Created
October 2, 2023 12:40
-
-
Save robertz/2a5885fe0ccbb48d8ffc8cf633b9c995 to your computer and use it in GitHub Desktop.
Read page metadata using jSoup in ColdFusion
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
component { | |
property name="jSoup" inject="javaLoader:org.jsoup.Jsoup"; | |
function spider( required string link ){ | |
var meta = { "url" : arguments.link, "alt_images" : [] }; | |
try { | |
var jsDoc = jSoup | |
.connect( link ) | |
.followRedirects( true ) | |
.userAgent( "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0" ) | |
.get(); | |
var el = jsDoc.select( "meta" ); | |
var filtered = el.filter( ( item ) => { | |
return item.attr( "name" ).find( "twitter:" ) || | |
item.attr( "name" ).find( "og:" ) || | |
item.attr( "property" ).find( "twitter:" ) || | |
item.attr( "property" ).find( "og:" ); | |
} ); | |
filtered.each( function( i ){ | |
len( i.attr( "name" ) ) ? meta[ i.attr( "name" ) ] = i.attr( "content" ) : meta[ i.attr( "property" ) ] = i.attr( "content" ); | |
} ); | |
if ( !meta.keyExists( "image" ) ) { | |
el = jsDoc.select( "img" ); | |
el.each( function( item ){ | |
if ( item.attributes().hasKey( "src" ) ) { | |
if ( | |
item.attr( "src" ).findNoCase( ".jpg" ) || item.attr( "src" ).findNoCase( ".jpeg" ) || item | |
.attr( "src" ) | |
.findNoCase( ".gif" ) | |
) { | |
meta.alt_images.append( item.attr( "src" ) ); | |
} | |
} else if ( item.attributes().hasKey( "data-img-url" ) ) { | |
if ( | |
item.attr( "data-img-url" ).findNoCase( ".jpg" ) || item | |
.attr( "data-img-url" ) | |
.findNoCase( ".jpeg" ) || item.attr( "data-img-url" ).findNoCase( ".gif" ) | |
) { | |
meta.alt_images.append( item.attr( "data-img-url" ) ); | |
} | |
} | |
} ); | |
} | |
} catch ( any e ) { | |
// todo: log exception | |
} | |
return meta; | |
} | |
function extract_text( required string html ){ | |
var jsDoc = jSoup.parse( html ); | |
var ps = jsDoc.select( "p" ); | |
var t = []; | |
ps.each( function( el ){ | |
t.append( "<p>" & el.text() & "</p>" ); | |
} ) | |
res = arrayToList( t, "" ); | |
return res; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment