docs: Update CLAUDE.md with three-tier architecture and new providers
- Added new video players: Vidzy, LuLuvid, Uqload - Added new anime site: French-Manga - Added new series sites category with FS7 - Updated documentation to reflect three-tier architecture (anime sites → series sites → video players) - Added BaseSeriesSite interface documentation - Added "Adding New Series Site" section - Updated test organization with test_french_manga.py Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering>
This commit is contained in:
root
@@ -0,0 +1,23 @@
|
||||
"""Series streaming sites (catalogs) downloaders"""
|
||||
from .base import BaseSeriesSite
|
||||
# Import all series site downloaders
|
||||
from .fs7 import FS7Downloader
|
||||
|
||||
__all__ = [
|
||||
"BaseSeriesSite",
|
||||
"FS7Downloader",
|
||||
]
|
||||
|
||||
|
||||
def get_series_site(url: str) -> BaseSeriesSite:
|
||||
"""Factory function to get the appropriate series site for a URL"""
|
||||
sites = [
|
||||
FS7Downloader(),
|
||||
]
|
||||
|
||||
for site in sites:
|
||||
if site.can_handle(url):
|
||||
return site
|
||||
|
||||
# Return None if no match (should not happen in normal flow)
|
||||
return None
|
||||
@@ -0,0 +1,131 @@
|
||||
"""Base class for series streaming sites (catalogs)"""
|
||||
from abc import abstractmethod
|
||||
from typing import List, Dict, Any, Optional, Tuple
|
||||
import logging
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class BaseSeriesSite:
|
||||
"""
|
||||
Base class for series streaming sites.
|
||||
|
||||
Series sites provide catalogs, metadata, and episode listings.
|
||||
They typically link to video players for actual file hosting.
|
||||
|
||||
Examples: FS7 (French Stream), etc.
|
||||
|
||||
KEY FEATURE: Provides rich metadata and episode management for TV series
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
# Initialize HTTP client directly
|
||||
self.client = httpx.AsyncClient(timeout=10.0, follow_redirects=True)
|
||||
|
||||
@abstractmethod
|
||||
def can_handle(self, url: str) -> bool:
|
||||
"""Check if this series site can handle the given URL"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def search_anime(
|
||||
self,
|
||||
query: str,
|
||||
lang: str = "vf"
|
||||
) -> List[Dict[str, str]]:
|
||||
"""
|
||||
Search for series on this site.
|
||||
|
||||
Args:
|
||||
query: Search query (series title)
|
||||
lang: Language preference (vf, vostfr)
|
||||
|
||||
Returns:
|
||||
List of series with keys:
|
||||
- title: Series title
|
||||
- url: Series page URL
|
||||
- cover_image: Optional cover image URL
|
||||
- lang: Available languages
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def get_episodes(
|
||||
self,
|
||||
anime_url: str,
|
||||
lang: str = "vf"
|
||||
) -> List[Dict[str, str]]:
|
||||
"""
|
||||
Get list of episodes for a series.
|
||||
|
||||
Args:
|
||||
anime_url: URL of the series page
|
||||
lang: Language preference
|
||||
|
||||
Returns:
|
||||
List of episodes with keys:
|
||||
- episode_number: Episode number
|
||||
- url: Episode page URL
|
||||
- title: Optional episode title
|
||||
- host: Video player hosting the file
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def get_anime_metadata(self, anime_url: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Get detailed metadata for a series.
|
||||
|
||||
Args:
|
||||
anime_url: URL of the series page
|
||||
|
||||
Returns:
|
||||
Dict with metadata:
|
||||
- title: Series title
|
||||
- synopsis: Plot summary
|
||||
- genres: List of genres
|
||||
- rating: Rating (e.g., "8.5/10")
|
||||
- release_year: Release year
|
||||
- studio: Production studio
|
||||
- poster_image: Poster URL
|
||||
- total_episodes: Total episode count
|
||||
- status: Airing status (ongoing, completed)
|
||||
- languages: Available languages
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def get_download_link(self, url: str) -> Tuple[str, str]:
|
||||
"""
|
||||
Get download link for a specific episode.
|
||||
|
||||
For series sites, this extracts the video player URL from an episode page.
|
||||
Note: Returns video player URL, NOT direct download link!
|
||||
|
||||
Returns:
|
||||
Tuple of (video_player_url, episode_title)
|
||||
"""
|
||||
pass
|
||||
|
||||
# Common methods for all series sites
|
||||
async def close(self):
|
||||
"""Close HTTP client"""
|
||||
await self.client.aclose()
|
||||
|
||||
async def _fetch_page(self, url: str) -> str:
|
||||
"""Fetch HTML page content"""
|
||||
response = await self.client.get(url)
|
||||
response.raise_for_status()
|
||||
return response.text
|
||||
|
||||
def _parse_html(self, html: str) -> BeautifulSoup:
|
||||
"""Parse HTML with BeautifulSoup"""
|
||||
return BeautifulSoup(html, 'lxml')
|
||||
|
||||
def _extract_season_number(self, title: str) -> Optional[int]:
|
||||
"""Extract season number from title (e.g., 'Saison 2' -> 2)"""
|
||||
import re
|
||||
match = re.search(r'saison\s*(\d+)', title.lower())
|
||||
return int(match.group(1)) if match else None
|
||||
@@ -0,0 +1,262 @@
|
||||
"""FS7 (French Stream) series site downloader"""
|
||||
import logging
|
||||
import re
|
||||
from typing import List, Dict, Any, Optional
|
||||
from urllib.parse import urljoin, urlparse
|
||||
from bs4 import BeautifulSoup
|
||||
from app.utils import sanitize_filename
|
||||
from .base import BaseSeriesSite
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class FS7Downloader(BaseSeriesSite):
|
||||
"""
|
||||
Downloader for FS7 (French Stream) series site.
|
||||
|
||||
FS7 is a French streaming site for TV series and films.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.base_url = "https://fs7.lol"
|
||||
self.search_url = f"{self.base_url}/"
|
||||
# Update client headers to mimic browser
|
||||
self.client.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',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
||||
'Accept-Language': 'fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7',
|
||||
'Accept-Encoding': 'gzip, deflate',
|
||||
'Connection': 'keep-alive',
|
||||
'Upgrade-Insecure-Requests': '1'
|
||||
})
|
||||
|
||||
def can_handle(self, url: str) -> bool:
|
||||
"""Check if this downloader can handle the given URL"""
|
||||
return "fs7.lol" in url.lower() or "french-stream" in url.lower()
|
||||
|
||||
async def search_anime(
|
||||
self,
|
||||
query: str,
|
||||
lang: str = "vf"
|
||||
) -> List[Dict[str, str]]:
|
||||
"""
|
||||
Search for series on FS7.
|
||||
|
||||
Args:
|
||||
query: Search query
|
||||
lang: Language preference (vf, vostfr)
|
||||
|
||||
Returns:
|
||||
List of series with title, url, cover_image
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Searching FS7 for: {query}")
|
||||
|
||||
# FS7 uses GET request with query parameters for search
|
||||
response = await self.client.get(
|
||||
self.search_url,
|
||||
params={
|
||||
"do": "search",
|
||||
"subaction": "search",
|
||||
"story": query
|
||||
}
|
||||
)
|
||||
response.raise_for_status()
|
||||
html = response.text
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
results = []
|
||||
|
||||
# Look for series items (FS7 has both films and series in search results)
|
||||
# We filter for /s-tv/ URLs ending with .html (actual series/season pages)
|
||||
items = soup.find_all('a', href=re.compile(r'/s-tv/\d+-.+\.html'))
|
||||
|
||||
for item in items[:20]: # Limit to 20 results
|
||||
url = item.get('href', '')
|
||||
if not url.startswith('http'):
|
||||
url = urljoin(self.base_url, url)
|
||||
|
||||
# Extract title from the item
|
||||
title_elem = item.find('img', alt=True)
|
||||
if title_elem:
|
||||
title = title_elem.get('alt', '').strip()
|
||||
else:
|
||||
# Get text content and clean it
|
||||
text = item.get_text(strip=True)
|
||||
# Skip if it's just a category name
|
||||
if any(cat in text.lower() for cat in ['séries', 'series', 'vf', 'vostfr', 'vo', 'netflix', 'disney', 'amazon', 'apple']):
|
||||
continue
|
||||
title = text
|
||||
|
||||
# Extract cover image
|
||||
img = item.find('img')
|
||||
cover_image = img.get('src', '') if img else ''
|
||||
|
||||
# Only add if we have a title and it's not empty
|
||||
if title and len(title) > 5:
|
||||
# Avoid duplicates
|
||||
if not any(r['url'] == url for r in results):
|
||||
results.append({
|
||||
'title': title,
|
||||
'url': url,
|
||||
'cover_image': cover_image
|
||||
})
|
||||
|
||||
logger.info(f"Found {len(results)} series on FS7")
|
||||
return results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error searching FS7: {e}")
|
||||
return []
|
||||
|
||||
async def get_episodes(
|
||||
self,
|
||||
anime_url: str,
|
||||
lang: str = "vf"
|
||||
) -> List[Dict[str, str]]:
|
||||
"""
|
||||
Get episode list for a series.
|
||||
|
||||
Args:
|
||||
anime_url: URL of the series page
|
||||
lang: Language preference
|
||||
|
||||
Returns:
|
||||
List of episodes with episode number and url
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Fetching episodes from: {anime_url}")
|
||||
|
||||
response = await self.client.get(anime_url)
|
||||
response.raise_for_status()
|
||||
html = response.text
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
episodes = []
|
||||
|
||||
# FS7 stores episode data in JavaScript div elements
|
||||
# Format: <div data-ep="1" data-vidzy="..." data-uqload="..." data-netu="..." data-voe="..."></div>
|
||||
episode_divs = soup.find_all('div', attrs={'data-ep': True})
|
||||
|
||||
for div in episode_divs:
|
||||
ep_num = div.get('data-ep', '').strip()
|
||||
|
||||
# Try different video players in order of preference
|
||||
video_url = None
|
||||
for player in ['data-vidzy', 'data-uqload', 'data-voe', 'data-netu']:
|
||||
player_url = div.get(player, '').strip()
|
||||
if player_url:
|
||||
video_url = player_url
|
||||
logger.debug(f"Found episode {ep_num} on {player}")
|
||||
break
|
||||
|
||||
if video_url and ep_num:
|
||||
episodes.append({
|
||||
'episode': ep_num,
|
||||
'url': video_url
|
||||
})
|
||||
|
||||
# Sort by episode number
|
||||
episodes.sort(key=lambda x: int(x['episode']) if x['episode'].isdigit() else 0)
|
||||
|
||||
logger.info(f"Found {len(episodes)} episodes")
|
||||
return episodes
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting episodes from FS7: {e}")
|
||||
return []
|
||||
|
||||
async def get_anime_metadata(
|
||||
self,
|
||||
anime_url: str
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get metadata for a series.
|
||||
|
||||
Args:
|
||||
anime_url: URL of the series page
|
||||
|
||||
Returns:
|
||||
Dictionary with metadata
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Fetching metadata from: {anime_url}")
|
||||
|
||||
response = await self.client.get(anime_url)
|
||||
response.raise_for_status()
|
||||
html = response.text
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
|
||||
# Extract title
|
||||
title = soup.find('h1')
|
||||
title = title.get_text(strip=True) if title else "Unknown"
|
||||
|
||||
# Extract description/synopsis
|
||||
description_elem = soup.find('div', class_='full-text')
|
||||
description = description_elem.get_text(strip=True) if description_elem else ""
|
||||
|
||||
# Extract cover image
|
||||
img = soup.find('img', class_='poster')
|
||||
poster_image = img.get('src', '') if img else ''
|
||||
|
||||
# Try to get poster from meta tag if not found
|
||||
if not poster_image:
|
||||
meta_img = soup.find('meta', property='og:image')
|
||||
poster_image = meta_img.get('content', '') if meta_img else ''
|
||||
|
||||
# Extract year
|
||||
year_match = re.search(r'\b(19|20)\d{2}\b', description)
|
||||
release_year = int(year_match.group()) if year_match else None
|
||||
|
||||
return {
|
||||
'title': title,
|
||||
'synopsis': description,
|
||||
'poster_image': poster_image,
|
||||
'release_year': release_year,
|
||||
'genres': [],
|
||||
'rating': None,
|
||||
'studio': None,
|
||||
'total_episodes': None,
|
||||
'status': None
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting metadata from FS7: {e}")
|
||||
return {
|
||||
'title': "Unknown",
|
||||
'synopsis': "",
|
||||
'poster_image': '',
|
||||
'genres': [],
|
||||
'rating': None,
|
||||
'release_year': None,
|
||||
'studio': None,
|
||||
'total_episodes': None,
|
||||
'status': None
|
||||
}
|
||||
|
||||
async def get_download_link(
|
||||
self,
|
||||
url: str,
|
||||
target_filename: Optional[str] = None
|
||||
) -> tuple[str, str]:
|
||||
"""
|
||||
Extract download link from video player URL.
|
||||
|
||||
Args:
|
||||
url: Video player URL
|
||||
target_filename: Optional filename override
|
||||
|
||||
Returns:
|
||||
Tuple of (download_url, filename)
|
||||
"""
|
||||
# FS7 uses embedded video players
|
||||
# Delegate to the appropriate video player downloader
|
||||
from app.downloaders.video_players import get_video_player
|
||||
|
||||
player = get_video_player(url)
|
||||
if player:
|
||||
return await player.get_download_link(url, target_filename)
|
||||
else:
|
||||
raise ValueError(f"No video player found for URL: {url}")
|
||||
Reference in New Issue
Block a user