refactor: improve downloader robustness and test coverage

- Add test for cookies_file parameter verification
- Add test for yt-dlp configuration (format, outtmpl, postprocessors)
- Use validator module for robust space_id extraction
- Replace fragile URL splitting with validate_space_url()
- Handles trailing slashes and query parameters correctly

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
synapz-org
2025-10-26 09:43:26 -04:00
parent 0a6a2ffd71
commit 73775c122b
2 changed files with 66 additions and 2 deletions

View File

@@ -1,6 +1,7 @@
import os
import yt_dlp
from typing import Optional
from src.validator import validate_space_url
def download_space(
@@ -19,8 +20,13 @@ def download_space(
Returns:
Path to the downloaded MP3 file
"""
# Extract space ID from URL for filename
space_id = space_url.split('/')[-1]
# Extract space ID from URL using validator for robustness
is_valid, space_id, error_message = validate_space_url(space_url)
if not is_valid:
raise ValueError(f"Invalid space URL: {error_message}")
if space_id is None:
raise ValueError("Could not extract space ID from URL")
# Configure yt-dlp options
ydl_opts = {

View File

@@ -25,3 +25,61 @@ def test_download_space_basic(tmp_path):
# Verify result contains expected filename
assert "space_1ZkKzZWnVRRKv" in result
def test_download_space_with_cookies(tmp_path):
"""Test that cookies file is passed to yt-dlp when provided."""
space_url = "https://x.com/i/spaces/1ZkKzZWnVRRKv"
cookies_path = "/path/to/cookies.txt"
with patch('src.downloader.yt_dlp.YoutubeDL') as mock_ytdl_class:
# Mock the YoutubeDL instance
mock_ytdl = Mock()
mock_ytdl_class.return_value.__enter__.return_value = mock_ytdl
mock_ytdl.extract_info.return_value = {'id': '1ZkKzZWnVRRKv'}
# Call download_space with cookies
result = download_space(
space_url=space_url,
output_dir=str(tmp_path),
cookies_file=cookies_path
)
# Verify YoutubeDL was initialized with correct options
call_args = mock_ytdl_class.call_args[0][0]
assert 'cookiefile' in call_args
assert call_args['cookiefile'] == cookies_path
def test_download_space_ytdlp_configuration(tmp_path):
"""Test that yt-dlp is configured correctly with format, outtmpl, and postprocessors."""
space_url = "https://x.com/i/spaces/1ZkKzZWnVRRKv"
with patch('src.downloader.yt_dlp.YoutubeDL') as mock_ytdl_class:
# Mock the YoutubeDL instance
mock_ytdl = Mock()
mock_ytdl_class.return_value.__enter__.return_value = mock_ytdl
mock_ytdl.extract_info.return_value = {'id': '1ZkKzZWnVRRKv'}
# Call download_space
result = download_space(
space_url=space_url,
output_dir=str(tmp_path),
cookies_file=None
)
# Verify YoutubeDL was initialized with correct options
call_args = mock_ytdl_class.call_args[0][0]
# Check format
assert call_args['format'] == 'bestaudio/best'
# Check outtmpl contains the space_id
assert 'outtmpl' in call_args
assert 'space_1ZkKzZWnVRRKv' in call_args['outtmpl']
# Check postprocessors for MP3 conversion
assert 'postprocessors' in call_args
assert len(call_args['postprocessors']) > 0
assert call_args['postprocessors'][0]['key'] == 'FFmpegExtractAudio'
assert call_args['postprocessors'][0]['preferredcodec'] == 'mp3'