feat: add multiple video player support for Frieren S2 downloads
- Add Lpayer API decryption using AES (key: kiemtienmua911ca) - Add yt-dlp extraction for bypassing player blocking - Add HTTP 206 support for video validation (Range header) - Add VidMoly .biz domain support (alternative to .to) - Add SendVid extraction (working - downloaded S1 and S2 E1) - Add player fallback system with caching per anime URL - Add video URL validation before returning to downloader - Update HTTP clients with realistic browser headers - Add pycryptodome to requirements.txt - Add test file for fallback system Downloads working: SendVid (primary), Lpayer (403 issue), VidMoly (testing)
This commit is contained in:
root
@@ -1,20 +1,55 @@
|
||||
from .base import BaseAnimeSite
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
from typing import Optional
|
||||
from urllib.parse import urljoin
|
||||
|
||||
|
||||
class NekoSamaDownloader(BaseAnimeSite):
|
||||
"""Downloader for neko-sama.fr"""
|
||||
"""Downloader for neko-sama.org (anime streaming via Gupy)
|
||||
|
||||
NOTE: neko-sama.org now redirects to Gupy, which is a legal streaming search engine.
|
||||
It does NOT host video content - it provides metadata about where to watch legally.
|
||||
This provider can search and get metadata but cannot provide direct download links.
|
||||
"""
|
||||
|
||||
BASE_DOMAINS = ["neko-sama.fr", "nekosama.fr", "www.neko-sama.fr"]
|
||||
BASE_DOMAINS = ["neko-sama.org", "www.neko-sama.org", "neko-sama.fr", "nekosama.fr", "www.gupy.fr", "gupy.fr"]
|
||||
|
||||
def can_handle(self, url: str) -> bool:
|
||||
return any(domain in url.lower() for domain in self.BASE_DOMAINS)
|
||||
|
||||
async def get_download_link(self, url: str) -> tuple[str, str]:
|
||||
"""Extract download link from neko-sama URL"""
|
||||
async def get_download_link(self, url: str, target_filename: Optional[str] = None) -> tuple[str, str]:
|
||||
"""
|
||||
Extract download link from neko-sama URL.
|
||||
|
||||
NOTE: neko-sama.org/Gupy is a legal streaming search engine, NOT a video host.
|
||||
This returns streaming platform information instead of direct video links.
|
||||
"""
|
||||
try:
|
||||
# Check if this is a Gupy URL
|
||||
if 'gupy.fr' in url or 'neko-sama.org' in url:
|
||||
response = await self.client.get(url, follow_redirects=True)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
# Look for streaming platform links
|
||||
streaming_links = []
|
||||
for link in soup.find_all('a', href=True):
|
||||
href = link.get('href', '')
|
||||
if '/out/' in href:
|
||||
text = link.get_text(strip=True)
|
||||
if text and 'Regarder' in text:
|
||||
streaming_links.append(f"{text}: {href}")
|
||||
|
||||
if streaming_links:
|
||||
title_elem = soup.find('h1') or soup.find('title')
|
||||
title = title_elem.get_text(strip=True).split('|')[0].strip() if title_elem else "Unknown"
|
||||
info = "Available streaming platforms:\n" + "\n".join(streaming_links[:5])
|
||||
filename = target_filename or f"{title}_streaming_info.txt"
|
||||
return info, filename
|
||||
|
||||
raise Exception("No streaming links found - Gupy is a legal streaming search, not a video host")
|
||||
|
||||
# Legacy: try original method for other URLs
|
||||
response = await self.client.get(url, follow_redirects=True)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
@@ -60,7 +95,7 @@ class NekoSamaDownloader(BaseAnimeSite):
|
||||
filename = self._generate_filename(str(response.url))
|
||||
return match, filename
|
||||
|
||||
raise Exception("Could not find video link")
|
||||
raise Exception("Could not find video link - Neko-Sama/Gupy does not host video content")
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"Error extracting NekoSama link: {str(e)}")
|
||||
@@ -80,11 +115,13 @@ class NekoSamaDownloader(BaseAnimeSite):
|
||||
return filename.title()
|
||||
|
||||
async def get_episodes(self, anime_url: str, lang: str = "vostfr") -> list[dict]:
|
||||
"""Get list of episodes for an anime."""
|
||||
try:
|
||||
response = await self.client.get(anime_url)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
episodes = []
|
||||
# Try to find episode links
|
||||
episode_links = soup.find_all('a', href=re.compile(r'episode'))
|
||||
|
||||
for link in episode_links:
|
||||
@@ -112,10 +149,7 @@ class NekoSamaDownloader(BaseAnimeSite):
|
||||
return []
|
||||
|
||||
async def get_anime_metadata(self, anime_url: str) -> dict:
|
||||
"""
|
||||
Extract rich metadata from anime page
|
||||
Returns synopsis, genres, rating, release year, studio, etc.
|
||||
"""
|
||||
"""Extract rich metadata from anime page."""
|
||||
try:
|
||||
print(f"[NEKO-SAMA] Extracting metadata from: {anime_url}")
|
||||
response = await self.client.get(anime_url)
|
||||
@@ -134,68 +168,55 @@ class NekoSamaDownloader(BaseAnimeSite):
|
||||
'alternative_titles': []
|
||||
}
|
||||
|
||||
# Extract synopsis
|
||||
synopsis_selectors = [
|
||||
'div.synopsis',
|
||||
'div.description',
|
||||
'div[class*="synopsis"]',
|
||||
'div[class*="desc"]',
|
||||
'p.synopsis',
|
||||
'.anime-synopsis',
|
||||
'.summary'
|
||||
]
|
||||
# Extract title and year from h1
|
||||
title_elem = soup.find('h1')
|
||||
if title_elem:
|
||||
title_text = title_elem.get_text(strip=True)
|
||||
# Extract year from title like "Naruto (2002)"
|
||||
year_match = re.search(r'\((\d{4})\)', title_text)
|
||||
if year_match:
|
||||
metadata['release_year'] = int(year_match.group(1))
|
||||
|
||||
# Extract synopsis - Gupy shows it as paragraphs
|
||||
synopsis_elem = soup.find('p')
|
||||
if synopsis_elem:
|
||||
text = synopsis_elem.get_text(strip=True)
|
||||
if len(text) > 50:
|
||||
metadata['synopsis'] = text
|
||||
|
||||
for selector in synopsis_selectors:
|
||||
synopsis_elem = soup.select_one(selector)
|
||||
if synopsis_elem:
|
||||
synopsis = synopsis_elem.get_text(strip=True)
|
||||
if len(synopsis) > 50:
|
||||
metadata['synopsis'] = synopsis
|
||||
break
|
||||
|
||||
# Extract genres
|
||||
genre_links = soup.find_all('a', href=re.compile(r'genre|tag|type', re.I))
|
||||
# Extract genres from meta tags or links
|
||||
genre_links = soup.find_all('a', href=re.compile(r'serie-|genre|tag'))
|
||||
if genre_links:
|
||||
metadata['genres'] = [link.get_text(strip=True) for link in genre_links[:5]]
|
||||
genres = []
|
||||
for link in genre_links[:5]:
|
||||
text = link.get_text(strip=True)
|
||||
if text and '/' not in text and len(text) < 30:
|
||||
genres.append(text)
|
||||
metadata['genres'] = genres
|
||||
|
||||
# Extract rating
|
||||
rating_selectors = [
|
||||
'span.rating',
|
||||
'div.rating',
|
||||
'span.score',
|
||||
'div[class*="rating"]',
|
||||
'div[class*="score"]'
|
||||
]
|
||||
|
||||
for selector in rating_selectors:
|
||||
rating_elem = soup.select_one(selector)
|
||||
if rating_elem:
|
||||
rating_text = rating_elem.get_text(strip=True)
|
||||
rating_match = re.search(r'(\d+\.?\d*)\s*/\s*10', rating_text)
|
||||
if rating_match:
|
||||
metadata['rating'] = f"{rating_match.group(1)}/10"
|
||||
break
|
||||
|
||||
# Extract release year
|
||||
page_text = soup.get_text()
|
||||
year_matches = re.findall(r'\b(19\d{2}|20\d{2})\b', page_text)
|
||||
if year_matches:
|
||||
import datetime
|
||||
current_year = datetime.datetime.now().year + 2
|
||||
valid_years = [int(y) for y in year_matches if 1950 <= int(y) <= current_year]
|
||||
if valid_years:
|
||||
from collections import Counter
|
||||
metadata['release_year'] = Counter(valid_years).most_common(1)[0][0]
|
||||
# Extract rating from percentage
|
||||
rating_elem = soup.find(string=re.compile(r'\d+(\.\d+)?%'))
|
||||
if rating_elem:
|
||||
match = re.search(r'(\d+(\.\d+)?)%', rating_elem)
|
||||
if match:
|
||||
rating = float(match.group(1)) / 10
|
||||
metadata['rating'] = f"{rating:.1f}/10"
|
||||
|
||||
# Extract poster image
|
||||
poster_elem = soup.select_one('img.poster, img.cover, .anime-poster img')
|
||||
poster_elem = soup.find('img', src=re.compile(r'poster|poster'))
|
||||
if poster_elem:
|
||||
metadata['poster_image'] = poster_elem.get('src') or poster_elem.get('data-src')
|
||||
metadata['poster_image'] = poster_elem.get('src')
|
||||
|
||||
# Extract total episodes
|
||||
episodes_count = len(await self.get_episodes(anime_url))
|
||||
if episodes_count > 0:
|
||||
metadata['total_episodes'] = episodes_count
|
||||
# Extract episode count from page text
|
||||
page_text = soup.get_text()
|
||||
ep_match = re.search(r'(\d+)\s*episodes?', page_text, re.I)
|
||||
if ep_match:
|
||||
metadata['total_episodes'] = int(ep_match.group(1))
|
||||
|
||||
# Extract studio/director
|
||||
director_elem = soup.find('a', href=re.compile(r'person|réalisé'))
|
||||
if director_elem:
|
||||
metadata['studio'] = director_elem.get_text(strip=True)
|
||||
|
||||
print(f"[NEKO-SAMA] Extracted metadata: {metadata}")
|
||||
return metadata
|
||||
@@ -205,44 +226,59 @@ class NekoSamaDownloader(BaseAnimeSite):
|
||||
return {}
|
||||
|
||||
async def search_anime(self, query: str, lang: str = "vostfr", include_metadata: bool = False) -> list[dict]:
|
||||
"""
|
||||
Search for anime on neko-sama
|
||||
|
||||
Args:
|
||||
query: Search query string
|
||||
lang: Language preference (vostfr, vf)
|
||||
include_metadata: Whether to fetch full metadata for each result (slower)
|
||||
"""
|
||||
"""Search for anime on neko-sama (uses Gupy backend)."""
|
||||
try:
|
||||
import time
|
||||
from html import unescape
|
||||
start = time.time()
|
||||
print(f"[NEKO-SAMA] Searching for '{query}' ({lang})...")
|
||||
|
||||
# Neko-Sama URL pattern: https://neko-sama.fr/anime/{anime-name}
|
||||
search_url = f"https://neko-sama.fr/anime/{query.lower().replace(' ', '-')}"
|
||||
# Neko-Sama now uses Gupy - try the direct URL pattern
|
||||
search_slug = query.lower().replace(' ', '-')
|
||||
search_urls = [
|
||||
f"https://www.gupy.fr/series/{search_slug}/",
|
||||
f"https://neko-sama.org/series/{search_slug}/",
|
||||
]
|
||||
|
||||
response = await self.client.get(search_url)
|
||||
results = []
|
||||
for search_url in search_urls:
|
||||
response = await self.client.get(search_url, follow_redirects=True)
|
||||
print(f"[NEKO-SAMA] Tried {search_url} -> {response.status_code}")
|
||||
|
||||
if response.status_code == 200:
|
||||
final_url = str(response.url)
|
||||
print(f"[NEKO-SAMA] Found anime at {final_url}")
|
||||
|
||||
# Extract title from page
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
title_elem = soup.find('h1') or soup.find('title')
|
||||
title = unescape(title_elem.get_text(strip=True)) if title_elem else query
|
||||
# Clean up title
|
||||
title = title.split('|')[0].split('-')[0].strip()
|
||||
|
||||
result = {
|
||||
'title': title,
|
||||
'url': final_url,
|
||||
'cover_image': None,
|
||||
'type': 'direct',
|
||||
'metadata': None
|
||||
}
|
||||
|
||||
# Try to get poster
|
||||
poster = soup.find('img', src=re.compile(r'poster'))
|
||||
if poster:
|
||||
result['cover_image'] = poster.get('src')
|
||||
|
||||
if include_metadata:
|
||||
metadata = await self.get_anime_metadata(final_url)
|
||||
result['metadata'] = metadata
|
||||
|
||||
results.append(result)
|
||||
break
|
||||
|
||||
elapsed = time.time() - start
|
||||
print(f"[NEKO-SAMA] Got response {response.status_code} in {elapsed:.2f}s")
|
||||
|
||||
if response.status_code == 200:
|
||||
print(f"[NEKO-SAMA] Found anime at {str(response.url)}")
|
||||
result = {
|
||||
'title': query,
|
||||
'url': str(response.url),
|
||||
'type': 'direct',
|
||||
'metadata': None
|
||||
}
|
||||
|
||||
if include_metadata:
|
||||
metadata = await self.get_anime_metadata(str(response.url))
|
||||
result['metadata'] = metadata
|
||||
|
||||
return [result]
|
||||
|
||||
print(f"[NEKO-SAMA] No anime found")
|
||||
return []
|
||||
print(f"[NEKO-SAMA] Search completed in {elapsed:.2f}s, found {len(results)} results")
|
||||
return results
|
||||
|
||||
except Exception as e:
|
||||
print(f"[NEKO-SAMA] Error: {str(e)}")
|
||||
|
||||
Reference in New Issue
Block a user