from typing import Optional from bs4 import BeautifulSoup from .base import BaseVideoPlayer import re class SendVidDownloader(BaseVideoPlayer): """Downloader for SendVid videos""" def can_handle(self, url: str) -> bool: return "sendvid.com" in url.lower() async def _fetch_page(self, url: str) -> str: """Fetch page with proper headers to avoid 403 errors""" headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36', 'Referer': 'https://sendvid.com/', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Accept-Language': 'en-US,en;q=0.5', } response = await self.client.get(url, headers=headers) response.raise_for_status() return response.text async def get_download_link(self, url: str, target_filename: str = None) -> tuple[str, str]: """ Extract direct download link from SendVid embed page SendVid embed pages contain the direct MP4 URL in a tag """ print(f"[SENDVID] Fetching page: {url}") html = await self._fetch_page(url) soup = BeautifulSoup(html, 'lxml') # Try to find the video source in the tag source_tag = soup.find('source', {'id': 'video_source'}) if source_tag and source_tag.get('src'): video_url = source_tag['src'] print(f"[SENDVID] Found video URL in tag") # Generate filename if target_filename: filename = target_filename else: # Extract filename from video URL or generate one filename = self._extract_filename_from_url(url, video_url) print(f"[SENDVID] Download URL: {video_url}") print(f"[SENDVID] Filename: {filename}") return video_url, filename # Fallback: try to find in og:video meta property og_video = soup.find('meta', {'property': 'og:video'}) if og_video and og_video.get('content'): video_url = og_video['content'] print(f"[SENDVID] Found video URL in og:video meta") if target_filename: filename = target_filename else: filename = self._extract_filename_from_url(url, video_url) print(f"[SENDVID] Download URL: {video_url}") print(f"[SENDVID] Filename: {filename}") return video_url, filename raise Exception("Could not extract video URL from SendVid page") def _extract_filename_from_url(self, page_url: str, video_url: str) -> str: """Generate filename from SendVod URLs""" # Try to extract video ID from page URL video_id_match = re.search(r'/embed/([a-z0-9]+)', page_url) if video_id_match: video_id = video_id_match.group(1) # Try to get title from page (might need to fetch, but for now use ID) return f"sendvid_{video_id}.mp4" # Fallback: extract from video URL filename_match = re.search(r'/([^/]+\.mp4)', video_url) if filename_match: return filename_match.group(1) return "sendvid_video.mp4"