labels

sparql.py

@@ -3,24 +3,16 @@
 sparql = SPARQLWrapper("https://query.wikidata.org/bigdata/namespace/wdq/sparql")
 sparql.setQuery("""
 PREFIX wd: <http://www.wikidata.org/entity/>
-PREFIX wdt: <http://www.wikidata.org/prop/direct/>
-PREFIX wikibase: <http://wikiba.se/ontology#>
-PREFIX xsd:   <http://www.w3.org/2001/XMLSchema#>
-
-SELECT DISTINCT ?episode ?episodeLabel ?number ?date WHERE {
-  ?episode wdt:P31 wd:Q838795 .
-  ?episode wdt:P361 wd:Q13915 .
-  ?episode wdt:P433 ?number .
-  ?episode wdt:P577 ?date
-
-  SERVICE wikibase:label {
-    bd:serviceParam wikibase:language "en" .
-  }
- } ORDER BY xsd:integer(?number)
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+SELECT DISTINCT ?l WHERE {
+  wd:Q18615489 rdfs:label ?l .
+}
 """)
 sparql.setReturnFormat(JSON)
 results = sparql.query().convert()
 
+langs = []
 for result in results["results"]["bindings"]:
-    print(result["episode"]["value"], result["episodeLabel"]["value"])
+    langs.append(result["l"]["xml:lang"])
 
+print(langs)

xkcd-labels.py

@@ -0,0 +1,36 @@
+from SPARQLWrapper import SPARQLWrapper, JSON
+
+all_langs=['af', 'an', 'ast', 'bar', 'bm', 'br', 'ca', 'co', 'cs', 'cy', 'da', 'de', 'de-at', 'de-ch', 'en',
+    'en-ca', 'en-gb', 'eo', 'es', 'et', 'eu', 'fi', 'fr', 'frc', 'frp', 'fur', 'ga', 'gd', 'gl', 'gsw', 'hr',
+    'hu', 'ia', 'id', 'ie', 'io', 'it', 'jam', 'kab', 'kg', 'lb', 'li', 'lij', 'lt', 'lv', 'mg', 'min', 'ms',
+    'nap', 'nb', 'nds', 'nds-nl', 'nl', 'nn', 'nrm', 'oc', 'pap', 'pcd', 'pl', 'pms', 'prg', 'pt', 'pt-br',
+    'rgn', 'rm', 'ro', 'sc', 'scn', 'sco', 'sk', 'sr-el', 'sv', 'sw', 'tr', 'vec', 'vi', 'vls', 'vmf', 'vo',
+    'wa', 'wo', 'zu', 'fo', 'is', 'kl']
+
+for i in range(1,1609):
+    sparql = SPARQLWrapper("https://query.wikidata.org/bigdata/namespace/wdq/sparql")
+    sparql.setQuery("""
+    PREFIX wd: <http://www.wikidata.org/entity/>
+    PREFIX wdt: <http://www.wikidata.org/prop/direct/>
+    SELECT DISTINCT ?episode ?number ?title WHERE {
+      ?episode wdt:P31 wd:Q838795 .
+      ?episode wdt:P361 wd:Q13915 .
+      ?episode wdt:P433 '{}' .
+      ?episode rdfs:label ?title .
+    } 
+    """.format(i))
+    sparql.setReturnFormat(JSON)
+    results = sparql.query().convert()
+
+    used_langs = []
+    for result in results["results"]["bindings"]:
+
+        episode = result['episode']['value'].rsplit('/',1)[-1]
+        lang = result["title"]["xml:lang"]
+        title  = result["title"]['value']
+        used_langs.append(lang)
+
+    missing_langs = set(all_langs) - set(used_langs)
+
+    for m in missing_langs:
+        print(episode,'L'+ lang,title)

xkcd-scraper.py

@@ -108,7 +108,7 @@ def ordinal(value):
     episodenumber = urlbit.replace("/","")
 
     if int(episodenumber) > latest_imported_episode:
-        descriptions = "strip de xkcd n° " + episodenumber + ", Folge des Webcomics xkcd, " + ordinal(episodenumber) + " strip of the webcomic xkcd"
+        descriptions = "strip de xkcd n°" + episodenumber + ", Folge des Webcomics xkcd, " + ordinal(episodenumber) + " strip of the webcomic xkcd"
         #date = a.attrs.get('title') or ""
         date = "+0000000" + '-'.join(["{0:0>2}".format(v) for v in a.attrs.get('title').split("-")]) + "T00:00:00Z/11" or ""