Refactor JSON file retrieval to use regex for improved accuracy in matching file links and streamline file name extraction.

test_regex.py

@@ -0,0 +1,49 @@
+import requests
+import re
+import os
+
+def get_json_files_from_folder(folder):
+    base_url = "https://git.gald.site/gald/galdistream/src/branch/main/resources/"
+    url = base_url + folder
+    r = requests.get(url, timeout=10)
+    r.raise_for_status()
+    
+    # Hledáme JSON soubory pomocí regex
+    json_pattern = r'href="(/gald/galdistream/src/branch/main/resources/[^"]*\.json)"'
+    matches = re.findall(json_pattern, r.text)
+    
+    files = []
+    for match in matches:
+        # Extrahujeme pouze název souboru
+        file_name = match.split("/")[-1]
+        files.append(file_name)
+    return files
+
+def update_json_db():
+    base_url_raw = "https://git.gald.site/gald/galdistream/raw/branch/main/resources/"
+    folders = ["movies", "series"]
+    all_files = []
+    for folder in folders:
+        try:
+            files = get_json_files_from_folder(folder)
+            print(f"Nalezené soubory v {folder}: {files}")
+            all_files += [f"{folder}/{file}" for file in files]
+        except Exception as e:
+            print(f"Chyba při získávání souborů ze složky {folder}: {e}")
+    
+    print(f"Celkem souborů ke stažení: {len(all_files)}")
+    for file in all_files:
+        url = base_url_raw + file
+        local_path = "resources/" + file
+        try:
+            r = requests.get(url, timeout=10)
+            r.raise_for_status()
+            os.makedirs(os.path.dirname(local_path), exist_ok=True)
+            with open(local_path, "wb") as f:
+                f.write(r.content)
+            print(f"Staženo: {file}")
+        except Exception as e:
+            print(f"Chyba při stahování {file}: {e}")
+
+if __name__ == '__main__':
+    update_json_db()