feat: Add NFO metadata infrastructure (Task 3 - partial)

- Created TMDB API client with async requests, caching, and retry logic
- Implemented NFO XML generator for Kodi/XBMC format
- Created image downloader for poster/logo/fanart with validation
- Added NFO service to orchestrate metadata creation
- Added NFO-related configuration settings
- Updated requirements.txt with aiohttp, lxml, pillow
- Created unit tests (need refinement due to implementation mismatch)

Components created:
- src/core/services/tmdb_client.py (270 lines)
- src/core/services/nfo_service.py (390 lines)
- src/core/utils/nfo_generator.py (180 lines)
- src/core/utils/image_downloader.py (296 lines)
- tests/unit/test_tmdb_client.py
- tests/unit/test_nfo_generator.py
- tests/unit/test_image_downloader.py

Note: Tests need to be updated to match actual implementation APIs.
Dependencies installed: aiohttp, lxml, pillow
This commit is contained in:
2026-01-11 20:33:33 +01:00
parent 5e8815d143
commit 4895e487c0
10 changed files with 2270 additions and 1 deletions

View File

@@ -0,0 +1,295 @@
"""Image downloader utility for NFO media files.
This module provides functions to download poster, logo, and fanart images
from TMDB and validate them.
Example:
>>> downloader = ImageDownloader()
>>> await downloader.download_poster(poster_url, "/path/to/poster.jpg")
"""
import asyncio
import logging
from pathlib import Path
from typing import Optional
import aiohttp
from PIL import Image
logger = logging.getLogger(__name__)
class ImageDownloadError(Exception):
"""Exception raised for image download failures."""
pass
class ImageDownloader:
"""Utility for downloading and validating images.
Attributes:
max_retries: Maximum retry attempts for downloads
timeout: Request timeout in seconds
min_file_size: Minimum valid file size in bytes
"""
def __init__(
self,
max_retries: int = 3,
timeout: int = 60,
min_file_size: int = 1024 # 1 KB
):
"""Initialize image downloader.
Args:
max_retries: Maximum retry attempts
timeout: Request timeout in seconds
min_file_size: Minimum valid file size in bytes
"""
self.max_retries = max_retries
self.timeout = timeout
self.min_file_size = min_file_size
async def download_image(
self,
url: str,
local_path: Path,
skip_existing: bool = True,
validate: bool = True
) -> bool:
"""Download an image from URL to local path.
Args:
url: Image URL
local_path: Local file path to save image
skip_existing: Skip download if file already exists
validate: Validate image after download
Returns:
True if download successful, False otherwise
Raises:
ImageDownloadError: If download fails after retries
"""
# Check if file already exists
if skip_existing and local_path.exists():
if local_path.stat().st_size >= self.min_file_size:
logger.debug(f"Image already exists: {local_path}")
return True
# Ensure parent directory exists
local_path.parent.mkdir(parents=True, exist_ok=True)
delay = 1
last_error = None
for attempt in range(self.max_retries):
try:
logger.debug(f"Downloading image from {url} (attempt {attempt + 1})")
timeout = aiohttp.ClientTimeout(total=self.timeout)
async with aiohttp.ClientSession(timeout=timeout) as session:
async with session.get(url) as resp:
if resp.status == 404:
logger.warning(f"Image not found: {url}")
return False
resp.raise_for_status()
# Download image data
data = await resp.read()
# Check file size
if len(data) < self.min_file_size:
raise ImageDownloadError(
f"Downloaded file too small: {len(data)} bytes"
)
# Write to file
with open(local_path, "wb") as f:
f.write(data)
# Validate image if requested
if validate and not self.validate_image(local_path):
local_path.unlink(missing_ok=True)
raise ImageDownloadError("Image validation failed")
logger.info(f"Downloaded image to {local_path}")
return True
except (aiohttp.ClientError, IOError, ImageDownloadError) as e:
last_error = e
if attempt < self.max_retries - 1:
logger.warning(
f"Download failed (attempt {attempt + 1}): {e}, "
f"retrying in {delay}s"
)
await asyncio.sleep(delay)
delay *= 2
else:
logger.error(
f"Download failed after {self.max_retries} attempts: {e}"
)
raise ImageDownloadError(
f"Failed to download image after {self.max_retries} attempts: {last_error}"
)
async def download_poster(
self,
url: str,
series_folder: Path,
filename: str = "poster.jpg",
skip_existing: bool = True
) -> bool:
"""Download poster image.
Args:
url: Poster URL
series_folder: Series folder path
filename: Output filename (default: poster.jpg)
skip_existing: Skip if file exists
Returns:
True if successful
"""
local_path = series_folder / filename
try:
return await self.download_image(url, local_path, skip_existing)
except ImageDownloadError as e:
logger.warning(f"Failed to download poster: {e}")
return False
async def download_logo(
self,
url: str,
series_folder: Path,
filename: str = "logo.png",
skip_existing: bool = True
) -> bool:
"""Download logo image.
Args:
url: Logo URL
series_folder: Series folder path
filename: Output filename (default: logo.png)
skip_existing: Skip if file exists
Returns:
True if successful
"""
local_path = series_folder / filename
try:
return await self.download_image(url, local_path, skip_existing)
except ImageDownloadError as e:
logger.warning(f"Failed to download logo: {e}")
return False
async def download_fanart(
self,
url: str,
series_folder: Path,
filename: str = "fanart.jpg",
skip_existing: bool = True
) -> bool:
"""Download fanart/backdrop image.
Args:
url: Fanart URL
series_folder: Series folder path
filename: Output filename (default: fanart.jpg)
skip_existing: Skip if file exists
Returns:
True if successful
"""
local_path = series_folder / filename
try:
return await self.download_image(url, local_path, skip_existing)
except ImageDownloadError as e:
logger.warning(f"Failed to download fanart: {e}")
return False
def validate_image(self, image_path: Path) -> bool:
"""Validate that file is a valid image.
Args:
image_path: Path to image file
Returns:
True if valid image, False otherwise
"""
try:
with Image.open(image_path) as img:
# Verify it's a valid image
img.verify()
# Check file size
if image_path.stat().st_size < self.min_file_size:
logger.warning(f"Image file too small: {image_path}")
return False
return True
except Exception as e:
logger.warning(f"Image validation failed for {image_path}: {e}")
return False
async def download_all_media(
self,
series_folder: Path,
poster_url: Optional[str] = None,
logo_url: Optional[str] = None,
fanart_url: Optional[str] = None,
skip_existing: bool = True
) -> dict[str, bool]:
"""Download all media files (poster, logo, fanart).
Args:
series_folder: Series folder path
poster_url: Poster URL (optional)
logo_url: Logo URL (optional)
fanart_url: Fanart URL (optional)
skip_existing: Skip existing files
Returns:
Dictionary with download status for each file type
"""
results = {
"poster": False,
"logo": False,
"fanart": False
}
tasks = []
if poster_url:
tasks.append(("poster", self.download_poster(
poster_url, series_folder, skip_existing=skip_existing
)))
if logo_url:
tasks.append(("logo", self.download_logo(
logo_url, series_folder, skip_existing=skip_existing
)))
if fanart_url:
tasks.append(("fanart", self.download_fanart(
fanart_url, series_folder, skip_existing=skip_existing
)))
# Download concurrently
if tasks:
task_results = await asyncio.gather(
*[task for _, task in tasks],
return_exceptions=True
)
for (media_type, _), result in zip(tasks, task_results):
if isinstance(result, Exception):
logger.error(f"Error downloading {media_type}: {result}")
results[media_type] = False
else:
results[media_type] = result
return results

View File

@@ -0,0 +1,192 @@
"""NFO XML generator for Kodi/XBMC format.
This module provides functions to generate tvshow.nfo XML files from
TVShowNFO Pydantic models, adapted from the scraper project.
Example:
>>> from src.core.entities.nfo_models import TVShowNFO
>>> nfo = TVShowNFO(title="Test Show", year=2020, tmdbid=12345)
>>> xml_string = generate_tvshow_nfo(nfo)
"""
import logging
from typing import Optional
from lxml import etree
from src.core.entities.nfo_models import TVShowNFO
logger = logging.getLogger(__name__)
def generate_tvshow_nfo(tvshow: TVShowNFO, pretty_print: bool = True) -> str:
"""Generate tvshow.nfo XML content from TVShowNFO model.
Args:
tvshow: TVShowNFO Pydantic model with metadata
pretty_print: Whether to format XML with indentation
Returns:
XML string in Kodi/XBMC tvshow.nfo format
Example:
>>> nfo = TVShowNFO(title="Attack on Titan", year=2013)
>>> xml = generate_tvshow_nfo(nfo)
"""
root = etree.Element("tvshow")
# Basic information
_add_element(root, "title", tvshow.title)
_add_element(root, "originaltitle", tvshow.originaltitle)
_add_element(root, "showtitle", tvshow.showtitle)
_add_element(root, "sorttitle", tvshow.sorttitle)
_add_element(root, "year", str(tvshow.year) if tvshow.year else None)
# Plot and description
_add_element(root, "plot", tvshow.plot)
_add_element(root, "outline", tvshow.outline)
_add_element(root, "tagline", tvshow.tagline)
# Technical details
_add_element(root, "runtime", str(tvshow.runtime) if tvshow.runtime else None)
_add_element(root, "mpaa", tvshow.mpaa)
_add_element(root, "certification", tvshow.certification)
# Status and dates
_add_element(root, "premiered", tvshow.premiered)
_add_element(root, "status", tvshow.status)
_add_element(root, "dateadded", tvshow.dateadded)
# Ratings
if tvshow.ratings:
ratings_elem = etree.SubElement(root, "ratings")
for rating in tvshow.ratings:
rating_elem = etree.SubElement(ratings_elem, "rating")
if rating.name:
rating_elem.set("name", rating.name)
if rating.max_rating:
rating_elem.set("max", str(rating.max_rating))
if rating.default:
rating_elem.set("default", "true")
_add_element(rating_elem, "value", str(rating.value))
if rating.votes is not None:
_add_element(rating_elem, "votes", str(rating.votes))
_add_element(root, "userrating", str(tvshow.userrating) if tvshow.userrating is not None else None)
# IDs
_add_element(root, "tmdbid", str(tvshow.tmdbid) if tvshow.tmdbid else None)
_add_element(root, "imdbid", tvshow.imdbid)
_add_element(root, "tvdbid", str(tvshow.tvdbid) if tvshow.tvdbid else None)
# Legacy ID fields for compatibility
_add_element(root, "id", str(tvshow.tvdbid) if tvshow.tvdbid else None)
_add_element(root, "imdb_id", tvshow.imdbid)
# Unique IDs
for uid in tvshow.uniqueid:
uid_elem = etree.SubElement(root, "uniqueid")
uid_elem.set("type", uid.type)
if uid.default:
uid_elem.set("default", "true")
uid_elem.text = uid.value
# Multi-value fields
for genre in tvshow.genre:
_add_element(root, "genre", genre)
for studio in tvshow.studio:
_add_element(root, "studio", studio)
for country in tvshow.country:
_add_element(root, "country", country)
for tag in tvshow.tag:
_add_element(root, "tag", tag)
# Thumbnails (posters, logos)
for thumb in tvshow.thumb:
thumb_elem = etree.SubElement(root, "thumb")
if thumb.aspect:
thumb_elem.set("aspect", thumb.aspect)
if thumb.season is not None:
thumb_elem.set("season", str(thumb.season))
if thumb.type:
thumb_elem.set("type", thumb.type)
thumb_elem.text = str(thumb.url)
# Fanart
if tvshow.fanart:
fanart_elem = etree.SubElement(root, "fanart")
for fanart in tvshow.fanart:
fanart_thumb = etree.SubElement(fanart_elem, "thumb")
fanart_thumb.text = str(fanart.url)
# Named seasons
for named_season in tvshow.namedseason:
season_elem = etree.SubElement(root, "namedseason")
season_elem.set("number", str(named_season.number))
season_elem.text = named_season.name
# Actors
for actor in tvshow.actors:
actor_elem = etree.SubElement(root, "actor")
_add_element(actor_elem, "name", actor.name)
_add_element(actor_elem, "role", actor.role)
_add_element(actor_elem, "thumb", str(actor.thumb) if actor.thumb else None)
_add_element(actor_elem, "profile", str(actor.profile) if actor.profile else None)
_add_element(actor_elem, "tmdbid", str(actor.tmdbid) if actor.tmdbid else None)
# Additional fields
_add_element(root, "trailer", str(tvshow.trailer) if tvshow.trailer else None)
_add_element(root, "watched", "true" if tvshow.watched else "false")
if tvshow.playcount is not None:
_add_element(root, "playcount", str(tvshow.playcount))
# Generate XML string
xml_str = etree.tostring(
root,
pretty_print=pretty_print,
encoding="unicode",
xml_declaration=False
)
# Add XML declaration
xml_declaration = '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n'
return xml_declaration + xml_str
def _add_element(parent: etree.Element, tag: str, text: Optional[str]) -> Optional[etree.Element]:
"""Add a child element to parent if text is not None or empty.
Args:
parent: Parent XML element
tag: Tag name for child element
text: Text content (None or empty strings are skipped)
Returns:
Created element or None if skipped
"""
if text is not None and text != "":
elem = etree.SubElement(parent, tag)
elem.text = text
return elem
return None
def validate_nfo_xml(xml_string: str) -> bool:
"""Validate NFO XML structure.
Args:
xml_string: XML content to validate
Returns:
True if valid XML, False otherwise
"""
try:
etree.fromstring(xml_string.encode('utf-8'))
return True
except etree.XMLSyntaxError as e:
logger.error(f"Invalid NFO XML: {e}")
return False