feat: add project acceptance collection service

crawler_client.py

@@ -78,6 +78,29 @@ def _post(
     return data
 
 
+def _get(path: str) -> dict[str, Any]:
+    url = f"{Config.CRAWLER_BASE_URL}{path}"
+    try:
+        response = CRAWLER_SESSION.get(url, timeout=Config.CRAWLER_TIMEOUT_SECONDS)
+        response.raise_for_status()
+        payload = response.json()
+    except requests.RequestException as exc:
+        raise CrawlerError(f"爬虫服务请求失败：{exc}") from exc
+    except ValueError as exc:
+        raise CrawlerError("爬虫服务返回的不是有效 JSON") from exc
+    if payload.get("code") != 200 or not payload.get("success", False):
+        raise CrawlerError(payload.get("msg") or "爬虫服务返回失败")
+    data = payload.get("data")
+    if not isinstance(data, dict):
+        raise CrawlerError("爬虫服务响应缺少 data")
+    return data
+
+
+def get_wen_resources() -> dict[str, Any]:
+    """查询当前可用 Cookie 和可立即下发截图的设备。"""
+    return _get("/api/v1/xhs/wen/resources")
+
+
 def start_collection(mode: str, keywords: list[str]) -> dict[str, Any]:
     """深度任务走 sources，轻度/常规任务走 overview。"""
 
@@ -113,3 +136,38 @@ def resume_collection(crawler_task_id: str) -> dict[str, Any]:
     """沿用原爬虫任务 ID，从 framework 保存的检查点继续采集。"""
 
     return _post(f"/api/v1/xhs/wen/tasks/{crawler_task_id}/resume", {})
+
+
+def fetch_content_detail(note_url: str) -> dict[str, Any]:
+    """按小红书笔记链接读取完整笔记详情。"""
+
+    return _post(
+        "/api/v1/fetch_content_detail",
+        {"plant": "xhs", "link": note_url},
+        retry_transient=True,
+    )
+
+
+def schedule_xapi_screenshots(search_queries: list[str], device_count: int) -> dict[str, Any]:
+    """向手机集群下发问一问关键词搜索与截图任务。"""
+
+    queries = normalize_collection_keywords(search_queries)
+    return _post(
+        "/api/v1/xhs/wen/xapi/schedule",
+        {"keywords": queries, "device_count": device_count},
+        retry_transient=False,
+    )
+
+
+def collect_keyword_sources(keyword: str, credential_id: str | None = None) -> dict[str, Any]:
+    """使用 sources 的完整 Cookie 池采集单个关键词。"""
+
+    normalized = normalize_collection_keywords([keyword])[0]
+    body: dict[str, Any] = {"keyword": normalized}
+    if credential_id:
+        body["credential_id"] = credential_id
+    return _post(
+        "/api/v1/xhs/wen/sources",
+        body,
+        retry_transient=False,
+    )