anya/services/sources.py

import logging

logger = logging.getLogger(__name__)


def get_sources(path, delimiter='\n'):
    """Load source URLs from a file, one per line.

    Blank lines and lines starting with ``#`` are ignored, so the file can be
    annotated with comments (e.g. grouping HTML vs. RSS feeds).
    """
    logger.info("Attempting to load sources from file: '%s' with delimiter: %r", path, delimiter)
    try:
        with open(path, 'r', encoding='utf-8-sig') as source_file:
            content = source_file.read()
    except FileNotFoundError:
        logger.error("Source file not found at path: '%s'", path, exc_info=True)
        raise
    except PermissionError:
        logger.error("Permission denied when accessing source file: '%s'", path, exc_info=True)
        raise
    except Exception as e:
        logger.error("Failed to read sources from '%s': %s", path, e, exc_info=True)
        raise

    sources = []
    for line in content.split(delimiter):
        stripped = line.strip()
        if not stripped or stripped.startswith('#'):
            continue
        sources.append(stripped)

    logger.info("Successfully loaded %d source entries from '%s'", len(sources), path)
    return sources