feature: update funkcí pro stahování dat

funkce fetch_set a download_heslare byly upraveny pro stahování dat nejen z OAI-PMH API, ale nově i z API digiarchivu (= osoby se nově nestahují z hesláře osob, ale z facetek digiarchivu, kde mají osoby přidělené "role" nálezce/vedoucí)

amcr_viewer/amcr_codelists.py

@@ -103,13 +103,19 @@ def load_all_data():
     return categorized_data
 
 
-def fetch_set(internal_name, api_set, task=None):
+def fetch_set(base_url, internal_name, api_set, task=None):
     dataset = []
-    params = {
+    params_amcr = {
         "verb": "ListRecords",
         "metadataPrefix": "oai_dc",
         "set": api_set
     }
+    params_da = {
+        "entity": "samostatny_nalez" if internal_name == "nalezce" else "akce",
+        "rows": 0,
+        "noFacets": "false",
+        "onlyFacets": "true"
+    }
 
     while True:
         # Check for cancellation at each iteration
@@ -117,7 +123,8 @@ def fetch_set(internal_name, api_set, task=None):
             return None
 
         try:
-            response = requests.get(BASE_URL, params=params, timeout=30)
+            if "digiarchiv" not in base_url:
+                response = requests.get(base_url, params=params_amcr, timeout=30)
                 response.raise_for_status()
                 root = ET.fromstring(response.content)  # nosec
 
@@ -179,7 +186,7 @@ def fetch_set(internal_name, api_set, task=None):
                 # Pagination
                 token = root.find('.//oai:resumptionToken', NS)
                 if token is not None and token.text:
-                params = {
+                    params_amcr = {
                         "verb": "ListRecords",
                         "resumptionToken": token.text
                     }
@@ -187,6 +194,25 @@ def fetch_set(internal_name, api_set, task=None):
                 else:
                     break
             
+            else:
+                response = requests.get(base_url, params=params_da, timeout=30)
+                response.raise_for_status()
+                data_json = response.json()
+
+                records = data_json['facet_counts']['facet_fields'][api_set]
+
+                for r in records:
+
+                    nazev = r["name"]
+
+                    dataset.append({
+                            'Název': nazev,
+                            'Kód': nazev,
+                            'Kategorie': internal_name
+                        })
+                
+                break                    
+
         except Exception as e:
             QgsMessageLog.logMessage(
                 f"Chyba u setu {api_set}: {e}",
@@ -201,8 +227,13 @@ def download_heslare(task=None):
     ensure_codelists_dir()
     all_data = []
     total_sets = len(slovnicek)
+# index, (interni, api_nazev)
+    for index, (key, value) in enumerate(slovnicek.items()):
+
+        base_url = value[0]
+        interni = key
+        api_nazev = value[1]
 
-    for index, (interni, api_nazev) in enumerate(slovnicek.items()):
         # Check if the user cancelled the task via the QGIS taskbar
         if task and task.isCanceled():
             return False
@@ -212,7 +243,7 @@ def download_heslare(task=None):
             "AMČR", Qgis.Info)
 
         # Pass the task correctly to the updated fetch function
-        data = fetch_set(interni, api_nazev, task=task)
+        data = fetch_set(base_url, interni, api_nazev, task=task)
 
         if data is None:
             return False  # Cancelled mid-download