Skip to content

Commit

Permalink
Latest IMDB scraper with IMPA awards
Browse files Browse the repository at this point in the history
  • Loading branch information
elan committed May 8, 2009
1 parent 1c559b1 commit a59d845
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions system/scrapers/video/imdb.xml
Original file line number Original file line Diff line number Diff line change
Expand Up @@ -50,13 +50,13 @@
<RegExp input="$$1" output="\1" dest="7"> <RegExp input="$$1" output="\1" dest="7">
<expression clear="yes">/title/([t0-9]*)/faq</expression> <expression clear="yes">/title/([t0-9]*)/faq</expression>
</RegExp> </RegExp>
<RegExp input="$$1" output="&lt;entity&gt;&lt;title&gt;\1 (\2)&lt;/title&gt;&lt;url&gt;http://$INFO[url]/title/$$7/&lt;/url&gt;&lt;id&gt;$$7&lt;/id&gt;&lt;/entity&gt;" dest="5"> <RegExp input="$$1" output="&lt;entity&gt;&lt;title&gt;\1&lt;/title&gt;&lt;year&gt;\2&lt;/year&gt;&lt;url&gt;http://$INFO[url]/title/$$7/&lt;/url&gt;&lt;id&gt;$$7&lt;/id&gt;&lt;/entity&gt;" dest="5">
<expression clear="yes" noclean="1">&lt;meta name=&quot;title&quot; content=&quot;([^&quot;]*) \(([0-9]*)\)</expression> <expression clear="yes" noclean="1">&lt;meta name=&quot;title&quot; content=&quot;([^&quot;]*) \(([0-9]*)\)</expression>
</RegExp> </RegExp>
<RegExp input="$$1" output="\1" dest="4"> <RegExp input="$$1" output="\1" dest="4">
<expression noclean="1">(&gt;&lt;a href=&quot;/title.*)</expression> <expression noclean="1">(&gt;&lt;a href=&quot;/title.*)</expression>
</RegExp> </RegExp>
<RegExp input="$$4" output="&lt;entity&gt;&lt;title&gt;\2 (\3)&lt;/title&gt;&lt;url&gt;http://$INFO[url]/title/\1/&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;&lt;/entity&gt;" dest="5+"> <RegExp input="$$4" output="&lt;entity&gt;&lt;title&gt;\2&lt;/title&gt;&lt;year&gt;\3&lt;/year&gt;&lt;url&gt;http://$INFO[url]/title/\1/&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;&lt;/entity&gt;" dest="5+">
<expression repeat="yes" noclean="1,2">&gt;&lt;a href=&quot;/title/([t0-9]*)/[^&gt;]*&gt;([^&lt;]*)&lt;/a&gt; *\(([0-9]*)</expression> <expression repeat="yes" noclean="1,2">&gt;&lt;a href=&quot;/title/([t0-9]*)/[^&gt;]*&gt;([^&lt;]*)&lt;/a&gt; *\(([0-9]*)</expression>
</RegExp> </RegExp>
<expression clear="yes" noclean="1"></expression> <expression clear="yes" noclean="1"></expression>
Expand Down Expand Up @@ -201,8 +201,8 @@
<RegExp input="$$1" output="\1" dest="4"> <RegExp input="$$1" output="\1" dest="4">
<expression clear="yes" noclean="1">value=&quot;/([^&quot;]*)/[^&quot;]*\.html&quot;&gt;</expression> <expression clear="yes" noclean="1">value=&quot;/([^&quot;]*)/[^&quot;]*\.html&quot;&gt;</expression>
</RegExp> </RegExp>
<RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\1&lt;/thumb&gt;" dest="8+"> <RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\2&lt;/thumb&gt;" dest="8+">
<expression clear="yes" noclean="1">&lt;img SRC=&quot;posters/([^&quot;]*)&quot;</expression> <expression clear="yes" noclean="1">&lt;img (SRC|src)=&quot;posters/([^&quot;]*)&quot;</expression>
</RegExp> </RegExp>
<RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\1&lt;/thumb&gt;" dest="9+"> <RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\1&lt;/thumb&gt;" dest="9+">
<expression clear="yes" repeat="yes" noclean="1">thumbs/imp_([^&gt;]*ver[^&gt;]*.jpg)&gt;</expression> <expression clear="yes" repeat="yes" noclean="1">thumbs/imp_([^&gt;]*ver[^&gt;]*.jpg)&gt;</expression>
Expand Down

0 comments on commit a59d845

Please sign in to comment.