[Xbmc-addons] Scrapers branch, dharma-pre, updated. f6f4ad224159f09518c2959a3f6cc9972c0d3936

Wed, 27 Oct 2010 06:54:43 -0700 

The branch, dharma-pre has been updated
       via  f6f4ad224159f09518c2959a3f6cc9972c0d3936 (commit)
      from  c1b19c0a084cb024face3b2fe6cda088d9e97998 (commit)

- Log -----------------------------------------------------------------
http://xbmc.git.sourceforge.net/git/gitweb.cgi?p=xbmc/scrapers;a=commit;h=f6f4ad224159f09518c2959a3f6cc9972c0d3936

commit f6f4ad224159f09518c2959a3f6cc9972c0d3936
Author: olympia <[email protected]>
Date:   Wed Oct 27 15:52:30 2010 +0200

    [metadata.amazon.com] Bring back to life

diff --git a/metadata.amazon.com/addon.xml b/metadata.amazon.com/addon.xml
index 004f542..064f5a9 100644
--- a/metadata.amazon.com/addon.xml
+++ b/metadata.amazon.com/addon.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 <addon id="metadata.amazon.com"
        name="Amazon.com"
-       version="1.0.3" 
+       version="1.0.4" 
        provider-name="C-Quel + John Lockwood">
   <requires>
     <import addon="xbmc.metadata" version="1.0"/>
@@ -21,6 +21,5 @@
     <description lang="pl">Pobieraj informacje o filmach z 
www.amazon.com</description>
     <description lang="pt">Descarregar informação de filmes de 
www.amazon.com</description>
     <platform>all</platform>
-    <broken>Doesn't find any movie</broken>
   </extension>
 </addon>
diff --git a/metadata.amazon.com/amazonus.xml b/metadata.amazon.com/amazonus.xml
index 80e6fd0..5c4f627 100644
--- a/metadata.amazon.com/amazonus.xml
+++ b/metadata.amazon.com/amazonus.xml
@@ -1,115 +1,57 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!-- Initial basic version doing Studio and Thumb believed to have been 
written by C-Quel -->
-<!-- Then updated by John Lockwood to scrape Title, Year, MPAA, Runtime, 
Rating, Votes, Plot, Actors, Directors -->
-<!-- This version 1.1 dated 12/01/09 includes fix by C-Quel for processing 
results from Amazon to match recent change -->
-<!-- Version 1.1 also now supports the Writers field -->
-<scraper framework="1.0" date="2009-05-22">
+<?xml version="1.0" encoding="utf-8"?>
+<scraper framework="1.1" date="2010-10-27">
        <CreateSearchUrl dest="3">
-               <RegExp input="$$1" 
output="&lt;url&gt;http://www.amazon.com/s/ref=nb_ss_d_h_?url=search-alias%3Ddvd&amp;amp;field-keywords=\1&lt;/url&gt;";
 dest="3">
-                       <expression noclean="1"/>
+               <RegExp input="$$1" 
output="&lt;url&gt;http://www.amazon.com/s/ref=nb_ss_d_h_?url=search-alias=dvd&amp;amp;field-keywords=\1|User-Agent=Mozilla%2F4.0%20(compatible%3B%20MSIE%207.0%3B%20Windows%20NT%206.0)&lt;/url&gt;"
 dest="3">
+                       <expression noclean="1" />
                </RegExp>
        </CreateSearchUrl>
        <GetSearchResults dest="8">
                <RegExp input="$$5" output="&lt;?xml version=&quot;1.0&quot; 
encoding=&quot;iso-8859-1&quot; 
standalone=&quot;yes&quot;?&gt;&lt;results&gt;\1&lt;/results&gt;" dest="8">
-                       <RegExp input="$$1" 
output="&lt;entity&gt;&lt;title&gt;\2&lt;/title&gt;&lt;url&gt;\1&lt;/url&gt;&lt;/entity&gt;"
 dest="5">
-                               <expression repeat="yes" clear="yes" 
noclean="1">productTitle&quot;&gt;&lt;a 
href=&quot;([^&quot;]*)&quot;&gt;([^&lt;]*)&lt;/a&gt;</expression>
+                       <RegExp input="$$1" 
output="&lt;entity&gt;&lt;title&gt;\2&lt;/title&gt;&lt;url&gt;\1&lt;/url&gt;&lt;year&gt;\3&lt;/year&gt;&lt;/entity&gt;"
 dest="5">
+                               <expression repeat="yes" clear="yes" 
noclean="1">&lt;a class="title" 
href="([^"]*)"&gt;([^&lt;]*)&lt;/a&gt;.*?-&amp;nbsp;(\d{4})</expression>
                        </RegExp>
-                       <expression clear="yes" noclean="1"/>
+                       <expression clear="yes" noclean="1" />
                </RegExp>
        </GetSearchResults>
        <GetDetails clearbuffers="no" dest="3">
                <RegExp input="$$5" output="&lt;details&gt;\1&lt;/details&gt;" 
dest="3">
                        <RegExp input="$$1" 
output="&lt;title&gt;\1&lt;/title&gt;" dest="5">
-                               <expression 
noclean="1">&lt;title&gt;[Amazon.com: ]*([^:]*)</expression>
+                               <expression 
noclean="1">&lt;title&gt;Amazon.com: ([^:]*)</expression>
                        </RegExp>
                        <RegExp input="$$1" 
output="&lt;year&gt;\1&lt;/year&gt;" dest="5+">
                                <expression trim="1">[ \[\(]([0-9]{4})[ 
\]\)][^&lt;]*&lt;/span&gt;</expression>
                        </RegExp>
-                       <RegExp input="$$1" 
output="&lt;top250&gt;\1&lt;/top250&gt;" dest="5+">
-                               <expression>Top 250: 
#([0-9]*)&lt;/a&gt;</expression>
-                       </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;G&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(g)._</expression>
-                                </RegExp>
-                                <expression>(g)</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;PG&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(pg)._</expression>
-                                </RegExp>
-                                <expression>(pg)</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;PG-13&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(pg-13)._</expression>
-                                </RegExp>
-                                <expression>(pg-13)</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;R&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(r)._</expression>
-                                </RegExp>
-                                <expression>(r)</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;NC-17&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(nc-17)._</expression>
-                                </RegExp>
-                                <expression>(nc-17)</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;mpaa&gt;UNRATED&lt;/mpaa&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression>&lt;b&gt;Rating: 
&lt;/b&gt;[^_]*/(unrated)._</expression>
-                                </RegExp>
-                                <expression>(unrated)</expression>
-                        </RegExp>
-                       <RegExp input="$$1" 
output="&lt;certification&gt;\1&lt;/certification&gt;" dest="5+">
-                               <expression 
repeat="yes">Classification:&lt;/b&gt;[^&gt;]*alt=&quot;([0-9]*)&quot;</expression>
-                       </RegExp>
-                       <RegExp input="$$1" 
output="&lt;tagline&gt;\1&lt;/tagline&gt;" dest="5+">
-                               
<expression>&lt;h5&gt;Tagline:&lt;/h5&gt;([^&lt;]*)</expression>
+                       <RegExp input="$$1" 
output="&lt;mpaa&gt;\1&lt;/mpaa&gt;" dest="5+">
+                               <expression>&lt;b&gt;Rated: 
&lt;/b&gt;[^&gt;]*&gt;[^&gt;]*&gt;([^\s]*)</expression>
                        </RegExp>
                        <RegExp input="$$1" 
output="&lt;runtime&gt;\1&lt;/runtime&gt;" dest="5+">
-                               <expression trim="1">Run 
Time:&lt;/b&gt;[^0-9]*([^&lt;]*)&lt;/li&gt;</expression>
+                               <expression trim="1">Run 
Time:&lt;/b&gt;[^0-9]*([^\s]*)</expression>
                        </RegExp>
                        <RegExp input="$$1" 
output="&lt;rating&gt;\1.\2&lt;/rating&gt;&lt;votes&gt;\3&lt;/votes&gt;" 
dest="5+">
-                               <expression noclean="1">Average Customer 
Review&lt;/b&gt;[^_]*stars-([0-9])-([0-9])[^)]*&gt;([0-9]*) customer 
reviews&lt;/a&gt;\)</expression>
-                       </RegExp>
-                       <RegExp input="$$1" 
output="&lt;genre&gt;\1&lt;/genre&gt;" dest="5+">
-                               <expression 
repeat="yes">&quot;/Sections/Genres/[^/]*/&quot;&gt;([^&lt;]*)&lt;/a&gt;</expression>
+                               <expression noclean="1">Average Customer 
Review&lt;/b&gt;.*?title="([^\s]*)</expression>
                        </RegExp>
                        <RegExp input="$$1" 
output="&lt;studio&gt;\1&lt;/studio&gt;" dest="5+">
-                               <expression>Studio:&lt;/b&gt;  
([^&lt;]*)&lt;/li&gt;</expression>
-                       </RegExp>
-                       <RegExp input="$$1" 
output="&lt;outline&gt;\2&lt;/outline&gt;&lt;plot&gt;\2&lt;/plot&gt;" dest="5+">
-                               <expression trim="1">Plot 
(Outline|Summary):&lt;/h5&gt;([^&lt;]*)</expression>
+                               <expression 
trim="1">Studio:&lt;/b&gt;([^&lt;]*)&lt;/li&gt;</expression>
                        </RegExp>
                        <RegExp input="$$1" 
output="&lt;plot&gt;\1&lt;/plot&gt;" dest="5+">
-                               <expression trim="1">&lt;b&gt;Product 
Description&lt;/b&gt;&lt;br /[^&gt;]*&gt;([^&lt;]+)</expression>
+                               <expression trim="1">Product 
Description&lt;/h3&gt;([^&gt;]*&gt;)?([^&lt;]+)</expression>
+                       </RegExp>
+                       <RegExp input="$$1" 
output="&lt;thumb&gt;\1_SS500.jpg&lt;/thumb&gt;" dest="5+">
+                               <expression 
noclean="1">src="([^_]*)_S</expression>
+                       </RegExp>
+                       <RegExp input="$$9" 
output="&lt;director&gt;\1&lt;/director&gt;" dest="5+">
+                               <RegExp input="$$1" output="\1" dest="9">
+                                       <expression 
noclean="1">&lt;b&gt;Directors:&lt;/b&gt; ([^\n]*&lt;/a&gt;)</expression>
+                               </RegExp>
+                               <expression repeat="yes" 
noclean="1">[^&gt;]*&gt;([^&lt;]+)&lt;/a&gt;</expression>
+                       </RegExp>
+                       <RegExp input="$$9" 
output="&lt;actor&gt;&lt;name&gt;\1&lt;/name&gt;&lt;/actor&gt;" dest="5+">
+                               <RegExp input="$$1" output="\1" dest="9">
+                                       <expression 
noclean="1">&lt;b&gt;Actors:&lt;/b&gt; ([^\n]*&lt;/a&gt;)</expression>
+                               </RegExp>
+                               <expression repeat="yes" 
noclean="1">[^&gt;]*&gt;([^&lt;]+)&lt;/a&gt;</expression>
                        </RegExp>
-                        <RegExp input="$$1" 
output="&lt;thumb&gt;\101.L.jpg&lt;/thumb&gt;" dest="5+">
-                               <expression 
noclean="1">&quot;original_image&quot;, 
&quot;([^&quot;]*)AA2[0-9]0_\.jpg&quot;</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;credits&gt;\1&lt;/credits&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression 
noclean="1">&lt;b&gt;Writers:&lt;/b&gt; ([^\n]*&lt;/a&gt;)</expression>
-                                </RegExp>
-                                <expression noclean="1" 
repeat="yes">[^&gt;]*&gt;([^&lt;]+)&lt;/a&gt;</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;director&gt;\1&lt;/director&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression 
noclean="1">&lt;b&gt;Directors:&lt;/b&gt; ([^\n]*&lt;/a&gt;)</expression>
-                                </RegExp>
-                                <expression noclean="1" 
repeat="yes">[^&gt;]*&gt;([^&lt;]+)&lt;/a&gt;</expression>
-                        </RegExp>
-                        <RegExp input="$$9" 
output="&lt;actor&gt;&lt;name&gt;\1&lt;/name&gt;&lt;/actor&gt;" dest="5+">
-                                <RegExp input="$$1" output="\1" dest="9">
-                                        <expression 
noclean="1">&lt;b&gt;Actors:&lt;/b&gt; ([^\n]*&lt;/a&gt;)</expression>
-                                </RegExp>
-                                <expression noclean="1" 
repeat="yes">[^&gt;]*&gt;([^&lt;]+)&lt;/a&gt;</expression>
-                        </RegExp>
-                       <expression noclean="1"/>
+                       <expression noclean="1" />
                </RegExp>
        </GetDetails>
-</scraper>
+</scraper>
\ No newline at end of file

-----------------------------------------------------------------------

Summary of changes:
 .../LICENSE.txt                                    |    0
 metadata.amazon.com/addon.xml                      |    3 +-
 metadata.amazon.com/amazonus.xml                   |  120 +++++---------------
 3 files changed, 32 insertions(+), 91 deletions(-)
 copy {metadata.albums.daum.net => metadata.amazon.com}/LICENSE.txt (100%)


hooks/post-receive
-- 
Scrapers


------------------------------------------------------------------------------
Nokia and AT&T present the 2010 Calling All Innovators-North America contest
Create new apps & games for the Nokia N8 for consumers in  U.S. and Canada
$10 million total in prizes - $4M cash, 500 devices, nearly $6M in marketing
Develop with Nokia Qt SDK, Web Runtime, or Java and Publish to Ovi Store 
http://p.sf.net/sfu/nokia-dev2dev
_______________________________________________
Xbmc-addons mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/xbmc-addons

Reply via email to