初始化

crawler/storage.py

@@ -0,0 +1,95 @@
+"""存储管理：index.jsonl 读写、输出目录管理"""
+
+import json
+import logging
+from pathlib import Path
+
+from crawler.models import ArticleItem, CrawlResult
+from crawler.utils import get_news_day
+
+logger = logging.getLogger(__name__)
+
+
+def write_index_jsonl(result: CrawlResult) -> Path:
+    """将单源抓取结果写入 index.jsonl
+
+    Args:
+        result: 单源抓取结果
+
+    Returns:
+        index 文件路径
+    """
+    today = get_news_day()
+    out_dir = Path(f"data/raw/{result.source_id}/{today}")
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    index_path = out_dir / "index.jsonl"
+
+    # 追加写入（同一天多次抓取合并）
+    existing: set[str] = set()
+    if index_path.exists():
+        with open(index_path, encoding="utf-8") as f:
+            for line in f:
+                line = line.strip()
+                if not line:
+                    continue
+                try:
+                    item = json.loads(line)
+                    existing.add(item.get("url_hash", ""))
+                except json.JSONDecodeError:
+                    continue
+
+    written = 0
+    with open(index_path, "a", encoding="utf-8") as f:
+        for article in result.articles:
+            if article.status != "success":
+                continue
+            if article.url_hash in existing:
+                continue  # 跳过已存在的
+
+            record = article.model_dump()
+            f.write(json.dumps(record, ensure_ascii=False) + "\n")
+            existing.add(article.url_hash)
+            written += 1
+
+    logger.info("[%s] index.jsonl 写入 %d 条（跳过重复 %d 条）",
+                result.source_id, written,
+                len(result.articles) - written)
+    return index_path
+
+
+def load_index(
+    source_id: str,
+    date_str: str | None = None,
+) -> list[ArticleItem]:
+    """读取指定源/日期的 index.jsonl
+
+    Args:
+        source_id: 新闻源 ID
+        date_str: 日期字符串 YYYYMMDD，默认当前新闻日
+
+    Returns:
+        ArticleItem 列表
+    """
+    if date_str is None:
+        date_str = get_news_day()
+
+    index_path = Path(f"data/raw/{source_id}/{date_str}/index.jsonl")
+
+    if not index_path.exists():
+        logger.warning("index 文件不存在: %s", index_path)
+        return []
+
+    articles: list[ArticleItem] = []
+    with open(index_path, encoding="utf-8") as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                data = json.loads(line)
+                articles.append(ArticleItem(**data))
+            except (json.JSONDecodeError, Exception) as e:
+                logger.warning("解析 index 行失败: %s", e)
+
+    return articles