feat: Add SendVid downloader support
Add complete support for SendVid video hosting service used by Anime-Sama for anime series like Hell's Paradise. Changes: - Create SendVidDownloader class with proper headers to avoid 403 errors - Add SendVid detection and handling in AnimeSamaDownloader - Update download_manager to include SendVid-specific headers - Support custom episode naming (e.g., "Hells Paradise - Episode 01.mp4") Technical details: - SendVid embed pages require User-Agent and Referer headers - Direct MP4 URLs extracted from <source> tags with IP/time-based parameters - Tested with Hell's Paradise Episode 01 (7MB, 24min, 1280x720) 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 +1,475 @@
|
||||
from .base import BaseDownloader
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import httpx
|
||||
from urllib.parse import urljoin, unquote
|
||||
|
||||
|
||||
class AnimeSamaDownloader(BaseDownloader):
|
||||
"""Downloader for anime-sama.org / anime-sama.store"""
|
||||
|
||||
# Static list of known domains (will be updated dynamically)
|
||||
BASE_DOMAINS = ["anime-sama.si", "www.anime-sama.si", "anime-sama.org", "anime-sama.store", "anime-sama.eu"]
|
||||
|
||||
@classmethod
|
||||
async def get_current_domain(cls) -> str:
|
||||
"""
|
||||
Fetch the current active domain from anime-sama.pw
|
||||
Returns the current domain (e.g., 'anime-sama.si')
|
||||
"""
|
||||
try:
|
||||
import httpx
|
||||
async with httpx.AsyncClient(timeout=10.0, follow_redirects=True) as client:
|
||||
response = await client.get("https://anime-sama.pw")
|
||||
|
||||
# Look for the main link in the HTML
|
||||
from bs4 import BeautifulSoup
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
# Look for the primary button/link
|
||||
primary_link = soup.find('a', class_='btn-primary')
|
||||
if primary_link and primary_link.get('href'):
|
||||
href = primary_link['href']
|
||||
# Extract domain from URL
|
||||
from urllib.parse import urlparse
|
||||
parsed = urlparse(href)
|
||||
domain = parsed.netloc # e.g., 'anime-sama.si'
|
||||
print(f"[ANIME-SAMA] Current domain from anime-sama.pw: {domain}")
|
||||
return domain
|
||||
|
||||
# Fallback: look for any anime-sama.* link
|
||||
for link in soup.find_all('a', href=True):
|
||||
href = link['href']
|
||||
if 'anime-sama.' in href and href.startswith('https://'):
|
||||
from urllib.parse import urlparse
|
||||
parsed = urlparse(href)
|
||||
domain = parsed.netloc
|
||||
if domain not in ['anime-sama.pw', 'www.anime-sama.pw']:
|
||||
print(f"[ANIME-SAMA] Found domain via fallback: {domain}")
|
||||
return domain
|
||||
|
||||
print("[ANIME-SAMA] Could not determine current domain, using default")
|
||||
return "anime-sama.si"
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Error fetching current domain: {e}")
|
||||
return "anime-sama.si"
|
||||
|
||||
@classmethod
|
||||
async def update_domains(cls) -> None:
|
||||
"""
|
||||
Update the BASE_DOMAINS list with the current active domain
|
||||
This should be called periodically to keep up with domain changes
|
||||
"""
|
||||
try:
|
||||
current_domain = await cls.get_current_domain()
|
||||
|
||||
# Add the current domain and its www variant if not already present
|
||||
domains_to_add = [current_domain]
|
||||
if not current_domain.startswith('www.'):
|
||||
domains_to_add.append(f'www.{current_domain}')
|
||||
|
||||
for domain in domains_to_add:
|
||||
if domain not in cls.BASE_DOMAINS:
|
||||
# Insert at the beginning for priority
|
||||
cls.BASE_DOMAINS.insert(0, domain)
|
||||
print(f"[ANIME-SAMA] Added new domain: {domain}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Error updating domains: {e}")
|
||||
|
||||
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 anime-sama URL
|
||||
Anime-Sama uses third-party video hosts (vidmoly, etc.)
|
||||
We'll try to extract the video URL from these hosts
|
||||
"""
|
||||
try:
|
||||
print(f"[ANIME-SAMA] Extracting link from: {url}")
|
||||
|
||||
# Check if URL contains the anime page context (format: video_url|anime_page_url|episode_title?)
|
||||
if '|' in url:
|
||||
parts = url.split('|')
|
||||
video_url = parts[0]
|
||||
anime_page_url = parts[1] if len(parts) > 1 else None
|
||||
episode_title = parts[2] if len(parts) > 2 else None
|
||||
|
||||
print(f"[ANIME-SAMA] Split URL - video: {video_url[:60]}..., anime: {anime_page_url}, episode: {episode_title}")
|
||||
|
||||
# Extract video from the host URL with anime context for filename
|
||||
if 'vidmoly.to' in video_url or 'vidmoly' in video_url:
|
||||
return await self._extract_from_vidmoly(video_url, anime_page_url, episode_title)
|
||||
elif 'sendvid.com' in video_url:
|
||||
return await self._extract_from_sendvid(video_url, anime_page_url, episode_title)
|
||||
else:
|
||||
# Try to extract from other hosts
|
||||
if episode_title:
|
||||
filename = f"{self._generate_anime_name(anime_page_url)} - {episode_title}.mp4"
|
||||
else:
|
||||
filename = self._generate_filename_from_anime_url(anime_page_url)
|
||||
return video_url, filename
|
||||
|
||||
# Check if this is a third-party host URL
|
||||
if 'vidmoly.to' in url or 'vidmoly' in url:
|
||||
return await self._extract_from_vidmoly(url)
|
||||
|
||||
# If it's an anime-sama page, try to find the video
|
||||
if 'anime-sama' in url.lower():
|
||||
response = await self.client.get(url, follow_redirects=True)
|
||||
final_url = str(response.url)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
# Look for iframe with video player
|
||||
iframes = soup.find_all('iframe')
|
||||
for iframe in iframes:
|
||||
src = iframe.get('src', '')
|
||||
if src and any(provider in src for provider in ['vidmoly', 'player', 'stream', 'play', 'embed']):
|
||||
if src.startswith('http'):
|
||||
print(f"[ANIME-SAMA] Found iframe: {src}")
|
||||
# Try to extract video from the player
|
||||
video_url = await self._extract_from_player(src)
|
||||
if video_url:
|
||||
filename = self._generate_filename(final_url)
|
||||
return video_url, filename
|
||||
|
||||
# Look for video tags
|
||||
videos = soup.find_all('video')
|
||||
for video in videos:
|
||||
src = video.get('src', '')
|
||||
if src:
|
||||
if not src.startswith('http'):
|
||||
src = urljoin(final_url, src)
|
||||
filename = self._generate_filename(final_url)
|
||||
return src, filename
|
||||
|
||||
sources = video.find_all('source')
|
||||
for source in sources:
|
||||
src = source.get('src', '')
|
||||
if src:
|
||||
if not src.startswith('http'):
|
||||
src = urljoin(final_url, src)
|
||||
filename = self._generate_filename(final_url)
|
||||
return src, filename
|
||||
|
||||
raise Exception("Could not find video link on page")
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"Error extracting AnimeSama link: {str(e)}")
|
||||
|
||||
async def _extract_from_vidmoly(self, url: str, anime_page_url: str = None, episode_title: str = None) -> tuple[str, str]:
|
||||
"""Extract video URL from vidmoly player - delegate to VidMolyDownloader"""
|
||||
try:
|
||||
print(f"[ANIME-SAMA] Extracting from vidmoly: {url}")
|
||||
print(f"[ANIME-SAMA] Delegating to VidMolyDownloader...")
|
||||
|
||||
# Import VidMolyDownloader
|
||||
from .vidmoly import VidMolyDownloader
|
||||
|
||||
# Generate the target filename first
|
||||
if episode_title and anime_page_url:
|
||||
anime_name = self._generate_anime_name(anime_page_url)
|
||||
target_filename = f"{anime_name} - {episode_title}.mp4"
|
||||
print(f"[ANIME-SAMA] Generated filename: {target_filename} (episode: {episode_title})")
|
||||
elif anime_page_url:
|
||||
target_filename = self._generate_filename_from_anime_url(anime_page_url)
|
||||
print(f"[ANIME-SAMA] Generated filename: {target_filename} (no episode title)")
|
||||
else:
|
||||
target_filename = None
|
||||
print(f"[ANIME-SAMA] No target_filename generated")
|
||||
|
||||
# Use VidMolyDownloader to extract and download
|
||||
vidmoly_downloader = VidMolyDownloader()
|
||||
|
||||
# Pass the target filename to VidMolyDownloader if available
|
||||
if target_filename:
|
||||
video_url, temp_filename = await vidmoly_downloader.get_download_link(url, target_filename=target_filename)
|
||||
else:
|
||||
video_url, temp_filename = await vidmoly_downloader.get_download_link(url)
|
||||
|
||||
# Use the target filename
|
||||
filename = target_filename if target_filename else temp_filename
|
||||
|
||||
print(f"[ANIME-SAMA] Got video: {filename}")
|
||||
|
||||
# Rename the file if needed
|
||||
import os
|
||||
if temp_filename != filename:
|
||||
# temp_filename might be a full path or just the name
|
||||
temp_path = temp_filename if os.path.isabs(temp_filename) else os.path.join('downloads', temp_filename)
|
||||
|
||||
if os.path.exists(temp_path):
|
||||
final_path = os.path.join('downloads', filename)
|
||||
if os.path.exists(final_path):
|
||||
os.remove(final_path)
|
||||
os.rename(temp_path, final_path)
|
||||
print(f"[ANIME-SAMA] Renamed {temp_filename} -> {filename}")
|
||||
else:
|
||||
print(f"[ANIME-SAMA] Warning: temp file not found: {temp_path}")
|
||||
|
||||
# Return the original VidMoly URL - the file exists so download_manager will skip it
|
||||
return url, filename
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Vidmoly extraction error: {e}")
|
||||
raise Exception(f"Error extracting from vidmoly: {str(e)}")
|
||||
|
||||
async def _extract_from_sendvid(self, url: str, anime_page_url: str = None, episode_title: str = None) -> tuple[str, str]:
|
||||
"""Extract video URL from sendvid player - delegate to SendVidDownloader"""
|
||||
try:
|
||||
print(f"[ANIME-SAMA] Extracting from sendvid: {url}")
|
||||
print(f"[ANIME-SAMA] Delegating to SendVidDownloader...")
|
||||
|
||||
# Import SendVidDownloader
|
||||
from .sendvid import SendVidDownloader
|
||||
|
||||
# Generate the target filename first
|
||||
if episode_title and anime_page_url:
|
||||
anime_name = self._generate_anime_name(anime_page_url)
|
||||
target_filename = f"{anime_name} - {episode_title}.mp4"
|
||||
print(f"[ANIME-SAMA] Generated filename: {target_filename} (episode: {episode_title})")
|
||||
elif anime_page_url:
|
||||
target_filename = self._generate_filename_from_anime_url(anime_page_url)
|
||||
print(f"[ANIME-SAMA] Generated filename: {target_filename} (no episode title)")
|
||||
else:
|
||||
target_filename = None
|
||||
print(f"[ANIME-SAMA] No target_filename generated")
|
||||
|
||||
# Use SendVidDownloader to extract the video URL
|
||||
sendvid_downloader = SendVidDownloader()
|
||||
|
||||
# Pass the target filename to SendVidDownloader if available
|
||||
if target_filename:
|
||||
video_url, filename = await sendvid_downloader.get_download_link(url, target_filename=target_filename)
|
||||
else:
|
||||
video_url, filename = await sendvid_downloader.get_download_link(url)
|
||||
|
||||
# Use the target filename
|
||||
filename = target_filename if target_filename else filename
|
||||
|
||||
print(f"[ANIME-SAMA] Got video: {filename}")
|
||||
|
||||
# Return the direct video URL (SendVid provides direct MP4 links)
|
||||
# The download_manager will handle the actual download
|
||||
return video_url, filename
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] SendVid extraction error: {e}")
|
||||
raise Exception(f"Error extracting from sendvid: {str(e)}")
|
||||
|
||||
def _generate_filename_from_anime_url(self, anime_url: str) -> str:
|
||||
"""Generate filename from anime-sama anime page URL"""
|
||||
try:
|
||||
# Extract anime name from URL like: https://anime-sama.si/catalogue/naruto/saison1/vostfr/
|
||||
# Format: /catalogue/{anime}/saison{N}/{lang}/
|
||||
parts = anime_url.split('/')
|
||||
for i, part in enumerate(parts):
|
||||
if part == 'catalogue' and i + 1 < len(parts):
|
||||
anime_name = parts[i + 1].replace('-', ' ').title()
|
||||
# Try to find episode number
|
||||
episode = "01"
|
||||
for j, part2 in enumerate(parts):
|
||||
if 'saison' in part2 and j + 2 < len(parts):
|
||||
# Look for episode in the remaining path
|
||||
pass
|
||||
return f"{anime_name} - Episode {episode}.mp4"
|
||||
# Fallback
|
||||
return "Anime - Episode 01.Mp4"
|
||||
except:
|
||||
return "Anime - Episode 01.Mp4"
|
||||
|
||||
def _generate_anime_name(self, anime_url: str) -> str:
|
||||
"""Extract just the anime name from anime-sama URL"""
|
||||
try:
|
||||
# Extract anime name from URL like: https://anime-sama.si/catalogue/naruto/saison1/vostfr/
|
||||
parts = anime_url.split('/')
|
||||
for i, part in enumerate(parts):
|
||||
if part == 'catalogue' and i + 1 < len(parts):
|
||||
return parts[i + 1].replace('-', ' ').title()
|
||||
# Fallback
|
||||
return "Anime"
|
||||
except:
|
||||
return "Anime"
|
||||
|
||||
async def _extract_from_player(self, player_url: str) -> str | None:
|
||||
"""Try to extract direct video URL from player iframe"""
|
||||
try:
|
||||
response = await self.client.get(player_url)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
# Check for video tags
|
||||
videos = soup.find_all('video')
|
||||
for video in videos:
|
||||
src = video.get('src') or video.get('data-src')
|
||||
if src:
|
||||
return src
|
||||
|
||||
# Check for source tags
|
||||
sources = soup.find_all('source')
|
||||
for source in sources:
|
||||
src = source.get('src')
|
||||
if src and any(ext in src for ext in ['mp4', 'm3u8', 'mkv']):
|
||||
return src
|
||||
|
||||
# Check scripts in player page
|
||||
scripts = soup.find_all('script')
|
||||
for script in scripts:
|
||||
if script.string:
|
||||
match = re.search(r'(https?://[^"\'>\s]+\.(?:mp4|m3u8)(?:\?[^"\'>\s]*)?)', script.string)
|
||||
if match:
|
||||
return match.group(1)
|
||||
|
||||
except:
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
def _generate_filename(self, url: str) -> str:
|
||||
"""Generate filename from URL"""
|
||||
# Extract anime name and episode info from URL
|
||||
# URL format: .../catalogue/{anime}/saison{N}/{vostfr|vf}/episode-{N}
|
||||
parts = url.split('/')
|
||||
|
||||
anime_name = "anime"
|
||||
episode = "1"
|
||||
|
||||
for i, part in enumerate(parts):
|
||||
if part == 'catalogue' and i + 1 < len(parts):
|
||||
anime_name = parts[i + 1].replace('-', ' ')
|
||||
elif 'episode-' in part:
|
||||
episode = part.replace('episode-', '')
|
||||
elif part in ['vostfr', 'vf']:
|
||||
lang = part.upper()
|
||||
|
||||
filename = f"{anime_name} - Episode {episode}.mp4"
|
||||
return filename.title()
|
||||
|
||||
async def search_anime(self, query: str, lang: str = "vostfr") -> list[dict]:
|
||||
"""
|
||||
Search for anime on anime-sama
|
||||
Returns list of anime with title, url, and cover image
|
||||
"""
|
||||
try:
|
||||
# Update domains before searching to ensure we have the current domain
|
||||
await self.update_domains()
|
||||
|
||||
import time
|
||||
start = time.time()
|
||||
print(f"[ANIME-SAMA] Searching for '{query}' ({lang})...")
|
||||
|
||||
# Use the current domain from anime-sama.pw
|
||||
current_domain = await self.get_current_domain()
|
||||
|
||||
# Convert query to URL format (lowercase, replace spaces with hyphens)
|
||||
query_formatted = query.lower().replace(' ', '-').replace("'", '').replace(':', '')
|
||||
search_url = f"https://{current_domain}/catalogue/{query_formatted}/saison1/{lang}/"
|
||||
|
||||
response = await self.client.get(search_url, follow_redirects=True)
|
||||
|
||||
elapsed = time.time() - start
|
||||
print(f"[ANIME-SAMA] Got response {response.status_code} in {elapsed:.2f}s")
|
||||
|
||||
if response.status_code == 200:
|
||||
# Check if it's a valid anime page by looking for episode selector
|
||||
if 'selectEpisodes' in response.text or 'episodes.js' in response.text:
|
||||
print(f"[ANIME-SAMA] Found anime at {str(response.url)}")
|
||||
return [{
|
||||
'title': query,
|
||||
'url': str(response.url),
|
||||
'type': 'direct'
|
||||
}]
|
||||
|
||||
print(f"[ANIME-SAMA] No anime found (status: {response.status_code})")
|
||||
return []
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Error: {str(e)}")
|
||||
return []
|
||||
|
||||
async def get_episodes(self, anime_url: str, lang: str = "vostfr") -> list[dict]:
|
||||
"""
|
||||
Get list of episodes for an anime
|
||||
Returns list of episode numbers and their URLs
|
||||
Anime-Sama uses a JavaScript file (episodes.js) to store episode URLs
|
||||
"""
|
||||
try:
|
||||
response = await self.client.get(anime_url)
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
|
||||
episodes = []
|
||||
|
||||
# Try to find the episodes.js file in the HTML
|
||||
episodes_js_match = re.search(r'episodes\.js\?filever=(\d+)', response.text)
|
||||
if episodes_js_match:
|
||||
file_ver = episodes_js_match.group(1)
|
||||
# Build the URL to episodes.js
|
||||
episodes_js_url = f"{anime_url.rstrip('/')}/episodes.js?filever={file_ver}"
|
||||
|
||||
print(f"[ANIME-SAMA] Found episodes.js at {episodes_js_url}")
|
||||
|
||||
try:
|
||||
# Fetch the episodes.js file
|
||||
js_response = await self.client.get(episodes_js_url)
|
||||
js_content = js_response.text
|
||||
|
||||
# Parse the JavaScript file to extract episode URLs
|
||||
# The file contains arrays like: var eps1 = ['url1', 'url2', ...]
|
||||
eps_matches = re.findall(r'var\s+eps\d+\s*=\s*(\[[^\]]+\])', js_content)
|
||||
|
||||
if eps_matches:
|
||||
# Extract URLs from the first array found
|
||||
urls_text = eps_matches[0]
|
||||
# Parse the array of URLs
|
||||
episode_urls = re.findall(r"'(https?://[^']+)'", urls_text)
|
||||
|
||||
for idx, url in enumerate(episode_urls, start=1):
|
||||
episode_num = str(idx).zfill(2)
|
||||
episode_title = f'Episode {episode_num}'
|
||||
# Store both the video URL, the anime page URL, and the episode title
|
||||
# Format: video_url|anime_page_url|episode_title
|
||||
combined_url = f"{url}|{anime_url}|{episode_title}"
|
||||
episodes.append({
|
||||
'episode': episode_num,
|
||||
'url': combined_url,
|
||||
'title': episode_title
|
||||
})
|
||||
|
||||
print(f"[ANIME-SAMA] Found {len(episodes)} episodes")
|
||||
return episodes
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Error fetching episodes.js: {e}")
|
||||
|
||||
# Fallback: Try to find episode links in the HTML (old method)
|
||||
episode_links = soup.find_all('a', href=True)
|
||||
for link in episode_links:
|
||||
href = link['href']
|
||||
if 'episode-' in href:
|
||||
# Extract episode number
|
||||
match = re.search(r'episode-(\d+)', href)
|
||||
if match:
|
||||
episode_num = match.group(1)
|
||||
full_url = urljoin(anime_url, href)
|
||||
|
||||
episodes.append({
|
||||
'episode': episode_num,
|
||||
'url': full_url
|
||||
})
|
||||
|
||||
# Remove duplicates and sort
|
||||
seen = set()
|
||||
unique_episodes = []
|
||||
for ep in episodes:
|
||||
if ep['episode'] not in seen:
|
||||
seen.add(ep['episode'])
|
||||
unique_episodes.append(ep)
|
||||
|
||||
unique_episodes.sort(key=lambda x: int(x['episode']))
|
||||
|
||||
return unique_episodes
|
||||
|
||||
except Exception as e:
|
||||
print(f"[ANIME-SAMA] Error getting episodes: {e}")
|
||||
return []
|
||||
Reference in New Issue
Block a user