Implement full media crawler workflow with Flask backend and Vue frontend.

Add TMDB search and media detail pages, HDHive resource ingestion flow, unified error handling, Docker single-container runtime, and project docs/config updates for local deployment.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/adapters/cms_adapter.py

@@ -0,0 +1,146 @@
+import time
+
+from config import Config
+from http_client import request_json
+from error_handling import AppServiceError
+
+_CMS_TOKEN_CACHE = {"token": "", "expires_at": 0}
+
+
+def _resolve_login_url():
+    if Config.CMS_LOGIN_URL:
+        return Config.CMS_LOGIN_URL
+    if Config.CMS_BASE_URL:
+        return f"{Config.CMS_BASE_URL.rstrip('/')}/api/auth/login"
+    raise AppServiceError(
+        "CMS login url is not configured",
+        category="validation",
+        code="CMS_CONFIG_MISSING",
+        provider="cms",
+    )
+
+
+def _resolve_add_share_url():
+    if Config.CMS_ADD_SHARE_URL:
+        return Config.CMS_ADD_SHARE_URL
+    if Config.CMS_BASE_URL:
+        return f"{Config.CMS_BASE_URL.rstrip('/')}/api/cloud/add_share_down"
+    raise AppServiceError(
+        "CMS add share url is not configured",
+        category="validation",
+        code="CMS_CONFIG_MISSING",
+        provider="cms",
+    )
+
+
+def _headers(token):
+    headers = {"Content-Type": "application/json"}
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+    return headers
+
+
+def _extract_cms_token(login_result):
+    data = login_result.get("data") or {}
+    token = (data.get("data") or {}).get("token")
+    if not token:
+        raise AppServiceError(
+            "CMS login succeeded but token missing",
+            category="upstream",
+            code="CMS_TOKEN_MISSING",
+            provider="cms",
+            detail={"response": data},
+        )
+    return token
+
+
+def _login_and_get_token():
+    if Config.CMS_TOKEN:
+        return Config.CMS_TOKEN
+    if not Config.CMS_USERNAME or not Config.CMS_PASSWORD:
+        raise AppServiceError(
+            "CMS username/password is required when CMS_TOKEN is not provided",
+            category="validation",
+            code="CMS_CONFIG_MISSING",
+            provider="cms",
+        )
+    login_result = request_json(
+        _resolve_login_url(),
+        method="POST",
+        payload={"username": Config.CMS_USERNAME, "password": Config.CMS_PASSWORD},
+        headers={"Content-Type": "application/json"},
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="cms",
+    )
+    token = _extract_cms_token(login_result)
+    _CMS_TOKEN_CACHE["token"] = token
+    _CMS_TOKEN_CACHE["expires_at"] = int(time.time()) + 3500
+    return token
+
+
+def _get_cached_token():
+    if Config.CMS_TOKEN:
+        return Config.CMS_TOKEN
+    if _CMS_TOKEN_CACHE["token"] and _CMS_TOKEN_CACHE["expires_at"] > int(time.time()):
+        return _CMS_TOKEN_CACHE["token"]
+    return _login_and_get_token()
+
+
+def _should_refresh_token(response_data):
+    code = (response_data or {}).get("code")
+    msg = (response_data or {}).get("msg") or (response_data or {}).get("message") or ""
+    return code != 200 and msg != "提取分享链接失败"
+
+
+def _add_share(url_value, token):
+    return request_json(
+        _resolve_add_share_url(),
+        method="POST",
+        payload={"url": url_value},
+        headers=_headers(token),
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="cms",
+    )
+
+
+def create_resource(payload):
+    resource = payload.get("resource") or {}
+    share_url = resource.get("unlockUrl") or payload.get("url")
+    if not share_url:
+        raise AppServiceError(
+            "CMS ingest requires unlockUrl",
+            category="validation",
+            code="CMS_INPUT_INVALID",
+            provider="cms",
+        )
+
+    token = _get_cached_token()
+    first_result = _add_share(share_url, token)
+    first_data = first_result.get("data") or {}
+    if _should_refresh_token(first_data):
+        refreshed_token = _login_and_get_token()
+        second_result = _add_share(share_url, refreshed_token)
+        second_data = second_result.get("data") or {}
+        if (second_data.get("code") or 0) != 200:
+            raise AppServiceError(
+                second_data.get("msg") or second_data.get("message") or "CMS ingest failed",
+                category="upstream",
+                code=str(second_data.get("code") or "CMS_INGEST_FAILED"),
+                provider="cms",
+                detail={"response": second_data},
+            )
+        return second_result
+
+    if (first_data.get("code") or 0) != 200:
+        raise AppServiceError(
+            first_data.get("msg") or first_data.get("message") or "CMS ingest failed",
+            category="business_rule"
+            if (first_data.get("msg") == "提取分享链接失败")
+            else "upstream",
+            code=str(first_data.get("code") or "CMS_INGEST_FAILED"),
+            provider="cms",
+            detail={"response": first_data},
+        )
+    return first_result

backend/adapters/emby_adapter.py

@@ -0,0 +1,23 @@
+from config import Config
+from http_client import request_json
+
+
+def _headers():
+    headers = {"Content-Type": "application/json"}
+    if Config.EMBY_TOKEN:
+        headers["X-Emby-Token"] = Config.EMBY_TOKEN
+    return headers
+
+
+def exists_by_tmdb_id(tmdb_id):
+    url = f"{Config.EMBY_BASE_URL}/Items?AnyProviderIdEquals=Tmdb.{tmdb_id}&Recursive=true&Limit=1"
+    result = request_json(
+        url,
+        headers=_headers(),
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="emby",
+    )
+    total = ((result.get("data") or {}).get("TotalRecordCount")) or 0
+    result["exists"] = total > 0
+    return result

backend/adapters/hdhive_adapter.py

@@ -0,0 +1,60 @@
+from config import Config
+from http_client import request_json
+
+
+def _headers():
+    headers = {
+        "Accept": "application/json",
+        "X-API-Key": Config.HDHIVE_API_KEY,
+    }
+    if Config.HDHIVE_ACCESS_TOKEN:
+        headers["Authorization"] = f"Bearer {Config.HDHIVE_ACCESS_TOKEN}"
+    return headers
+
+
+def search_resource(media_type, tmdb_id):
+    url = f"{Config.HDHIVE_BASE_URL}/api/open/resources/{media_type}/{tmdb_id}"
+    return request_json(
+        url,
+        headers=_headers(),
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="hdhive",
+    )
+
+
+def unlock_link(slug):
+    url = f"{Config.HDHIVE_BASE_URL}/api/open/resources/unlock"
+    return request_json(
+        url,
+        method="POST",
+        payload={"slug": slug},
+        headers={**_headers(), "Content-Type": "application/json"},
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="hdhive",
+    )
+
+
+def normalize_resource(search_data, unlock_data):
+    resolution = (search_data or {}).get("video_resolution")
+    source = (search_data or {}).get("source")
+    subtitle_language = (search_data or {}).get("subtitle_language")
+    return {
+        "resourceTitle": (search_data or {}).get("title", ""),
+        "quality": ", ".join(resolution) if isinstance(resolution, list) else "",
+        "size": (search_data or {}).get("share_size", ""),
+        "diskType": (search_data or {}).get("pan_type", ""),
+        "source": ", ".join(source) if isinstance(source, list) else "",
+        "subtitleLanguage": ", ".join(subtitle_language)
+        if isinstance(subtitle_language, list)
+        else "",
+        "slug": (search_data or {}).get("slug", ""),
+        "unlockUrl": (unlock_data or {}).get("full_url")
+        or (unlock_data or {}).get("url")
+        or "",
+        "availability": "available"
+        if ((unlock_data or {}).get("full_url") or (unlock_data or {}).get("url"))
+        else "unknown",
+        "raw": {"searchData": search_data, "unlockData": unlock_data},
+    }

backend/adapters/tmdb_adapter.py

@@ -0,0 +1,56 @@
+from config import Config
+from http_client import request_json
+from urllib.parse import quote
+
+
+def _headers():
+    headers = {"Content-Type": "application/json"}
+    if Config.TMDB_TOKEN:
+        headers["Authorization"] = f"Bearer {Config.TMDB_TOKEN}"
+    return headers
+
+
+def search_media(query, media_type="movie", page=1):
+    normalized_type = "tv" if media_type == "tv" else "movie"
+    url = (
+        f"{Config.TMDB_BASE_URL}/search/{normalized_type}"
+        f"?language=zh-CN&query={quote(str(query))}&page={page}"
+    )
+    result = request_json(
+        url,
+        headers=_headers(),
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="tmdb",
+    )
+    data = result.get("data") or {}
+    result["items"] = data.get("results") if isinstance(data, dict) else []
+    return result
+
+
+def get_media_detail(tmdb_id, media_type):
+    normalized_type = "tv" if media_type == "tv" else "movie"
+    url = f"{Config.TMDB_BASE_URL}/{normalized_type}/{tmdb_id}?language=zh-CN"
+    result = request_json(
+        url,
+        headers=_headers(),
+        max_retry=Config.MAX_RETRY,
+        retry_delay_ms=Config.RETRY_DELAY_MS,
+        provider="tmdb",
+    )
+    data = result.get("data") or {}
+    normalized = {
+        "tmdbId": tmdb_id,
+        "type": normalized_type,
+        "title": data.get("title") or data.get("name") or "",
+        "originalTitle": data.get("original_title") or data.get("original_name") or "",
+        "overview": data.get("overview") or "",
+        "year": (data.get("release_date") or data.get("first_air_date") or "")[:4],
+        "rating": data.get("vote_average"),
+        "posterPath": data.get("poster_path") or "",
+        "genres": [g.get("name") for g in data.get("genres", []) if g.get("name")],
+        "seasons": len(data.get("seasons", [])) if isinstance(data.get("seasons"), list) else 0,
+        "raw": data,
+    }
+    result["normalized"] = normalized
+    return result