zxdb.py: Añadida nueva query

zxdb.py

@@ -1,5 +1,6 @@
-## Script para descargar pantallas de carga de spectrum a partir de zxdb
+## Script para descargar ficheros de spectrum a partir de zxdb
 
+## Imports utilizados en el script
 import os
 import mysql.connector
 import requests
@@ -11,15 +12,20 @@ from mysql.connector import errorcode
 from urllib.parse import urlparse
 from urllib.request import urlretrieve
 
-
+## Direcciones de internet de donde descargar los datos
 url_prefix = {
     "spectrum_computing": r"https://spectrumcomputing.co.uk",
     "wos": r"https://php.sustancia.synology.me/wos",
     "nvg": r"https://php.sustancia.synology.me/nvg",
 }
+
+## Rutas locales donde depositar los resultados
 destination_path = r"/home/sergio/zx/zxdb/games/"
 cache_path = r"/home/sergio/zx/zxdb/cache/games/"
 temp_file = r"/tmp/zxdb.download.tmp"
+
+## Parametros de configuración
+should_clear_destination_path = True # Establece si se limpia primero la carpeta de destino
 wait = True  # Establece una pausa aleatoria entre descargas
 min_wait = 2  # Segundos mínimos a esperar entre descargas
 max_wait = min_wait + 1  # Segundos máximos a esperar entre descargas
@@ -32,24 +38,42 @@ filetypes_on_root = [
 ]  # Tipos de fichero que se guardan en la carpeta raíz del juego
 
 
-def select1(cursor):
+def select(cursor):
-    query = "SELECT id, title FROM entries WHERE id BETWEEN %s AND %s"
+    query = []
-    id_start = 1950
+    selected_query = 0
-    id_end = 1980
-    cursor.execute(query, (id_start, id_end))
-    for id, title in cursor:
-        print("{} ({})".format(title, id))
 
-
+    ## Esta consulta devuelve todos los juegos, filtrando aplicaciones, libros, etc y todos los ficheros asociados a esos juegos
-def select2(cursor):
+    ## 0
-    query = "select file_link from downloads where filetype_id=1"
+    select = """
-    cursor.execute(query)
+        SELECT DISTINCT
-    for file_link in cursor:
+            e.title, l.name, r.release_year, d.file_link, f.text
-        elements.append(url_prefix[0] + str(file_link)[3:-3])
+        FROM
-
+            ((((((publishers p
-
+                INNER JOIN entries e ON
-def select3(cursor):
+                    p.entry_id = e.id)
-    query = """
+                INNER JOIN labels l ON
+                    p.label_id = l.id)
+                INNER JOIN genretypes g ON
+                    e.genretype_id = g.id)
+                INNER JOIN downloads d ON
+                    e.id = d.entry_id)
+                INNER JOIN filetypes f ON
+                    d.filetype_id = f.id)                    
+                INNER JOIN releases r ON
+                    e.id = r.entry_id AND
+                    p.release_seq = r.release_seq)
+        WHERE
+            (e.availabletype_id = 'A' OR e.availabletype_id = 'D') AND
+            (f.text <> 'Remote link' AND f.text <> '?') AND
+            r.release_seq = 0 AND
+            (g.text like '%Game:%' AND g.text not like 'Casual%')
+        ORDER BY
+            e.title;"""
+    query.append(select)
+    
+    ## Esta consulta se usa para filtrar mas la consulta anterior
+    ## 1
+    select = """
         SELECT DISTINCT
             e.title, l.name, r.release_year, d.file_link, f.text
         FROM
@@ -80,7 +104,39 @@ def select3(cursor):
             #(l.country_id = 'ES' AND l.labeltype_id = 'Z') AND
             #l.name in ('Ocean Software Ltd', 'Imagine Software Ltd', 'Palace Software', 'Gremlin Graphics Software Ltd', 'Elite Systems Ltd', 'Melbourne House', 'Ultimate Play The Game', 'Durell Software Ltd', 'Codemasters Ltd') AND
             #e.title = 'Arkanoid - Revenge of Doh' AND
-    cursor.execute(query)
+    query.append(select)
+    
+    ## Esta consulta devuelve todos los juegos, filtrando aplicaciones, libros, etc y SOLO los ficheros de cinta, disco o pokes
+    ## 2
+    select = """
+        SELECT DISTINCT
+            e.title, l.name, r.release_year, d.file_link, f.text
+        FROM
+            ((((((publishers p
+                INNER JOIN entries e ON
+                    p.entry_id = e.id)
+                INNER JOIN labels l ON
+                    p.label_id = l.id)
+                INNER JOIN genretypes g ON
+                    e.genretype_id = g.id)
+                INNER JOIN downloads d ON
+                    e.id = d.entry_id)
+                INNER JOIN filetypes f ON
+                    d.filetype_id = f.id)                    
+                INNER JOIN releases r ON
+                    e.id = r.entry_id AND
+                    p.release_seq = r.release_seq)
+        WHERE
+            (e.availabletype_id = 'A' OR e.availabletype_id = 'D') AND
+            (f.text IN ('Tape image','Disk image','Snapshot image','POK pokes file')) AND
+            r.release_seq = 0 AND
+            (g.text like '%Game:%' AND g.text not like 'Casual%')
+        ORDER BY
+            e.title;"""
+    query.append(select)
+    
+    cursor.execute(query[selected_query])
+    
     for row in cursor:
         element = dict(
             title=row[0],
@@ -91,7 +147,7 @@ def select3(cursor):
         )
         elements.append(element)
 
-
+## Establece la conexión a la BBDD y ejecuta la consulta
 def connect():
     config = {
         "user": "root",
@@ -104,7 +160,7 @@ def connect():
     try:
         connection = mysql.connector.connect(**config)
         cursor = connection.cursor()
-        select3(cursor)
+        select(cursor)
 
     except mysql.connector.Error as err:
         if err.errno == errorcode.ER_ACCESS_DENIED_ERROR:
@@ -119,7 +175,7 @@ def connect():
             connection.close()
             cursor.close()
 
-
+## Procesa todos lo elementos, modificando cada uno de sus parametros
 def process_elements():
     global elements
     for i in range(len(elements)):
@@ -161,6 +217,7 @@ def process_elements():
             elements[i]["url"] = url_prefix["nvg"] + str(elements[i]["url"][4:])
 
 
+## Devuelve el fichero que forma la parte final de una URL
 def url_filename(url):
     parsed_url = urlparse(url)
     path = parsed_url.path
@@ -168,6 +225,7 @@ def url_filename(url):
     return filename
 
 
+## Descarga un fichero a partir de una URL
 def download_file(url, dest):
     try:
         r = requests.get(url)
@@ -190,6 +248,7 @@ def download_file(url, dest):
         raise SystemExit(e)
 
 
+## Descomprime los ficheros que coinciden con la lista de extensiones
 def unzip_file(src, dst):
     # with zipfile.ZipFile(src, "r") as zip_ref:
     #    zip_ref.extractall(dst)
@@ -205,6 +264,8 @@ def unzip_file(src, dst):
     zip_file.close()
 
 
+## Obtiene los ficheros de la consulta desde internet o desde la caché
+## y los deposita en la carpeta destino, descomprimiendo los archivos necesarios
 def get_files():
     # Variables para la presentación en pantalla de la descarga
     current_file = 0
@@ -315,6 +376,7 @@ def get_files():
             )
 
 
+## Elimina los caracteres ilegales de la cadena de texto
 def normalize_path(path):
     illegal_chars = ["<", ">", ":", '"', "/", "\\", "|", "?", "*"]
     replace_with = "_"
@@ -323,6 +385,23 @@ def normalize_path(path):
     return path
 
 
+## Limpia la carpeta de destino
+def clear_destination_folder():
+    if should_clear_destination_path:
+        print("Clear destination folder ...")
+        folder = destination_path
+        for filename in os.listdir(folder):
+            file_path = os.path.join(folder, filename)
+            try:
+                if os.path.isfile(file_path) or os.path.islink(file_path):
+                    os.unlink(file_path)
+                elif os.path.isdir(file_path):
+                    shutil.rmtree(file_path)
+            except Exception as e:
+                print('Failed to delete %s. Reason: %s' % (file_path, e))
+
+
+## Bucle principal
 def main():
     connect()
     process_elements()
@@ -332,7 +411,9 @@ def main():
     #    for key, value in element.items():
     #        print(key, ':', value)
 
+    clear_destination_folder()
     get_files()
+
     # for element in elements:
     #    print(element['title'])