^<]*)</expression>
+ </RegExp>
+ </ParseIMDBUSACert>
+
+ <GetIMDBCountryCert dest="5">
+ <RegExp input="$$1" output="<details><url
cache="$$1-combined.html"
function="ParseIMDBCountryCert">http://akas.imdb.com/title/$$1/combined</url></details>"
dest="5">
+ <expression noclean="1" />
+ </RegExp>
+ </GetIMDBCountryCert>
+ <ParseIMDBCountryCert dest="5">
+ <RegExp input="$$1"
output="<details><mpaa>$INFO[certprefix]\1</mpaa></details>"
dest="5">
+
<expression>>\s*$INFO[imdbcertcountry]:([^<]+)</a></expression>
+ </RegExp>
+ </ParseIMDBCountryCert>
+
+ <GetIMDBAKATitlesById dest="5">
+ <RegExp input="$$1" output="<details><url
cache="$$1-combined.html"
function="ParseIMDBAKATitles">http://akas.imdb.com/title/$$1/combined</url></details>"
dest="5">
+ <expression noclean="1" />
+ </RegExp>
+ </GetIMDBAKATitlesById>
+ <ParseIMDBAKATitles dest="5">
+ <RegExp input="$$2"
output="<details><title>\1</title></details>" dest="5">
+ <RegExp input="$$1" output="\1" dest="2">
+ <expression><h1>([^<]*)</expression>
+ </RegExp>
+ <RegExp input="$$10" output="\1" dest="4">
+ <RegExp input="$$1" output="\1" dest="9">
+ <expression><meta
name="title"
content="(?:&#x22;)?([^"]*?)(?:&#x22;)?
\([^\(]*?([0-9]{4})\)</expression>
+ </RegExp>
+ <RegExp input="$$9" output="\1" dest="10">
+ <expression />
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+Hong
Kong [<em>][^"]+English</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((Canada)\s(<em>)?\((English|imdb))</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+(UK(<em>)?<br>)</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^"]+International\s(<em>)?\(English
title\)(</em>)?(,|<)( |b)</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^"]+International\s(<em>)?\(English
title\)(</em>)? (<em>)?\(imdb</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="12">
+ <expression clear="yes"><a
href="/country/[^>]+>(UK</a></div>)</expression>
+ </RegExp>
+ <RegExp input="$$12" output="$$9" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="12">
+ <expression clear="yes"><a
href="/country/[^>]+>(USA</a></div>)</expression>
+ </RegExp>
+ <RegExp input="$$12" output="$$9" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+(USA(<em>)?<br>)</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((USA)\s(<em>)?\((English|imdb))</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="11">
+ <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((USA)\s(<em>)?\((new
title))</expression>
+ </RegExp>
+ <RegExp input="$$11" output="\1" dest="10">
+ <expression>(.+)</expression>
+ </RegExp>
+ <expression noclean="1" />
+ </RegExp>
+ <RegExp input="$$4" output="\1" dest="2">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="4">
+
<expression>>\s*?"([^<]+)"[^<]+[<em>]?[^"]+$INFO[imdbakatitles]</expression>
+ </RegExp>
+ <RegExp input="$$4" output="\1" dest="2">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="4">
+
<expression>>\s*?"([^<]+)"[^<]+[<em>]?[^"]+$INFO[imdbakatitles]\s(<em>)?\((imdb
display)</expression>
+ </RegExp>
+ <RegExp input="$$4" output="\1" dest="2">
+ <expression>(.+)</expression>
+ </RegExp>
+ <RegExp input="$$1" output="\1" dest="5">
+ <expression><a
href="/country/[^>]+>($INFO[imdbakatitles])</expression>
+ </RegExp>
+ <RegExp input="$$5" output="$$9" dest="4">
+ <expression>($INFO[imdbakatitles])</expression>
+ </RegExp>
+ <RegExp input="$INFO[imdbakatitles]" output="$$9"
dest="4">
+ <expression>Keep Original</expression>
+ </RegExp>
+ <RegExp input="$$4" output="\1" dest="2">
+ <expression>(.+)</expression>
+ </RegExp>
+ <expression noclean="1" />
+ </RegExp>
+ </ParseIMDBAKATitles>
+
</scraperfunctions>
diff --git a/metadata.imdb.com/addon.xml b/metadata.imdb.com/addon.xml
index d18627c..205cfa3 100644
--- a/metadata.imdb.com/addon.xml
+++ b/metadata.imdb.com/addon.xml
@@ -1,13 +1,13 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<addon id="metadata.imdb.com"
name="IMDb"
- version="2.5.0"
+ version="2.5.1"
provider-name="Team XBMC">
<requires>
<import addon="xbmc.metadata" version="1.0"/>
<import addon="metadata.common.themoviedb.org" version="2.1.4"/>
<import addon="metadata.common.movieposterdb.com" version="1.0.5"/>
- <import addon="metadata.common.imdb.com" version="2.1.9"/>
+ <import addon="metadata.common.imdb.com" version="2.2.0"/>
<import addon="metadata.common.impa.com" version="1.0.3"/>
<import addon="metadata.common.hdtrailers.net" version="1.0.7"/>
<import addon="metadata.common.youtubetrailers" version="1.0.4"/>
diff --git a/metadata.imdb.com/changelog.txt b/metadata.imdb.com/changelog.txt
index d32ff16..8706284 100644
--- a/metadata.imdb.com/changelog.txt
+++ b/metadata.imdb.com/changelog.txt
@@ -1,3 +1,7 @@
+[B]2.5.1[/B]
+- removed and factored out GetIMDBAKATitlesById to IMDb scraper library
+- removed and factored out scraping certification to IMDb scraper library
+
[B]2.5.0[/B]
- added: Set title scraping from TMDb
- refactored: scraper settings
diff --git a/metadata.imdb.com/imdb.xml b/metadata.imdb.com/imdb.xml
index f7ed6f6..6ad389d 100644
--- a/metadata.imdb.com/imdb.xml
+++ b/metadata.imdb.com/imdb.xml
@@ -50,8 +50,8 @@
<RegExp input="$$1"
output="<top250>\1</top250>" dest="5+">
<expression>Top 250 #([0-9]*)</</expression>
</RegExp>
- <RegExp input="$$1"
output="<mpaa>\1</mpaa>" dest="5+">
-
<expression>MPAA</a>\)</h4>\n?<span
itemprop="contentRating">([^<]*)</expression>
+ <RegExp input="$$2" output="<chain
function="GetIMDBUSACert">$$2</chain>" dest="5+">
+ <expression/>
</RegExp>
<RegExp input="$$1"
output="<tagline>\1</tagline>" dest="5+">
<expression><h4[^>]*?>Taglines:</h4>\n?([^<]*)</expression>
@@ -146,113 +146,4 @@
<expression noclean="1"/>
</RegExp>
</GetDetails>
- <GetIMDBAKATitlesById dest="5">
- <RegExp input="$$1" output="<details><url
cache="$$1-combined.html"
function="ParseIMDBAKATitles">http://akas.imdb.com/title/$$1/combined</url></details>"
dest="5">
- <expression noclean="1" />
- </RegExp>
- </GetIMDBAKATitlesById>
- <ParseIMDBAKATitles dest="5">
- <RegExp input="$$2"
output="<details><title>\1</title></details>" dest="5">
- <RegExp input="$$1" output="\1" dest="2">
- <expression><h1>([^<]*)</expression>
- </RegExp>
- <RegExp input="$$10" output="\1" dest="4">
- <RegExp input="$$1" output="\1" dest="9">
- <expression><meta
name="title"
content="(?:&#x22;)?([^"]*?)(?:&#x22;)?
\([^\(]*?([0-9]{4})\)</expression>
- </RegExp>
- <RegExp input="$$9" output="\1" dest="10">
- <expression />
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+Hong
Kong [<em>][^"]+English</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((Canada)\s(<em>)?\((English|imdb))</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+(UK(<em>)?<br>)</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^"]+International\s(<em>)?\(English
title\)(</em>)?(,|<)( |b)</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^"]+International\s(<em>)?\(English
title\)(</em>)? (<em>)?\(imdb</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="12">
- <expression clear="yes"><a
href="/country/[^>]+>(UK</a></div>)</expression>
- </RegExp>
- <RegExp input="$$12" output="$$9" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="12">
- <expression clear="yes"><a
href="/country/[^>]+>(USA</a></div>)</expression>
- </RegExp>
- <RegExp input="$$12" output="$$9" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+(USA(<em>)?<br>)</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((USA)\s(<em>)?\((English|imdb))</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="11">
- <expression
clear="yes">>\s*?"([^<]+)"[^<]+[<em>]?[^"]+((USA)\s(<em>)?\((new
title))</expression>
- </RegExp>
- <RegExp input="$$11" output="\1" dest="10">
- <expression>(.+)</expression>
- </RegExp>
- <expression noclean="1" />
- </RegExp>
- <RegExp input="$$4" output="\1" dest="2">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="4">
-
<expression>>\s*?"([^<]+)"[^<]+[<em>]?[^"]+$INFO[akatitles]</expression>
- </RegExp>
- <RegExp input="$$4" output="\1" dest="2">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="4">
-
<expression>>\s*?"([^<]+)"[^<]+[<em>]?[^"]+$INFO[akatitles]\s(<em>)?\((imdb
display)</expression>
- </RegExp>
- <RegExp input="$$4" output="\1" dest="2">
- <expression>(.+)</expression>
- </RegExp>
- <RegExp input="$$1" output="\1" dest="5">
- <expression><a
href="/country/[^>]+>($INFO[akatitles])</expression>
- </RegExp>
- <RegExp input="$$5" output="$$9" dest="4">
- <expression>($INFO[akatitles])</expression>
- </RegExp>
- <RegExp input="$INFO[akatitles]" output="$$9" dest="4">
- <expression>Keep Original</expression>
- </RegExp>
- <RegExp input="$$4" output="\1" dest="2">
- <expression>(.+)</expression>
- </RegExp>
- <expression noclean="1" />
- </RegExp>
- </ParseIMDBAKATitles>
</scraper>
diff --git a/metadata.imdb.com/resources/settings.xml
b/metadata.imdb.com/resources/settings.xml
index d0c6397..e7166f0 100644
--- a/metadata.imdb.com/resources/settings.xml
+++ b/metadata.imdb.com/resources/settings.xml
@@ -1,10 +1,11 @@
<?xml version="1.0" encoding="UTF-8"?>
<settings>
<category label="128">
- <setting label="30008" type="labelenum" values="Keep Original|USA /
International|Argentina|Austria|Belgium|Brazil|Bulgaria|Canada|China|Colombia|Chile|Croatia|Czech
Republic|Denmark|Finland|France|Germany|Greece|Hong
Kong|Hungary|Iceland|India|Israel|Italy|Japan|Mexico|Netherlands|Norway|Pakistan|Poland|Portugal|Romania|Russia|Serbia|Singapore|Slovenia|Spain|Sweden|Switzerland|Thailand|Turkey|Uruguay|Venezuela"
id="akatitles" default="Keep Original"/>
+ <setting label="30008" type="labelenum" values="Keep Original|USA /
International|Argentina|Austria|Belgium|Brazil|Bulgaria|Canada|China|Colombia|Chile|Croatia|Czech
Republic|Denmark|Finland|France|Germany|Greece|Hong
Kong|Hungary|Iceland|India|Israel|Italy|Japan|Mexico|Netherlands|Norway|Pakistan|Poland|Portugal|Romania|Russia|Serbia|Singapore|Slovenia|Spain|Sweden|Switzerland|Thailand|Turkey|Uruguay|Venezuela"
id="imdbakatitles" default="Keep Original"/>
<setting label="30000" type="bool" id="fullcredits" default="false"/>
<setting label="30013" type="bool" id="tmdbset" default="true"/>
<setting label="30007" type="labelenum" values="192|256|384|512|1024"
id="imdbscale" default="1024"/>
+ <setting label="certprefix" type="text" id="certprefix" default="Rated "
visible="false"/>
</category>
<category label="30011">
-----------------------------------------------------------------------
Summary of changes:
metadata.common.imdb.com/addon.xml | 2 +-
metadata.common.imdb.com/changelog.txt | 4 +
metadata.common.imdb.com/imdb.xml | 137 +++++++++++++++++++++++++++++-
metadata.imdb.com/addon.xml | 4 +-
metadata.imdb.com/changelog.txt | 4 +
metadata.imdb.com/imdb.xml | 113 +------------------------
metadata.imdb.com/resources/settings.xml | 3 +-
7 files changed, 150 insertions(+), 117 deletions(-)
hooks/post-receive
--
Scrapers
------------------------------------------------------------------------------
For Developers, A Lot Can Happen In A Second.
Boundary is the first to Know...and Tell You.
Monitor Your Applications in Ultra-Fine Resolution. Try it FREE!
http://p.sf.net/sfu/Boundary-d2dvs2
_______________________________________________
Xbmc-addons mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/xbmc-addons