encode Common Crawl discovery query parameters
CI / compose (push) Failing after 5m50s

This commit is contained in:
Marco0300
2026-09-05 11:45:50 +02:00
parent e3306966cc
commit 0f8c1988b2
+1 -1
View File
@@ -362,7 +362,7 @@ class ApprovedDirectorySource(GatedSource):
url="https://query.wikidata.org/sparql?format=json&"+urlencode({"query":sparql}) url="https://query.wikidata.org/sparql?format=json&"+urlencode({"query":sparql})
payload, _ = _HttpJsonSource()._get_json(url); records=[normalize_record({"name":x.get("itemLabel",{}).get("value",""),"website":x.get("website",{}).get("value","")}) for x in payload.get("results",{}).get("bindings",[])] payload, _ = _HttpJsonSource()._get_json(url); records=[normalize_record({"name":x.get("itemLabel",{}).get("value",""),"website":x.get("website",{}).get("value","")}) for x in payload.get("results",{}).get("bindings",[])]
return DiscoveryPage(records[:limit],metadata={"adapter":self.source_code,"provider":provider,"record_count":len(records)}) return DiscoveryPage(records[:limit],metadata={"adapter":self.source_code,"provider":provider,"record_count":len(records)})
index="https://index.commoncrawl.org/CC-MAIN-2026-30-index?url="+query+"&output=json&filter=status:200&collapse=urlkey" index="https://index.commoncrawl.org/CC-MAIN-2026-30-index?"+urlencode({"url":query,"output":"json","filter":"status:200","collapse":"urlkey"})
payload, _ = _HttpJsonSource()._get_json(index); records=[normalize_record({"name":str(x.get("url","")).split('/')[2] if '://' in str(x.get("url","")) else x.get("url", ""),"website":x.get("url","")}) for x in (payload if isinstance(payload,list) else [])] payload, _ = _HttpJsonSource()._get_json(index); records=[normalize_record({"name":str(x.get("url","")).split('/')[2] if '://' in str(x.get("url","")) else x.get("url", ""),"website":x.get("url","")}) for x in (payload if isinstance(payload,list) else [])]
return DiscoveryPage(records[:limit],metadata={"adapter":self.source_code,"provider":provider,"record_count":len(records)}) return DiscoveryPage(records[:limit],metadata={"adapter":self.source_code,"provider":provider,"record_count":len(records)})