- adds RISM demo crawler

command_line_scripts/indexRISM.php

@@ -0,0 +1,40 @@
+<?php
+namespace ADWLM\IncipitSearch;
+
+require 'vendor/autoload.php';
+
+
+/**
+ * This is to be called from command line to index the Gluck Gesamtausgabe catalog.
+ * ATTENTION: this must be called from the same directory as index.php
+ * or paths will be wrong
+ *
+ *
+ * Copyright notice
+ *
+ * (c) 2016
+ * Anna Neovesky  [email protected]
+ * Gabriel Reimers [email protected]
+ *
+ * Digital Academy www.digitale-akademie.de
+ * Academy of Sciences and Literatur | Mainz www.adwmainz.de
+ *
+ * Licensed under The MIT License (MIT)
+ *
+ * @package ADWLM\IncipitSearch
+ */
+
+
+/*
+ *
+ * ATTENTION:
+ * This only crawls a small sample of RISM and is only for demo purposes
+ *
+ */
+
+echo "====================\nATTENTION\n=======================\nThe RISM crawler is only for demo purposes and only crawls a small subset of RISM.\nThis is not fit for production\n\n";
+
+$crawler = new RISMIncipitCrawler();
+
+$crawler->createIndex();
+$crawler->crawlCatalog();

src/RISMIncipitCrawler.php

@@ -112,7 +112,7 @@ public function crawlCatalog()
     {
 
         $startID = 400110660;
-        $endID =   400110862;
+        $endID =   400110999;
 
         for ($i = $startID; $i < $endID; $i++) {
             $url = "https://opac.rism.info/id/rismid/" . $i . "?format=marc";