-
-
Save mariushoch/ae4538741ec3e5409dfa4e9a90c346dc to your computer and use it in GitHub Desktop.
Find items with conflicting sitelinks, for a given list of item ids.
This file contains 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
<?php | |
function errEcho( $str ) { | |
file_put_contents( 'php://stderr', $str, FILE_APPEND ); | |
} | |
if ( $argc !== 2 || $argv[1] === '--help' ) { | |
errEcho( "Find items with conflicting sitelinks, for a given list of item ids.\n\n" ); | |
errEcho( "Usage: findSiteLinkConflicts [--help] file-with-itemids\n" ); | |
exit( 0 ); | |
} | |
$fileName = $argv[1]; | |
$file = fopen( $fileName, 'r' ); | |
if ( !$file ) { | |
errEcho( "Could not open $fileName for reading.\n" ); | |
exit( 1 ); | |
} | |
while ( ( $line = fgets( $file ) ) !== false ) { | |
$itemId = trim( $line ); | |
if ( !preg_match( '/^Q[1-9]\d+\z/', $itemId ) ) { | |
errEcho( "Skipping input row: \"$itemId\"\n" ); | |
continue; | |
} | |
$subjectEntity = json_decode( | |
file_get_contents( | |
'https://www.wikidata.org/w/api.php?action=wbgetentities&ids=' . urlencode( $itemId ) . | |
'&props=sitelinks&format=json' | |
), | |
true | |
); | |
if ( !isset( $subjectEntity['entities'] ) ) { | |
errEcho( "Failed reading Item $itemId\n" ); | |
continue; | |
} | |
errEcho( "Checking sitelinks for Item $itemId\n" ); | |
$requestCount = 0; | |
$conflicts = []; | |
$siteLinks = $subjectEntity['entities'][$itemId]['sitelinks']; | |
foreach ( $siteLinks as $siteLink ) { | |
$siteId = $siteLink['site']; | |
$pageTitle = $siteLink['title']; | |
$apiJson = file_get_contents( | |
'https://www.wikidata.org/w/api.php?action=wbgetentities&sites=' . urlencode( $siteId ) . | |
'&titles=' . urlencode( $pageTitle ) . '&props=&format=json' | |
); | |
$apiResponse = json_decode( $apiJson, true ); | |
$requestCount++; | |
if ( $requestCount % 10 === 0 ) { | |
errEcho( "Got 10 sitelinks for $itemId\n" ); | |
} | |
if ( !isset( $apiResponse['entities'] ) ) { | |
continue; | |
} | |
$conflicts[] = array_keys( $apiResponse['entities'] )[0]; | |
} | |
$conflicts = array_diff( array_unique( $conflicts ), [ $itemId ] ); | |
echo "Item $itemId conflicts with: " . implode( ', ', $conflicts ) . "\n"; | |
} | |
errEcho( "\nDone\n" ); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment