Function _parse_publish_month

agents/reading-agent/main.py:226–241

(paper: Dict[str, Any])

def _parse_publish_month(paper: Dict[str, Any]) -> datetime:
    for key in ("publish_date", "published", "updated", "created_at", "fetched_at"):
        raw = _clean_text(paper.get(key))
        if not raw:
            continue
        for fmt, width in (("%Y-%m-%d", 10), ("%Y/%m/%d", 10), ("%Y-%m", 7), ("%Y/%m", 7)):
            try:
                return datetime.strptime(raw[:width], fmt)
            except ValueError:
                continue
        match = re.search(r"(20\d{2})[-/](\d{1,2})", raw)
        if match:
            year = int(match.group(1))
            month = max(1, min(12, int(match.group(2))))
            return datetime(year, month, 1)
    return datetime.now()


def _month_folder_name(paper: Dict[str, Any]) -> str: