Kimi Agent
520be53901
- Add proper Alembic initial migration (0001_initial_schema.py) - Migrate refresh tokens from JSON file to SQLite (RefreshTokenTable) - Remove Neko-Sama provider entirely (redirects to Gupy, not a host) - Fix provider health check always showing UNKNOWN - Run check_all_health() on startup - Fix POST /providers/health/check background task bug - Add HTMX refresh after manual health check trigger - Fix anime search relevance scoring with MIN_RELEVANCE_THRESHOLD=0.5 - Replace bare 'except:' with 'except Exception:' across codebase - Add Playwright E2E test suite (12 tests, auth setup, helpers) - Fix toast container blocking clicks via pointer-events: none - Remove obsolete Jest/Vite test files and config - Clean up obsolete test_watchlist scripts - Update sonarr model comment for active providers
76 lines
3.1 KiB
Python
76 lines
3.1 KiB
Python
from .base import BaseVideoPlayer
|
|
from bs4 import BeautifulSoup
|
|
import re
|
|
import httpx
|
|
|
|
|
|
class RapidFileDownloader(BaseVideoPlayer):
|
|
"""Downloader for rapidfile.net and similar hosts"""
|
|
|
|
def can_handle(self, url: str) -> bool:
|
|
return any(domain in url.lower() for domain in ["rapidfile.net", "rapidfile.com", "rapid-file"])
|
|
|
|
async def get_download_link(self, url: str) -> tuple[str, str]:
|
|
try:
|
|
# Get the initial page
|
|
response = await self.client.get(url)
|
|
response.raise_for_status()
|
|
soup = BeautifulSoup(response.text, 'lxml')
|
|
|
|
download_url = None
|
|
filename = "rapidfile_download"
|
|
|
|
# Method 1: Look for download button/link
|
|
download_btn = soup.find('a', {'id': 'downloadbtn'}) or soup.find('a', class_='download-btn')
|
|
if download_btn and download_btn.get('href'):
|
|
download_url = download_btn['href']
|
|
|
|
# Method 2: Look for form with POST action
|
|
if not download_url:
|
|
forms = soup.find_all('form')
|
|
for form in forms:
|
|
action = form.get('action', '')
|
|
if action and ('download' in action.lower() or 'file' in action.lower()):
|
|
download_url = action if action.startswith('http') else url + action
|
|
break
|
|
|
|
# Method 3: Look for any link with download/file in URL
|
|
if not download_url:
|
|
for link in soup.find_all('a', href=True):
|
|
href = link['href']
|
|
if any(keyword in href.lower() for keyword in ['download', 'get_file', 'file.php']):
|
|
if href.startswith('http'):
|
|
download_url = href
|
|
break
|
|
|
|
# Method 4: Check for direct file links in scripts
|
|
if not download_url:
|
|
scripts = soup.find_all('script')
|
|
for script in scripts:
|
|
if script.string:
|
|
match = re.search(r'(https?://[^\s\"\'<>]+/(?:download|file)[^\s\"\'<>]+)', script.string)
|
|
if match:
|
|
download_url = match.group(0)
|
|
break
|
|
|
|
if download_url:
|
|
# Get filename from headers or URL
|
|
try:
|
|
head_resp = await self.client.head(download_url, timeout=5.0)
|
|
fname = self._extract_filename_from_headers(head_resp.headers)
|
|
if fname:
|
|
filename = fname
|
|
else:
|
|
filename = download_url.split('/')[-1] or "rapidfile_download"
|
|
except Exception:
|
|
filename = download_url.split('/')[-1] or "rapidfile_download"
|
|
|
|
return download_url, filename
|
|
|
|
# If all else fails, return the original URL
|
|
filename = url.split('/')[-1] or "rapidfile_download"
|
|
return url, filename
|
|
|
|
except Exception as e:
|
|
raise Exception(f"Error extracting Rapidfile link: {str(e)}")
|