Add proxy client tests and auxiliary direct downloader

lbry_client.py

@@ -1,4 +1,4 @@
-"""LBRY daemon JSON-RPC client."""
+"""LBRY JSON-RPC client for local daemon or Odysee public proxy."""
 
 import json
 import logging
@@ -20,13 +20,33 @@ class LbryClientError(Exception):
 
 
 class LbryClient:
-    """JSON-RPC client for lbrynet daemon."""
+    """JSON-RPC client for lbrynet daemon or Odysee's public proxy."""
 
-    def __init__(self, api_url: str = "http://127.0.0.1:5279", timeout: int = 60):
+    ODYSEE_PROXY_URL = "https://api.na-backend.odysee.com/api/v1/proxy"
+
+    def __init__(
+        self,
+        api_url: str = "http://127.0.0.1:5279",
+        timeout: int = 60,
+        backend_name: str = "LBRY daemon",
+        supports_file_ops: bool = True,
+    ):
         self.api_url = api_url
         self.timeout = timeout
+        self.backend_name = backend_name
+        self.supports_file_ops = supports_file_ops
         self.session = requests.Session()
 
+    @classmethod
+    def create_odysee_proxy(cls, timeout: int = 60) -> "LbryClient":
+        """Create a client backed by Odysee's public JSON-RPC proxy."""
+        return cls(
+            api_url=cls.ODYSEE_PROXY_URL,
+            timeout=timeout,
+            backend_name="Odysee public proxy",
+            supports_file_ops=False,
+        )
+
     def _call(self, method: str, **params) -> Dict[str, Any]:
         """
         Make a JSON-RPC call to the daemon.
@@ -50,15 +70,15 @@ class LbryClient:
             response.raise_for_status()
         except requests.exceptions.ConnectionError as e:
             raise LbryClientError(
-                f"Could not connect to LBRY daemon at {self.api_url}. "
+                f"Could not connect to {self.backend_name} at {self.api_url}. "
-                f"Make sure lbrynet is installed and running. Error: {e}"
+                f"Error: {e}"
             )
         except requests.exceptions.Timeout:
             raise LbryClientError(
-                f"Request to LBRY daemon timed out after {self.timeout} seconds"
+                f"Request to {self.backend_name} timed out after {self.timeout} seconds"
             )
         except requests.exceptions.RequestException as e:
-            raise LbryClientError(f"Request to LBRY daemon failed: {e}")
+            raise LbryClientError(f"Request to {self.backend_name} failed: {e}")
 
         try:
             data = response.json()
@@ -68,7 +88,7 @@ class LbryClient:
         if "error" in data and data["error"]:
             error = data["error"]
             raise LbryClientError(
-                f"Daemon returned error: {error.get('message', error)}"
+                f"{self.backend_name} returned error: {error.get('message', error)}"
             )
 
         return data.get("result", {})
@@ -169,6 +189,25 @@ class LbryClient:
 
         return self._call("claim_search", **params)
 
+    def find_controlling_channel(self, channel_name: str) -> Optional[Dict[str, Any]]:
+        """
+        Find the controlling channel claim for a channel name.
+
+        This is needed for Odysee's public proxy because user-friendly channel
+        URLs can resolve to non-controlling channel claims that do not enumerate
+        stream uploads correctly.
+        """
+        result = self.claim_search(
+            name=channel_name,
+            claim_type=["channel"],
+            is_controlling=True,
+            order_by=["effective_amount"],
+            page=1,
+            page_size=1,
+        )
+        items = result.get("items", [])
+        return items[0] if items else None
+
     def get(
         self, uri: str, download_directory: Optional[str] = None, **kwargs
     ) -> Dict[str, Any]:

simple_direct_downloader.py

@@ -0,0 +1,254 @@
+"""Simple direct downloader - uses Odysee's public API."""
+
+import json
+import logging
+import time
+from pathlib import Path
+from typing import Dict, Optional
+
+try:
+    import requests
+except ImportError:
+    raise ImportError("requests is required")
+
+from models import Config, DownloadAction
+
+logger = logging.getLogger(__name__)
+
+
+class SimpleDirectDownloader:
+    """Simple downloader that gets files from Odysee CDN."""
+
+    def __init__(self, config: Config, base_dir: Path):
+        self.config = config
+        self.base_dir = base_dir
+        self.session = requests.Session()
+        self.session.headers.update(
+            {
+                "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:120.0) Gecko/20100101 Firefox/120.0"
+            }
+        )
+
+    def download(self, action: DownloadAction, dry_run: bool = False) -> bool:
+        """Download a file from Odysee."""
+        if action.action == "skip_existing":
+            return True
+
+        if dry_run:
+            print(f"[DRY-RUN] Would download: {action.claim_name}")
+            return True
+
+        version_dir = Path(action.target_dir)
+        version_dir.mkdir(parents=True, exist_ok=True)
+
+        try:
+            print(f"\n📥 Downloading: {action.claim_name}")
+
+            # Get the Odysee URL from the LBRY URI
+            odysee_url = self._get_odysee_url(action.uri)
+            print(f"   URL: {odysee_url}")
+
+            # Method 1: Try to get the download link from the page
+            download_url = self._get_download_link_from_page(odysee_url)
+
+            if not download_url:
+                # Method 2: Try API
+                download_url = self._get_from_api(action.uri)
+
+            if not download_url:
+                print(f"   ⚠️ Could not find download URL")
+                return False
+
+            print(f"   Download URL found!")
+
+            # Download the file
+            return self._download_file(
+                download_url, version_dir, action.claim_name, action
+            )
+
+        except Exception as e:
+            print(f"   ❌ Error: {e}")
+            logger.error(f"Download failed: {e}")
+            return False
+
+    def _get_odysee_url(self, lbry_uri: str) -> str:
+        """Convert LBRY URI to Odysee URL."""
+        # lbry://@channel/claim#id -> https://odysee.com/@channel:claim
+        uri = lbry_uri.replace("lbry://", "")
+        parts = uri.split("/")
+        if len(parts) >= 2:
+            channel = parts[0].replace("#", ":")
+            claim = parts[1].split("#")[0]
+            return f"https://odysee.com/{channel}/{claim}"
+        return f"https://odysee.com/{uri.replace('#', ':')}"
+
+    def _get_download_link_from_page(self, odysee_url: str) -> Optional[str]:
+        """Try to extract download link from Odysee page."""
+        try:
+            response = self.session.get(odysee_url, timeout=30)
+            if response.status_code == 200:
+                # Look for various patterns
+                patterns = [
+                    r'"content\":\{\"url\":\"([^\"]+)\"',
+                    r'"streaming_url\":\"([^\"]+)\"',
+                    r'"download_url\":\"([^\"]+)\"',
+                    r'"url\":\"(https://player\.odycdn\.com/[^\"]+)\"',
+                ]
+
+                for pattern in patterns:
+                    match = re.search(pattern, response.text)
+                    if match:
+                        url = match.group(1).replace("\\u0026", "&")
+                        if url.startswith("http"):
+                            return url
+
+            return None
+        except Exception as e:
+            logger.debug(f"Could not get from page: {e}")
+            return None
+
+    def _get_from_api(self, lbry_uri: str) -> Optional[str]:
+        """Try to get download URL from Odysee API."""
+        try:
+            api_url = "https://api.lbry.tv/api/v1/proxy"
+
+            payload = {
+                "jsonrpc": "2.0",
+                "method": "resolve",
+                "params": {"urls": [lbry_uri]},
+                "id": 1,
+            }
+
+            response = self.session.post(api_url, json=payload, timeout=30)
+
+            if response.status_code == 200:
+                data = response.json()
+                result = data.get("result", {}).get(lbry_uri, {})
+
+                # Get claim ID
+                claim_id = result.get("claim_id", "")
+                if claim_id:
+                    # Try common Odysee CDN patterns
+                    urls_to_try = [
+                        f"https://player.odycdn.com/v6/streams/{claim_id}",
+                        f"https://player.odycdn.com/v6/streams/{claim_id}/",
+                        f"https://cdn.lbryplayer.xyz/content/claims/{claim_id}/stream",
+                    ]
+
+                    for url in urls_to_try:
+                        # Test if URL works
+                        head_response = self.session.head(
+                            url, timeout=10, allow_redirects=True
+                        )
+                        if head_response.status_code == 200:
+                            return url
+
+            return None
+        except Exception as e:
+            logger.debug(f"API error: {e}")
+            return None
+
+    def _download_file(
+        self, url: str, version_dir: Path, claim_name: str, action: DownloadAction
+    ) -> bool:
+        """Download the file with progress."""
+        try:
+            # Try to determine filename
+            filename = f"{claim_name}.mp4"  # Default
+
+            response = self.session.get(url, stream=True, timeout=300)
+
+            # Try to get filename from headers
+            cd_header = response.headers.get("content-disposition", "")
+            if "filename=" in cd_header:
+                import re
+
+                fname_match = re.search(r'filename="?([^"]+)"?', cd_header)
+                if fname_match:
+                    filename = fname_match.group(1)
+
+            file_path = version_dir / filename
+
+            total_size = int(response.headers.get("content-length", 0))
+
+            if total_size > 0:
+                size_mb = total_size / (1024 * 1024)
+                print(f"   Size: {size_mb:.2f} MB")
+
+            print(f"   Saving to: {filename}")
+            print()
+
+            # Download with progress
+            downloaded = 0
+            start_time = time.time()
+            last_update = start_time
+
+            with open(file_path, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    if chunk:
+                        f.write(chunk)
+                        downloaded += len(chunk)
+
+                        current_time = time.time()
+                        if current_time - last_update >= 0.5:
+                            self._print_progress(downloaded, total_size, start_time)
+                            last_update = current_time
+
+            self._print_progress(downloaded, total_size, start_time, final=True)
+            print()
+
+            # Verify
+            if file_path.exists() and file_path.stat().st_size > 0:
+                size_mb = file_path.stat().st_size / (1024 * 1024)
+                elapsed = time.time() - start_time
+                speed = size_mb / elapsed if elapsed > 0 else 0
+                print(f"   ✅ Complete: {size_mb:.2f} MB @ {speed:.2f} MB/s")
+
+                # Write metadata
+                self._write_metadata(version_dir, action, file_path)
+                return True
+            else:
+                print(f"   ❌ Download failed")
+                return False
+
+        except Exception as e:
+            print(f"   ❌ Error: {e}")
+            return False
+
+    def _print_progress(
+        self, downloaded: int, total: int, start_time: float, final: bool = False
+    ):
+        """Print progress bar."""
+        if total > 0:
+            percent = min(100, int((downloaded / total) * 100))
+            filled = int(40 * percent / 100)
+            bar = "█" * filled + "░" * (40 - filled)
+
+            elapsed = time.time() - start_time
+            if elapsed > 0:
+                speed = (downloaded / (1024 * 1024)) / elapsed
+                print(f"\r   [{bar}] {percent}% | {speed:.2f} MB/s", end="", flush=True)
+        else:
+            mb = downloaded / (1024 * 1024)
+            print(f"\r   Downloaded: {mb:.2f} MB", end="", flush=True)
+
+    def _write_metadata(
+        self, version_dir: Path, action: DownloadAction, file_path: Path
+    ):
+        """Write metadata file."""
+        metadata = {
+            "claim_id": action.claim_id,
+            "claim_name": action.claim_name,
+            "version_token": action.version_token,
+            "uri": action.uri,
+            "downloaded_at": time.strftime("%Y-%m-%dT%H:%M:%S"),
+            "file_name": file_path.name,
+            "file_size": file_path.stat().st_size,
+            "download_source": "odysee_direct",
+        }
+
+        meta_path = version_dir / "metadata.json"
+        with open(meta_path, "w") as f:
+            json.dump(metadata, f, indent=2)
+
+        logger.info(f"Wrote metadata: {meta_path}")

tests/test_lbry_client.py

@@ -0,0 +1,34 @@
+"""Tests for LBRY client helper behavior."""
+
+from lbry_client import LbryClient
+
+
+def test_create_odysee_proxy_client_defaults():
+    client = LbryClient.create_odysee_proxy(timeout=42)
+
+    assert client.api_url == LbryClient.ODYSEE_PROXY_URL
+    assert client.timeout == 42
+    assert client.backend_name == "Odysee public proxy"
+    assert client.supports_file_ops is False
+
+
+def test_find_controlling_channel_uses_claim_search(monkeypatch):
+    client = LbryClient.create_odysee_proxy()
+    captured = {}
+
+    def fake_claim_search(**kwargs):
+        captured.update(kwargs)
+        return {"items": [{"claim_id": "control123", "name": "@example"}]}
+
+    monkeypatch.setattr(client, "claim_search", fake_claim_search)
+
+    result = client.find_controlling_channel("@example")
+
+    assert result == {"claim_id": "control123", "name": "@example"}
+    assert captured["name"] == "@example"
+    assert captured["claim_type"] == ["channel"]
+    assert captured["is_controlling"] is True
+    assert captured["order_by"] == ["effective_amount"]
+    assert captured["page"] == 1
+    assert captured["page_size"] == 1
+

tests/test_main.py

@@ -0,0 +1,69 @@
+"""Tests for main module channel resolution behavior."""
+
+from main import resolve_channel
+
+
+class FakeProxyClient:
+    """Minimal client stub for proxy-backed channel resolution tests."""
+
+    supports_file_ops = False
+
+    def resolve(self, urls):
+        uri = urls[0]
+        return {
+            uri: {
+                "claim_id": "vanity123",
+                "name": "@veritasium",
+                "value_type": "channel",
+                "value": {"title": "Veritasium"},
+                "permanent_url": "lbry://@veritasium#1",
+                "short_url": "lbry://@veritasium#1",
+            }
+        }
+
+    def find_controlling_channel(self, channel_name):
+        assert channel_name == "@veritasium"
+        return {
+            "claim_id": "control999",
+            "name": "@veritasium",
+            "value_type": "channel",
+            "value": {"title": "Veritasium"},
+            "permanent_url": "lbry://@veritasium#f",
+            "short_url": "lbry://@veritasium#f",
+        }
+
+
+class FakeDaemonClient:
+    """Minimal client stub for daemon-backed resolution tests."""
+
+    supports_file_ops = True
+
+    def resolve(self, urls):
+        uri = urls[0]
+        return {
+            uri: {
+                "claim_id": "daemon123",
+                "name": "@example",
+                "value_type": "channel",
+                "value": {"title": "Example"},
+                "permanent_url": "lbry://@example#1",
+                "short_url": "lbry://@example#1",
+            }
+        }
+
+
+def test_resolve_channel_uses_controlling_claim_for_proxy_client():
+    channel = resolve_channel(FakeProxyClient(), "https://odysee.com/@veritasium:1")
+
+    assert channel is not None
+    assert channel.channel_claim_id == "control999"
+    assert channel.channel_name == "@veritasium"
+
+
+def test_resolve_channel_keeps_daemon_claim_id():
+    channel = resolve_channel(FakeDaemonClient(), "https://odysee.com/@example:1")
+
+    assert channel is not None
+    assert channel.channel_claim_id == "daemon123"
+    assert channel.channel_name == "@example"
+