2009-04-26, 13:22
you need to set the SearchStringEncoding on the CreateSearchUrl function
spiff Wrote:you need to set the SearchStringEncoding on the CreateSearchUrl function
<RegExp input="$$1" output="<url function="GetThumbnailLink">http://www.cinefacts.de/kino/film/\1/\2/plakate.html</url>" dest="5+">
<expression repeat ="yes"><a href="/kino/film/([0-9]*)/([^\/]*)/plakate.html"></expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Thumbnail-->
<GetThumbnailLink clearbuffers="no" dest="6">
<RegExp input="$$1" output="<details><url function="GetThumbnail">http://www.cinefacts.de/kino/film/\1</url></details>" dest="6">
<expression repeat="yes" noclean="1"><a href="/kino/film/([^"]+)">[^<]*<img</expression>
</RegExp>
</GetThumbnailLink>
<GetThumbnail dest="5">
<RegExp input="$$2" output="<details><thumbs>\1</thumbs></details>" dest="5+">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="2">
<expression>="/kino/plakat/([^"]*)"</expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetThumbnail>
spiff Wrote:why are you repeating in getthumbnaillink? i don't get what you are trying to achieve and hence it is impossible to help you
<RegExp input="$$1" output="<url function="GetThumbnailLink" cache="some.xml" >http://www.cinefacts.de/kino/film/\1/\2/plakate.html</url>" dest="5+">
<expression repeat ="yes"><a href="/kino/film/([0-9]*)/([^\/]*)/plakate.html"></expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Thumbnail-->
<GetThumbnailLink clearbuffers="no" dest="6">
<RegExp input="$$7" output="<details>\1></details>" dest="6">
<RegExp input="$$1" output=";<url function="GetThumbnail">http://www.cinefacts.de/kino/film/\1</url>" dest="7+">
<expression repeat="yes" noclean="1"><a href="/kino/film/([^"]+)">[^<]*<img</expression>
<RegExp input="" output="<url function="CollectThumbnails>"></url>
<expression/>
</RegExp>
</RegExp>
</GetThumbnailLink>
<GetThumbnail clearbuffers="no" dest="5">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="8">
<expression>="/kino/plakat/([^"]*)"</expression>
</RegExp>
<RegExp input="" output="<details></details> dest="5">
<expression noclean="1"/>
</RegExp>
</GetThumbnail>
<CollectThumbnails dest="2">
<RegExp input="$$8" output="<details><thumbs>\1</thumbs></details>" dest="">
<expression noclean="1"/>
</RegExp>
</CollectThumbnails>
<RegExp input="$$1" output="<url function="GetThumbnailLink" cache="http://www.google.de" >http://www.cinefacts.de/kino/film/\1/\2/plakate.html</url>" dest="5+">
<expression repeat ="yes"><a href="/kino/film/([0-9]*)/([^\/]*)/plakate.html"></expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Thumbnail-->
<GetThumbnailLink clearbuffers="no" dest="6">
<RegExp input="$$7" output="<details>\1</details>" dest="6">
<RegExp input="$$1" output="<url function="GetThumbnail">http://www.cinefacts.de/kino/film/\1</url>" dest="7+">
<expression repeat="yes" noclean="1"><a href="/kino/film/([^"]+)">[^<]*<img</expression>
<RegExp input="" output="<url function="CollectThumbnails"></url>"
<expression/>
</RegExp>
</RegExp>
</GetThumbnailLink>
<GetThumbnail clearbuffers="no" dest="5">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="8">
<expression>="/kino/plakat/([^"]*)"</expression>
</RegExp>
<RegExp input="" output="<details></details>" dest="5">
<expression noclean="1"/>
</RegExp>
</GetThumbnail>
<CollectThumbnails dest="2">
<RegExp input="$$8" output="<details><thumbs>\1</thumbs></details>" dest="2">
<expression noclean="1"/>
</RegExp>
</CollectThumbnails>
</scraper>
<RegExp input="$$1" output="<url function="GetThumbnailLink" cache="some.xml">http://www.cinefacts.de/kino/film/\1/\2/plakate.html</url>" dest="5+">
<expression repeat ="yes"><a href="/kino/film/([0-9]*)/([^\/]*)/plakate.html"></expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Thumbnail-->
<GetThumbnailLink clearbuffers="no" dest="6">
<RegExp input="$$7" output="<details>\1</details>" dest="6">
<RegExp input="$$1" output="<url function="GetThumbnail">http://www.cinefacts.de/kino/film/\1</url>" dest="7">
<expression repeat="yes" noclean="1"><a href="/kino/film/([^"]+)">[^<]*<img</expression>
</RegExp>
<RegExp input="" output="<url function="CollectThumbnails" cache="some.xml" >http://doesnt.matter</url>" dest="7+">
<expression/>
</RegExp>
</RegExp>
</GetThumbnailLink>
<GetThumbnail clearbuffers="no" dest="5">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="8+">
<expression>="/kino/plakat/([^"]*)"</expression>
</RegExp>
<RegExp input="" output="<details></details>" dest="5">
<expression noclean="1"/>
</RegExp>
</GetThumbnail>
<CollectThumbnails dest="2">
<RegExp input="$$8" output="<details><thumbs>\1</thumbs></details>" dest="2">
<expression noclean="1"/>
</RegExp>
</CollectThumbnails>
</scraper>
spiff Wrote:Code:<RegExp input="$$1" output="<url function="GetThumbnailLink" cache="some.xml">http://www.cinefacts.de/kino/film/\1/\2/plakate.html</url>" dest="5+">
<expression repeat ="yes"><a href="/kino/film/([0-9]*)/([^\/]*)/plakate.html"></expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Thumbnail-->
<GetThumbnailLink clearbuffers="no" dest="6">
<RegExp input="$$7" output="<details>\1</details>" dest="6">
<RegExp input="$$1" output="<url function="GetThumbnail">http://www.cinefacts.de/kino/film/\1</url>" dest="7">
<expression repeat="yes" noclean="1"><a href="/kino/film/([^"]+)">[^<]*<img</expression>
</RegExp>
<RegExp input="" output="<url function="CollectThumbnails" cache="some.xml" >http://doesnt.matter</url>" dest="7+">
<expression/>
</RegExp>
</RegExp>
</GetThumbnailLink>
<GetThumbnail clearbuffers="no" dest="5">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="8+">
<expression>="/kino/plakat/([^"]*)"</expression>
</RegExp>
<RegExp input="" output="<details></details>" dest="5">
<expression noclean="1"/>
</RegExp>
</GetThumbnail>
<CollectThumbnails dest="2">
<RegExp input="$$8" output="<details><thumbs>\1</thumbs></details>" dest="2">
<expression noclean="1"/>
</RegExp>
</CollectThumbnails>
</scraper>
<!--Poster URL-->
<RegExp input="$$1" output="<url function="GetPosters">http://www.cinefacts.de/kino/film/\1/\2/\3/\4/plakat.html</url>" dest="5+">
<expression repeat="yes">"/kino/film/([0-9]*)/([^\/]*)/([^\/]*)/([^\/]*)/plakat.html"\)</expression>
</RegExp>
<expression noclean="1"/>
</RegExp>
</GetDetails>
<!--Poster-->
<GetPosters clearbuffers="no" dest="5">
<RegExp input="$$2" output="<?xml version=<details><thumbs>\1</thumbs></details>" dest="5+">
<RegExp input="$$1" output="<thumb>http://www.cinefacts.de/kino/plakat/\1</thumb>" dest="2">
<expression repeat="yes">href="/kino/plakat/([^"]*)"</expression>
</RegExp>
<expression noclean="1"></expression>
</RegExp>
</GetPosters>
</scraper>