All pastes #730638 Raw Edit

Someone

public text v1 · immutable
·published 2007-10-09 12:21 UTC
rendered paste body
<?xml version="1.0" encoding="UTF-8"?>
<scraper name="IMDb" content="movies" thumb="imdb.gif">
	<NfoUrl dest="3">
		<RegExp input="$$1" output="&lt;url&gt;http://akas.imdb.com/title/tt\1/&lt;/url&gt;&lt;id&gt;tt\1&lt;/id&gt;"  dest="3">
			<expression noclean="1">imdb.com/Title\?([0-9]*)</expression>
		</RegExp>
		<RegExp input="$$1" output="&lt;url&gt;http://akas.imdb.com/title/tt\1/&lt;/url&gt;&lt;id&gt;tt\1&lt;/id&gt;"  dest="3+">
			<expression noclean="1">imdb.com/title/tt([0-9]*)</expression>
		</RegExp>
	</NfoUrl>
	<CreateSearchUrl dest="3">
		<RegExp input="$$1" output="&lt;url&gt;http://akas.imdb.com/find?s=tt;q=\1&lt;/url&gt;" dest="3">
			<expression noclean="1"></expression>
		</RegExp>
	</CreateSearchUrl>
	<GetSearchResults dest="8">
		<RegExp input="$$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="$$1" output="\1" dest="7">
				<expression>/title/([t0-9]*)/faq</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;entity&gt;&lt;title&gt;\1 (\2)&lt;/title&gt;&lt;url&gt;http://akas.imdb.com/title/$$7/&lt;/url&gt;&lt;id&gt;$$7&lt;/id&gt;&lt;/entity&gt;" dest="5">
				<expression noclean="1">&lt;meta name=&quot;title&quot; content=&quot;([^&quot;]*) \(([0-9]*)\)</expression>
			</RegExp>
			<RegExp input="$$1" output="\1" dest="4">
				<expression noclean="1">(&lt;a href=&quot;/title.*)</expression>
			</RegExp>
			<RegExp input="$$4" output="&lt;entity&gt;&lt;title&gt;\2 (\3)&lt;/title&gt;&lt;url&gt;http://akas.imdb.com/title/\1/&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;&lt;/entity&gt;" dest="5+">
				<expression repeat="yes" noclean="1,2">&lt;a href=&quot;/title/([t0-9]*)/[^&gt;]*&gt;([^&lt;]*)&lt;/a&gt; *\(([0-9]*)</expression>
			</RegExp>
			<expression noclean="1"></expression>
		</RegExp>
	</GetSearchResults>
	<GetDetails 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 trim="1" noclean="1">&lt;title&gt;([^&lt;|^(]*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;year&gt;\1&lt;/year&gt;" dest="5+">
				<expression>a href=&quot;/Sections/Years/([0-9]*)&quot;&gt;</expression>
			</RegExp>
			<RegExp input="$$1" output="\1" dest="6">
				<expression noclean="1">&lt;h5&gt;Director(.*)&lt;h5&gt;Writer</expression>
			</RegExp>
			<RegExp input="$$6" output="&lt;director&gt;\1&lt;/director&gt;" dest="5+">
			  <expression repeat="yes">&lt;a href=&quot;/name/[^&gt;]*&gt;([^&lt;]*)&lt;</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;top250&gt;\1&lt;/top250&gt;" dest="5+">
				<expression>Top 250[^0-9]*([0-9]*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;mpaa&gt;\1&lt;/mpaa&gt;" dest="5+">
				<expression>MPAA&lt;/a&gt;:&lt;/h5&gt;(.[^&lt;]*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;tagline&gt;\1&lt;/tagline&gt;" dest="5+">
				<expression>&lt;h5&gt;Tagline:&lt;/h5&gt;([^&lt;]*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;runtime&gt;\1&lt;/runtime&gt;" dest="5+">
				<expression trim="1">&lt;h5&gt;Runtime:&lt;/h5&gt;[^0-9]*([^&lt;]*)</expression>
			</RegExp>
			<RegExp input="$$1" output="\1" dest="6">
	                        <expression noclean="1">&lt;div class=&quot;photo&quot;&gt;[^&lt;]*&lt;a[^&lt;]*&lt;img border=&quot;0&quot; alt=&quot;[^&quot;]*&quot; title=&quot;[^&quot;]*&quot; src=&quot;([^&quot;]*)&quot; height=&quot;[^&quot;]*&quot; width=&quot;[^&quot;]*&quot;&gt;</expression>
 			</RegExp>
                        <RegExp input="$$6" output="\1f.jpg" dest="7">
				<expression noclean="1">(.*)m\.jpg</expression>
                        </RegExp>
			<RegExp input="$$7" output="&lt;thumbs&gt;&lt;thumb&gt;\1&lt;/thumb&gt;&lt;/thumbs&gt;" dest="5+">
				<expression noclean="1"></expression>
                        </RegExp>
			<RegExp input="$$1" output="\1" dest="6">
				<expression noclean="1">&lt;h5&gt;Writer(.*)&lt;h5&gt;Release Date[^&lt;]*&lt;/h5&gt;</expression>
			</RegExp>
			<RegExp input="$$7" output="&lt;credits&gt;\1&lt;/credits&gt;" dest="5+">
				<RegExp input="$$6" output=" / \1" dest="7">
					<expression repeat="yes">&lt;a href=&quot;/name/[^&gt;]*&gt;([^&lt;]*)&lt;</expression>
				</RegExp>
				<expression> / (.*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;rating&gt;\1&lt;/rating&gt;&lt;votes&gt;\2&lt;/votes&gt;" dest="5+">
				<expression>&lt;b&gt;User Rating:&lt;/b&gt;[^&lt;]*&lt;b&gt;([0-9.]+)/10&lt;/b&gt;[^&lt;]*&lt;small&gt;\(&lt;a href=&quot;ratings&quot;&gt;([0-9,]+) votes&lt;/a&gt;\)&lt;/small&gt;</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;genre&gt;\1&lt;/genre&gt;" dest="5+">
				<expression repeat="yes">&quot;/Sections/Genres/[^/]*/&quot;&gt;([^&lt;]*)&lt;/a&gt;</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;studio&gt;\1&lt;/studio&gt;" dest="5+">
				<expression repeat="yes">&quot;/company/[^/]*/&quot;&gt;([^&lt;]*)&lt;/a&gt;</expression>
			</RegExp>
			<RegExp input="$$1" output="\1" dest="7">
				<expression noclean="1">first billed only: &lt;/b&gt;&lt;/td&gt;&lt;/tr&gt;(.*)</expression>
			</RegExp>
			<RegExp input="$$1" output="&lt;outline&gt;\2&lt;/outline&gt;&lt;plot&gt;\2&lt;/plot&gt;" dest="5+">
				<expression>Plot (Outline|Summary):&lt;/h5&gt;([^&lt;]*)</expression>
			</RegExp>

<!--	*********** CURRENTLY DISABLED FULL GETCAST SCRAPE ENABLED BELOW *********** -->
<!--			<RegExp input="$$1" output="&lt;actor&gt;&lt;thumbs&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2m.jpg&lt;/thumb&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2t.jpg&lt;/thumb&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2f.jpg&lt;/thumb&gt;&lt;/thumbs&gt;&lt;name&gt;\3&lt;/name&gt;&lt;role&gt;\5&lt;/role&gt;&lt;/actor&gt;" dest="5+">
				<expression repeat="yes" noclean="1,2" trim="3,5">&lt;img src=&quot;(http://ia.media-imdb.com/media/imdb/([^&quot;]*)?t\.jpg&quot;)?[^&gt;]*[^&quot;]*&quot;nm&quot;&gt;&lt;a href=&quot;[^&quot;]*&quot;&gt;([^&lt;]*)&lt;[^&quot;]*&quot;ddd&quot;&gt; ... [^&quot;]*&quot;char&quot;&gt;([^A-Z]*)?([^&lt;]*)</expression>
			</RegExp> -->

			<RegExp input="$$2" output="&lt;url function=&quot;GetPlot&quot;&gt;http://akas.imdb.com/title/\1/plotsummary&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;" dest="5+">
				<expression></expression>
			</RegExp>
			<RegExp input="$$2" output="&lt;url function=&quot;GetCast&quot;&gt;http://akas.imdb.com/title/\1/fullcredits#cast&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;" dest="5+">
				<expression></expression>
			</RegExp>
			<RegExp input="$$2" output="&lt;url function=&quot;GetIMPALink&quot;&gt;http://akas.imdb.com/title/\1/posters&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;" dest="5+">
				<expression></expression>
			</RegExp>
			<expression noclean="1"></expression>
		</RegExp>
	</GetDetails>
	<GetPlot dest="5">
		<RegExp input="$$2" output="&lt;details&gt;&lt;plot&gt;\1&lt;/plot&gt;&lt;/details&gt;" dest="5">
			<RegExp input="$$1" output="\1" dest="2">
				<expression>&lt;p class="plotpar"&gt;\n([^\n]*)</expression>
			</RegExp>
			<expression noclean="1"></expression>
		</RegExp>
	</GetPlot>
	<GetCast dest="5">
		<RegExp input="$$2" output="&lt;details&gt;\1&lt;/details&gt;" dest="5+">
			<RegExp input="$$1" output="&lt;actor&gt;&lt;thumbs&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2m.jpg&lt;/thumb&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2t.jpg&lt;/thumb&gt;&lt;thumb&gt;http://ia.media-imdb.com/media/imdb/\2f.jpg&lt;/thumb&gt;&lt;/thumbs&gt;&lt;name&gt;\3&lt;/name&gt;&lt;role&gt;\5&lt;/role&gt;&lt;/actor&gt;" dest="2">
				<expression repeat="yes" noclean="1,2" trim="3,5">&lt;img src=&quot;(http://ia.media-imdb.com/media/imdb/([^&quot;]*)?t\.jpg&quot;)?[^&gt;]*[^&quot;]*&quot;nm&quot;&gt;&lt;a href=&quot;[^&quot;]*&quot;&gt;([^&lt;]*)&lt;[^&quot;]*&quot;ddd&quot;&gt; ... [^&quot;]*&quot;char&quot;&gt;([^A-Z]*)?([^&lt;]*)</expression>
			</RegExp>
			<expression noclean="1"></expression>
		</RegExp>
	</GetCast>
	<GetIMPALink dest="5">
		<RegExp input="$$1" output="&lt;details&gt;&lt;url function=&quot;GetIMPAPosters&quot;&gt;http://www.impawards.com/\1&lt;/url&gt;&lt;id&gt;\1&lt;/id&gt;&lt;/details&gt;" dest="5+">
			<expression noclean="1">&lt;a href=&quot;http://www.impawards.com/([^&quot;]*)&quot;&gt;</expression>
		</RegExp>
	</GetIMPALink>
	<GetIMPAPosters dest="5">
		<RegExp input="$$1" output="&lt;details&gt;&lt;url function=&quot;GetIMPAPosters&quot;&gt;http://www.impawards.com/\1&lt;/url&gt;&lt;/details&gt;" dest="5">
			<expression>&lt;meta http-equiv=&quot;REFRESH&quot; content=&quot;0;URL=[^/]*/([^&quot;]*)&quot;&gt;</expression>
		</RegExp>
		<RegExp input="$$1" output="\1" dest="4">
			<expression noclean="1">value=&quot;/([^&quot;]*)/[^&quot;]*\.html&quot;&gt;</expression>
		</RegExp>
		<RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\1&lt;/thumb&gt;" dest="7">
			<expression noclean="1">&lt;img SRC=&quot;posters/([^&quot;]*)&quot;</expression>
		</RegExp>
		<RegExp input="$$1" output="&lt;thumb&gt;http://www.impawards.com/$$4/posters/\1&lt;/thumb&gt;" dest="6+">
			<expression repeat="yes" noclean="1">thumbs/imp_([^&gt;]*)&gt;</expression>
		</RegExp>
		<RegExp input="$$1" output="&lt;details&gt;&lt;thumbs&gt;$$7$$6&lt;/thumbs&gt;&lt;/details&gt;" dest="5+">
			<expression repeat="yes" noclean="1"></expression>
		</RegExp>
	</GetIMPAPosters>
</scraper>