fix: eliminate async safety violations and migrate to pathlib (#697)

## ℹ️ Description
Eliminate all blocking I/O operations in async contexts and modernize
file path handling by migrating from os.path to pathlib.Path.

- Link to the related issue(s): #692 
- Get rid of the TODO in pyproject.toml
- The added debug logging will ease the troubleshooting for path related
issues.

## 📋 Changes Summary

- Enable ASYNC210, ASYNC230, ASYNC240, ASYNC250 Ruff rules
- Wrap blocking urllib.request.urlopen() in run_in_executor
- Wrap blocking file operations (open, write) in run_in_executor
- Replace blocking os.path calls with async helpers using
run_in_executor
- Replace blocking input() with await ainput()
- Migrate extract.py from os.path to pathlib.Path
- Use Path() constructor and / operator for path joining
- Use Path.mkdir(), Path.rename() in executor instead of os functions
- Create mockable _path_exists() and _path_is_dir() helpers
- Add debug logging for all file system operations

### ⚙️ Type of Change
Select the type(s) of change(s) included in this pull request:
- [X] 🐞 Bug fix (non-breaking change which fixes an issue)
- [ ]  New feature (adds new functionality without breaking existing
usage)
- [ ] 💥 Breaking change (changes that might break existing user setups,
scripts, or configurations)


##  Checklist
Before requesting a review, confirm the following:
- [X] I have reviewed my changes to ensure they meet the project's
standards.
- [X] I have tested my changes and ensured that all tests pass (`pdm run
test`).
- [X] I have formatted the code (`pdm run format`).
- [X] I have verified that linting passes (`pdm run lint`).
- [X] I have updated documentation where necessary.

By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Refactor**
  * Made user prompt non‑blocking to improve responsiveness.
* Converted filesystem/path handling and prefs I/O to async‑friendly
operations; moved blocking network and file work to background tasks.
* Added async file/path helpers and async port‑check before browser
connections.

* **Tests**
* Expanded unit tests for path helpers, image download success/failure,
prefs writing, and directory creation/renaming workflows.

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
Jens
2025-12-05 20:53:40 +01:00
committed by GitHub
parent 6cbc25b54c
commit 220c01f257
9 changed files with 527 additions and 303 deletions

View File

@@ -1,7 +1,8 @@
# SPDX-FileCopyrightText: © Sebastian Thomschke and contributors
# SPDX-License-Identifier: AGPL-3.0-or-later
# SPDX-ArtifactOfProjectHomePage: https://github.com/Second-Hand-Friends/kleinanzeigen-bot/
import os
import asyncio, os # isort: skip
from pathlib import Path
def abspath(relative_path:str, relative_to:str | None = None) -> str:
@@ -24,3 +25,23 @@ def abspath(relative_path:str, relative_to:str | None = None) -> str:
base = os.path.dirname(base)
return os.path.normpath(os.path.join(base, relative_path))
async def exists(path:str | Path) -> bool:
"""
Asynchronously check if a file or directory exists.
:param path: Path to check
:return: True if path exists, False otherwise
"""
return await asyncio.get_running_loop().run_in_executor(None, Path(path).exists)
async def is_dir(path:str | Path) -> bool:
"""
Asynchronously check if a path is a directory.
:param path: Path to check
:return: True if path is a directory, False otherwise
"""
return await asyncio.get_running_loop().run_in_executor(None, Path(path).is_dir)

View File

@@ -22,7 +22,7 @@ from nodriver.core.tab import Tab as Page
from kleinanzeigen_bot.model.config_model import Config as BotConfig
from kleinanzeigen_bot.model.config_model import TimeoutConfig
from . import loggers, net
from . import files, loggers, net
from .chrome_version_detector import (
ChromeVersionInfo,
detect_chrome_version_from_binary,
@@ -100,6 +100,37 @@ class BrowserConfig:
self.profile_name:str | None = None
def _write_initial_prefs(prefs_file:str) -> None:
with open(prefs_file, "w", encoding = "UTF-8") as fd:
json.dump({
"credentials_enable_service": False,
"enable_do_not_track": True,
"google": {
"services": {
"consented_to_sync": False
}
},
"profile": {
"default_content_setting_values": {
"popups": 0,
"notifications": 2 # 1 = allow, 2 = block browser notifications
},
"password_manager_enabled": False
},
"signin": {
"allowed": False
},
"translate_site_blacklist": [
"www.kleinanzeigen.de"
],
"devtools": {
"preferences": {
"currentDockState": '"bottom"'
}
}
}, fd)
class WebScrapingMixin:
def __init__(self) -> None:
@@ -174,7 +205,7 @@ class WebScrapingMixin:
LOG.info("Creating Browser session...")
if self.browser_config.binary_location:
ensure(os.path.exists(self.browser_config.binary_location), f"Specified browser binary [{self.browser_config.binary_location}] does not exist.")
ensure(await files.exists(self.browser_config.binary_location), f"Specified browser binary [{self.browser_config.binary_location}] does not exist.")
else:
self.browser_config.binary_location = self.get_compatible_browser()
LOG.info(" -> Browser binary location: %s", self.browser_config.binary_location)
@@ -289,41 +320,14 @@ class WebScrapingMixin:
profile_dir = os.path.join(cfg.user_data_dir, self.browser_config.profile_name or "Default")
os.makedirs(profile_dir, exist_ok = True)
prefs_file = os.path.join(profile_dir, "Preferences")
if not os.path.exists(prefs_file):
if not await files.exists(prefs_file):
LOG.info(" -> Setting chrome prefs [%s]...", prefs_file)
with open(prefs_file, "w", encoding = "UTF-8") as fd:
json.dump({
"credentials_enable_service": False,
"enable_do_not_track": True,
"google": {
"services": {
"consented_to_sync": False
}
},
"profile": {
"default_content_setting_values": {
"popups": 0,
"notifications": 2 # 1 = allow, 2 = block browser notifications
},
"password_manager_enabled": False
},
"signin": {
"allowed": False
},
"translate_site_blacklist": [
"www.kleinanzeigen.de"
],
"devtools": {
"preferences": {
"currentDockState": '"bottom"'
}
}
}, fd)
await asyncio.get_running_loop().run_in_executor(None, _write_initial_prefs, prefs_file)
# load extensions
for crx_extension in self.browser_config.extensions:
LOG.info(" -> Adding Browser extension: [%s]", crx_extension)
ensure(os.path.exists(crx_extension), f"Configured extension-file [{crx_extension}] does not exist.")
ensure(await files.exists(crx_extension), f"Configured extension-file [{crx_extension}] does not exist.")
cfg.add_extension(crx_extension)
try: