refactor(portal): replace duplicate create_cached_session with import from http_client

import requests

from bs4 import BeautifulSoup

from pydantic import ValidationError

from requests.adapters import HTTPAdapter

from urllib3.util import Retry

from tdoc_crawler.crawlers.constants import LOGIN_URL, PORTAL_BASE_URL, TDOC_DOWNLOAD_URL, TDOC_VIEW_URL

from tdoc_crawler.http_client import create_cached_session

from tdoc_crawler.models.base import PortalCredentials

from tdoc_crawler.models.tdocs import TDocMetadata

# TODO: cache_dir not used at all in PortalSession? should be used for caching HTTP requests to portal pages via hishel package - wrong HTTPAdapter? See tdoc_crawler.models.base.HttpCacheConfig

def create_cached_session(cache_dir: Path, ttl: int = 7200, refresh_ttl_on_access: bool = True, max_retries: int = 3) -> requests.Session:

    """Create an HTTP session with caching."""

    # Create session

    session = requests.Session()

    # Add retry strategy

    retry_strategy = Retry(

        total=max_retries,

        backoff_factor=1,

        status_forcelist=[429, 500, 502, 503, 504],

    )

    # Add adapter with retry strategy

    adapter = HTTPAdapter(max_retries=retry_strategy)

    session.mount("http://", adapter)

    session.mount("https://", adapter)

    session.mount("ftp://", adapter)

    return session

logger = logging.getLogger(__name__)

            timeout: Request timeout in seconds

        """

        self.credentials = credentials

        self.cache_dir = cache_dir

        self.timeout = timeout

        self.session = create_cached_session(

            cache_dir=cache_dir,

        # If no URL provided, try to extract it from unauthenticated endpoint first

        if url is None:

            try:

                url = extract_tdoc_url_from_portal(tdoc_id, timeout=min(self.timeout, 15))

                url = extract_tdoc_url_from_portal(tdoc_id, cache_dir=self.cache_dir, timeout=min(self.timeout, 15))

                logger.debug(f"Using URL extracted from unauthenticated endpoint for {tdoc_id}")

            except Exception as e:

                logger.debug(f"URL extraction failed for {tdoc_id}, using authenticated method: {e}")

        raise PortalParsingError(error_msg) from exc

def extract_tdoc_url_from_portal(tdoc_id: str, timeout: int = 15) -> str:

def extract_tdoc_url_from_portal(tdoc_id: str, cache_dir: Path | None = None, timeout: int = 15) -> str:

    """Extract direct FTP download URL for a TDoc using unauthenticated DownloadTDoc.aspx endpoint.

    Args:

        tdoc_id: TDoc identifier (e.g., 'S4-251364')

        cache_dir: Directory for HTTP cache storage (optional)

        timeout: Request timeout in seconds (default 15 seconds)

    Returns:

    download_url = f"{TDOC_DOWNLOAD_URL}?contributionUid={tdoc_id}"

    # Create a session with browser-like headers to avoid 403 Forbidden

    session = requests.Session()

    session = create_cached_session(cache_dir) if cache_dir is not None else requests.Session()

    session.headers.update(

        {

            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",

    # Try to extract URL from unauthenticated endpoint first

    if url is None:

        try:

            url = extract_tdoc_url_from_portal(tdoc_id, timeout=min(timeout, 15))

            url = extract_tdoc_url_from_portal(tdoc_id, cache_dir=cache_dir, timeout=min(timeout, 15))

        except Exception as e:

            logger.debug(f"URL extraction failed for {tdoc_id}, falling back to authenticated method: {e}")

            # Continue with authenticated method below