From d4b901734dce468bdfd291b13f0969ebb6347513 Mon Sep 17 00:00:00 2001
From: jourdelune <jourdelune863@gmail.com>
Date: Tue, 23 Jul 2024 12:03:23 +0200
Subject: [PATCH] [update] improve code (pylint)

---
 src/robots.py | 6 +-----
 src/routes.py | 4 ++--
 src/utils.py  | 4 +++-
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/src/robots.py b/src/robots.py
index a566e4e..05d4034 100644
--- a/src/robots.py
+++ b/src/robots.py
@@ -2,7 +2,6 @@
 Class to respect robot.txt file
 """
 
-import asyncio
 import logging
 import urllib.parse
 
@@ -48,10 +47,7 @@ async def __call__(self, url: str, log: logging.Logger = None) -> bool:
 
         authorize = authorize = self._robots[robots_url].can_fetch(url, "*")
         for agent in self._user_agent:
-            agents_on_site = [
-                agent_on_site
-                for agent_on_site in self._robots[robots_url]._user_agents.keys()
-            ]
+            agents_on_site = list(self._robots[robots_url]._user_agents.keys())
 
             if agent in agents_on_site:
                 authorize = self._robots[robots_url].can_fetch(url, agent)
diff --git a/src/routes.py b/src/routes.py
index 7914990..5895f5b 100644
--- a/src/routes.py
+++ b/src/routes.py
@@ -13,7 +13,7 @@
 
 router = Router[BeautifulSoupCrawlingContext]()
 robots_parser = RobotTXT()
-regex = r"(https?:\/\/)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()!@:%_\+.~#?&\/\/=]*)\.(mp3|wav|ogg)"
+REGEX = r"(https?:\/\/)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()!@:%_\+.~#?&\/\/=]*)\.(mp3|wav|ogg)"
 
 
 @router.default_handler
@@ -29,7 +29,7 @@ async def default_handler(context: BeautifulSoupCrawlingContext) -> None:
     url = context.request.url
     html_page = str(context.soup).replace(r"\/", "/")
 
-    matches = re.finditer(regex, html_page)
+    matches = re.finditer(REGEX, html_page)
 
     # get all audios links
     audio_links = [html_page[match.start() : match.end()] for match in matches]
diff --git a/src/utils.py b/src/utils.py
index 8c33d53..4119b7b 100644
--- a/src/utils.py
+++ b/src/utils.py
@@ -12,7 +12,9 @@ def process(file_name: str) -> None:
     Args:
         file_name (str): the file name to process
     """
-    data = json.load(open(file_name, encoding="utf-8"))
+
+    with open(file_name, encoding="utf-8") as file:
+        data = json.load(file)
 
     unique_urls = set()
     unique_data = []