fandecinema.com
#1
hello I come to start a scrap for the site http://www.fan-de-cinema.com and I blocks already. If someone could help me (sorry for my bad english)
Code:
<?xml version="1.0" encoding="utf-8" standalone="yes"?>

<scraper name="fandecinema" content="movies" thumb="fandecinema.jpg">

    <NfoUrl dest="3">

        <RegExp input="$$1" output="http://www.fan-de-cinema.com/films/\1.html"  dest="3">

            <expression clear="yes" noclean="1">fan-de-cinema.com/films/([^\.]*)\.html</expression>

        </RegExp>

    </NfoUrl>



    <CreateSearchUrl dest="3">

        <RegExp input="$$1" output="http://www.fan-de-cinema.com/cherche.html?f=1&amp;a=1&amp;c=1&amp;s=1&amp;recherche=\1&amp;go.x=1&amp;go.y=1" dest="3">

            <expression noclean="1"></expression>
        </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 cache=&quot;\1.html&quot;&gt;http://www.fan-de-cinema.com/films/\1.html&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;&lt;/entity&gt;" dest="5">

                <expression repeat="yes">&lt;div class=&quot;titrefilm&quot;[^/]+/films/([^\.]*)\.html&quot;&gt;([^&lt;]*)&lt;/a&gt;&lt;/div&gt;</expression>

            </RegExp>

            <expression noclean="1"></expression>

        </RegExp>

    </GetSearchResults>



    <GetDetails clearbuffers="no" dest="3">

        <RegExp input="$$5" output="&lt;details&gt;\1&lt;/details&gt;" dest="3">

<!-- TITLE -->    

              
                        <RegExp input="$$1" output="&lt;title&gt;\1&lt;/title&gt;" dest="5+">

                <expression trim="1" noclean="1">&lt;h1&gt;([^&lt;]*)&lt;</expression>

            </RegExp>
                        
                    </RegExp>

    </GetDetails>

</scraper>
Reply
#2
i m not say where come the probleme :GetSearchResults
Reply

Logout Mark Read Team Forum Stats Members Help
fandecinema.com1