169 lines
6 KiB
Python
169 lines
6 KiB
Python
|
|
import logging
|
||
|
|
|
||
|
|
import httpx
|
||
|
|
from google.oauth2.credentials import Credentials
|
||
|
|
|
||
|
|
from app.config import settings
|
||
|
|
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
|
||
|
|
API_BASE = "https://www.googleapis.com/youtube/v3"
|
||
|
|
BATCH_SIZE = 50
|
||
|
|
|
||
|
|
|
||
|
|
class YouTubeQuotaExceeded(Exception):
|
||
|
|
pass
|
||
|
|
|
||
|
|
|
||
|
|
class YouTubeAPIError(Exception):
|
||
|
|
pass
|
||
|
|
|
||
|
|
|
||
|
|
def _headers(credentials: Credentials) -> dict:
|
||
|
|
return {"Authorization": f"Bearer {credentials.token}"}
|
||
|
|
|
||
|
|
|
||
|
|
def _raise_for_status(response: httpx.Response) -> None:
|
||
|
|
if response.status_code == 200:
|
||
|
|
return
|
||
|
|
try:
|
||
|
|
payload = response.json()
|
||
|
|
reason = payload.get("error", {}).get("errors", [{}])[0].get("reason", "")
|
||
|
|
message = payload.get("error", {}).get("message", response.text)
|
||
|
|
except Exception:
|
||
|
|
reason = ""
|
||
|
|
message = response.text
|
||
|
|
|
||
|
|
if response.status_code == 403 and reason in ("quotaExceeded", "dailyLimitExceeded", "rateLimitExceeded"):
|
||
|
|
raise YouTubeQuotaExceeded(message)
|
||
|
|
|
||
|
|
logger.error("YouTube API error %s: %s", response.status_code, message)
|
||
|
|
raise YouTubeAPIError(f"{response.status_code}: {message}")
|
||
|
|
|
||
|
|
|
||
|
|
def fetch_subscriptions(credentials: Credentials) -> list[dict]:
|
||
|
|
subscriptions: list[dict] = []
|
||
|
|
page_token: str | None = None
|
||
|
|
|
||
|
|
with httpx.Client(timeout=settings.metube_request_timeout_seconds) as client:
|
||
|
|
while True:
|
||
|
|
params = {
|
||
|
|
"part": "snippet,contentDetails",
|
||
|
|
"mine": "true",
|
||
|
|
"maxResults": 50,
|
||
|
|
}
|
||
|
|
if page_token:
|
||
|
|
params["pageToken"] = page_token
|
||
|
|
|
||
|
|
response = client.get(f"{API_BASE}/subscriptions", params=params, headers=_headers(credentials))
|
||
|
|
_raise_for_status(response)
|
||
|
|
data = response.json()
|
||
|
|
|
||
|
|
for item in data.get("items", []):
|
||
|
|
snippet = item.get("snippet", {})
|
||
|
|
resource_id = snippet.get("resourceId", {})
|
||
|
|
channel_id = resource_id.get("channelId")
|
||
|
|
if not channel_id:
|
||
|
|
continue
|
||
|
|
thumbnails = snippet.get("thumbnails", {})
|
||
|
|
thumbnail = (
|
||
|
|
thumbnails.get("high") or thumbnails.get("medium") or thumbnails.get("default") or {}
|
||
|
|
).get("url")
|
||
|
|
subscriptions.append(
|
||
|
|
{
|
||
|
|
"youtube_channel_id": channel_id,
|
||
|
|
"title": snippet.get("title", ""),
|
||
|
|
"description": snippet.get("description", ""),
|
||
|
|
"thumbnail_url": thumbnail,
|
||
|
|
}
|
||
|
|
)
|
||
|
|
|
||
|
|
page_token = data.get("nextPageToken")
|
||
|
|
if not page_token:
|
||
|
|
break
|
||
|
|
|
||
|
|
return subscriptions
|
||
|
|
|
||
|
|
|
||
|
|
def fetch_playlist_video_ids(credentials: Credentials, playlist_id: str, max_results: int) -> list[str]:
|
||
|
|
with httpx.Client(timeout=settings.metube_request_timeout_seconds) as client:
|
||
|
|
params = {
|
||
|
|
"part": "contentDetails",
|
||
|
|
"playlistId": playlist_id,
|
||
|
|
"maxResults": min(max_results, 50),
|
||
|
|
}
|
||
|
|
response = client.get(f"{API_BASE}/playlistItems", params=params, headers=_headers(credentials))
|
||
|
|
if response.status_code == 404:
|
||
|
|
return []
|
||
|
|
_raise_for_status(response)
|
||
|
|
data = response.json()
|
||
|
|
|
||
|
|
video_ids = []
|
||
|
|
for item in data.get("items", []):
|
||
|
|
video_id = item.get("contentDetails", {}).get("videoId")
|
||
|
|
if video_id:
|
||
|
|
video_ids.append(video_id)
|
||
|
|
return video_ids
|
||
|
|
|
||
|
|
|
||
|
|
def fetch_videos_details(credentials: Credentials, video_ids: list[str]) -> list[dict]:
|
||
|
|
results: list[dict] = []
|
||
|
|
|
||
|
|
with httpx.Client(timeout=settings.metube_request_timeout_seconds) as client:
|
||
|
|
for i in range(0, len(video_ids), BATCH_SIZE):
|
||
|
|
batch = video_ids[i : i + BATCH_SIZE]
|
||
|
|
params = {
|
||
|
|
"part": "snippet,contentDetails,status",
|
||
|
|
"id": ",".join(batch),
|
||
|
|
"maxResults": BATCH_SIZE,
|
||
|
|
}
|
||
|
|
response = client.get(f"{API_BASE}/videos", params=params, headers=_headers(credentials))
|
||
|
|
_raise_for_status(response)
|
||
|
|
data = response.json()
|
||
|
|
|
||
|
|
for item in data.get("items", []):
|
||
|
|
snippet = item.get("snippet", {})
|
||
|
|
thumbnails = snippet.get("thumbnails", {})
|
||
|
|
thumbnail = (
|
||
|
|
thumbnails.get("high") or thumbnails.get("medium") or thumbnails.get("default") or {}
|
||
|
|
).get("url")
|
||
|
|
results.append(
|
||
|
|
{
|
||
|
|
"youtube_video_id": item.get("id"),
|
||
|
|
"youtube_channel_id": snippet.get("channelId"),
|
||
|
|
"title": snippet.get("title", ""),
|
||
|
|
"description": snippet.get("description", ""),
|
||
|
|
"thumbnail_url": thumbnail,
|
||
|
|
"published_at": snippet.get("publishedAt"),
|
||
|
|
"duration_iso8601": item.get("contentDetails", {}).get("duration"),
|
||
|
|
}
|
||
|
|
)
|
||
|
|
|
||
|
|
return results
|
||
|
|
|
||
|
|
|
||
|
|
def fetch_uploads_playlists(credentials: Credentials, channel_ids: list[str]) -> dict[str, str]:
|
||
|
|
result: dict[str, str] = {}
|
||
|
|
|
||
|
|
with httpx.Client(timeout=settings.metube_request_timeout_seconds) as client:
|
||
|
|
for i in range(0, len(channel_ids), BATCH_SIZE):
|
||
|
|
batch = channel_ids[i : i + BATCH_SIZE]
|
||
|
|
params = {
|
||
|
|
"part": "snippet,contentDetails",
|
||
|
|
"id": ",".join(batch),
|
||
|
|
"maxResults": BATCH_SIZE,
|
||
|
|
}
|
||
|
|
response = client.get(f"{API_BASE}/channels", params=params, headers=_headers(credentials))
|
||
|
|
_raise_for_status(response)
|
||
|
|
data = response.json()
|
||
|
|
|
||
|
|
for item in data.get("items", []):
|
||
|
|
channel_id = item.get("id")
|
||
|
|
uploads = (
|
||
|
|
item.get("contentDetails", {}).get("relatedPlaylists", {}).get("uploads")
|
||
|
|
)
|
||
|
|
if channel_id and uploads:
|
||
|
|
result[channel_id] = uploads
|
||
|
|
|
||
|
|
return result
|