feat: 批量下载脚本、依赖文件、说明书

2026-03-19 13:47:53 +08:00
parent 1edabd6d3b
commit 25059a50a2
8 changed files with 368 additions and 3 deletions
--- a/.claude/settings.local.json
+++ b/.claude/settings.local.json
@@ -3,7 +3,10 @@
    "allow": [
      "Bash(git init:*)",
      "Bash(git add:*)",
-      "Bash(python -c \"import ast, sys; ast.parse\\(open\\('sap-c4c-AttachmentFolder.py'\\).read\\(\\)\\); print\\('语法检查通过'\\)\")"
+      "Bash(python -c \"import ast, sys; ast.parse\\(open\\('sap-c4c-AttachmentFolder.py'\\).read\\(\\)\\); print\\('语法检查通过'\\)\")",
+      "Bash(git commit:*)",
+      "Bash(head:*)",
+      "Bash(python3:*)"
    ]
  }
 }
--- a/README.md
+++ b/README.md
@@ -0,0 +1,130 @@
+# SAP C4C 附件批量下载工具
+
+从 SAP C4C 下载 Ticket 附件并上传到群晖 DSM。
+
+---
+
+## 环境要求
+
+- Python >= 3.8
+- Ubuntu 20.04+ 或 macOS
+
+---
+
+## 安装
+
+```bash
+pip install -r requirements.txt
+python -m playwright install chromium
+# Ubuntu 需额外执行（需要 sudo）
+python -m playwright install-deps chromium
+```
+
+---
+
+## 文件说明
+
+| 文件 | 说明 |
+|---|---|
+| `sap-c4c-AttachmentFolder.py` | 核心下载脚本，支持单个 Ticket 下载 |
+| `batch_download.py` | 批量下载脚本，从 CSV 读取 ID 并行执行 |
+| `get_ticket_ids.py` | 从 CSV 提取 Ticket ID 工具 |
+| `datasource/` | 存放 SAP Analytics 导出的 CSV 文件 |
+| `downloads/` | 本地临时下载目录（上传 DSM 后自动清理） |
+| `error_log.txt` | 错误日志，每次批量运行时重置 |
+
+---
+
+## 单个 Ticket 下载
+
+```bash
+python sap-c4c-AttachmentFolder.py \
+  --tenant https://my300375.c4c.saphybriscloud.cn \
+  --user admin \
+  --password 'your_password' \
+  --ticket 20950 \
+  --output-dir ./downloads
+```
+
+### 同时上传到群晖 DSM
+
+```bash
+python sap-c4c-AttachmentFolder.py \
+  --tenant https://my300375.c4c.saphybriscloud.cn \
+  --user admin \
+  --password 'your_password' \
+  --ticket 20950 \
+  --output-dir ./downloads \
+  --dsm-url http://10.0.10.235:5000 \
+  --dsm-user PLM \
+  --dsm-password 'dsm_password' \
+  --dsm-path /Newgonow/AU-SPFJ
+```
+
+### 仅列出附件不下载
+
+```bash
+python sap-c4c-AttachmentFolder.py ... --list-only
+```
+
+### JSON 输出模式
+
+```bash
+python sap-c4c-AttachmentFolder.py ... --json
+```
+
+---
+
+## 批量下载
+
+将 SAP Analytics 导出的 CSV 文件放入 `datasource/` 目录，然后运行：
+
+```bash
+python batch_download.py
+```
+
+- 默认读取 CSV 第二列的 Ticket ID，取前 10 个
+- 最多 5 个任务并行执行
+- 每个 Ticket 使用独立子目录 `downloads/{ticket_id}`，避免并行冲突
+- 上传 DSM 完成后自动清理本地文件和子目录
+- 错误记录到 `error_log.txt`
+
+### 修改并行数或 Ticket 数量
+
+编辑 `batch_download.py` 顶部配置：
+
+```python
+WORKERS = 5   # 并行数
+# get_ticket_ids(10) 中的 10 为读取数量
+```
+
+---
+
+## DSM 目录结构
+
+上传后文件按以下结构组织：
+
+```
+{dsm_path}/
+└── {ticket_id}_{serial_id}/
+    └── {issue_id}_{issue_description}/
+        └── 附件文件
+```
+
+> `Quote & Chassis` 类型的附件会同时复制到所有其他 issue 目录下。
+
+---
+
+## 环境变量（可选）
+
+也可通过环境变量代替命令行参数：
+
+| 环境变量 | 对应参数 |
+|---|---|
+| `C4C_TENANT` | `--tenant` |
+| `C4C_USERNAME` | `--user` |
+| `C4C_PASSWORD` | `--password` |
+| `DSM_URL` | `--dsm-url` |
+| `DSM_USERNAME` | `--dsm-user` |
+| `DSM_PASSWORD` | `--dsm-password` |
+| `DSM_PATH` | `--dsm-path` |
--- a/batch_download.py
+++ b/batch_download.py
@@ -0,0 +1,145 @@
+#!/usr/bin/env python3
+"""批量下载 SAP C4C 附件，从 CSV 读取 Ticket ID，并行执行并记录错误日志"""
+import subprocess
+import sys
+import os
+import json
+import datetime
+import csv
+import glob
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import threading
+
+# ── 配置 ──────────────────────────────────────────────────────────────────────
+TENANT   = "https://my300375.c4c.saphybriscloud.cn"
+USER     = "admin"
+PASSWORD = "Xjait.1?"
+OUTPUT   = "./downloads"
+DSM_URL  = "http://10.0.10.235:5000"
+DSM_USER = "PLM"
+DSM_PASS = "123456"
+DSM_PATH = "/Newgonow/AU-SPFJ"
+
+WORKERS     = 5
+
+SCRIPT      = os.path.join(os.path.dirname(__file__), "sap-c4c-AttachmentFolder.py")
+ERROR_LOG   = os.path.join(os.path.dirname(__file__), "error_log.txt")
+DATASOURCE  = os.path.join(os.path.dirname(__file__), "datasource")
+
+print_lock = threading.Lock()
+# ─────────────────────────────────────────────────────────────────────────────
+
+
+def get_ticket_ids(limit=10):
+    ids, seen = [], set()
+    for csv_file in glob.glob(os.path.join(DATASOURCE, "*.csv")):
+        with open(csv_file, encoding="utf-8-sig") as f:
+            reader = csv.reader(f)
+            next(reader, None)
+            for row in reader:
+                if len(row) < 2:
+                    continue
+                val = row[1].strip()
+                if val and val not in seen:
+                    seen.add(val)
+                    ids.append(val)
+                if len(ids) >= limit:
+                    break
+        if len(ids) >= limit:
+            break
+    return ids
+
+
+def log_error(ticket_id, message):
+    ts = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    with open(ERROR_LOG, "a", encoding="utf-8") as f:
+        f.write(f"[{ts}] Ticket {ticket_id}: {message}\n")
+
+
+def run_ticket(ticket_id, index, total):
+    with print_lock:
+        print(f"\n[{index}/{total}] 开始下载 Ticket {ticket_id} ...")
+    cmd = [
+        sys.executable, SCRIPT,
+        "--tenant",       TENANT,
+        "--user",         USER,
+        "--password",     PASSWORD,
+        "--ticket",       str(ticket_id),
+        "--output-dir",   os.path.join(OUTPUT, str(ticket_id)),
+        "--json",
+        "--dsm-url",      DSM_URL,
+        "--dsm-user",     DSM_USER,
+        "--dsm-password", DSM_PASS,
+        "--dsm-path",     DSM_PATH,
+    ]
+    try:
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=300)
+        # 解析 JSON 输出
+        try:
+            data = json.loads(result.stdout)
+            success = data.get("success", False)
+            downloaded = len(data.get("downloadedFiles", []))
+            dsm_uploads = data.get("dsmUpload", [])
+            ok_uploads  = sum(1 for u in dsm_uploads if u.get("success"))
+            fail_uploads = len(dsm_uploads) - ok_uploads
+
+            if success:
+                with print_lock:
+                    print(f"  ✓ [{ticket_id}] 下载 {downloaded} 个文件, DSM 上传 {ok_uploads} 成功 {fail_uploads} 失败")
+                if fail_uploads:
+                    fails = [u for u in dsm_uploads if not u.get("success")]
+                    for u in fails:
+                        log_error(ticket_id, f"DSM 上传失败: {u.get('file')} - {u.get('error')}")
+            else:
+                err = data.get("error", result.stderr or "未知错误")
+                with print_lock:
+                    print(f"  ✗ [{ticket_id}] 失败: {err}")
+                log_error(ticket_id, err)
+        except json.JSONDecodeError:
+            if result.returncode == 0:
+                with print_lock:
+                    print(f"  ✓ [{ticket_id}] 完成")
+            else:
+                err = result.stderr.strip() or result.stdout.strip() or "未知错误"
+                with print_lock:
+                    print(f"  ✗ [{ticket_id}] 失败: {err}")
+                log_error(ticket_id, err)
+
+    except subprocess.TimeoutExpired:
+        msg = "超时 (300s)"
+        with print_lock:
+            print(f"  ✗ [{ticket_id}] {msg}")
+        log_error(ticket_id, msg)
+    except Exception as e:
+        with print_lock:
+            print(f"  ✗ [{ticket_id}] 异常: {e}")
+        log_error(ticket_id, str(e))
+
+
+def main():
+    print("读取 Ticket ID ...")
+    ids = get_ticket_ids(10)
+    if not ids:
+        print("未找到任何 Ticket ID，请检查 datasource 目录")
+        sys.exit(1)
+
+    print(f"共 {len(ids)} 个 Ticket: {', '.join(ids)}")
+
+    # 清空/创建 error_log
+    open(ERROR_LOG, "w").close()
+
+    with ThreadPoolExecutor(max_workers=WORKERS) as executor:
+        futures = {executor.submit(run_ticket, tid, i, len(ids)): tid
+                   for i, tid in enumerate(ids, 1)}
+        for future in as_completed(futures):
+            future.result()  # 触发异常传播（已在 run_ticket 内处理）
+
+    print("\n全部完成。")
+    if os.path.getsize(ERROR_LOG) > 0:
+        print(f"有错误，详见 {ERROR_LOG}")
+    else:
+        print("无错误。")
+
+
+if __name__ == "__main__":
+    main()
--- a/datasource/SAPAnalyticsReport(Z96B303CD8F03C0B6AC322A).csv
+++ b/datasource/SAPAnalyticsReport(Z96B303CD8F03C0B6AC322A).csv
--- a/error_log.txt
+++ b/error_log.txt
--- a/get_ticket_ids.py
+++ b/get_ticket_ids.py
@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+"""从 datasource 目录下的 CSV 文件读取第二列，提取10个有效的 Ticket ID"""
+import csv
+import glob
+import os
+
+datasource_dir = os.path.join(os.path.dirname(__file__), "datasource")
+csv_files = glob.glob(os.path.join(datasource_dir, "*.csv"))
+
+ids = []
+seen = set()
+
+for csv_file in csv_files:
+    with open(csv_file, encoding="utf-8-sig") as f:
+        reader = csv.reader(f)
+        next(reader, None)  # 跳过表头
+        for row in reader:
+            if len(row) < 2:
+                continue
+            val = row[1].strip()
+            if val and val not in seen:
+                seen.add(val)
+                ids.append(val)
+            if len(ids) >= 10:
+                break
+    if len(ids) >= 10:
+        break
+
+print("找到的 Ticket ID：")
+for i, tid in enumerate(ids, 1):
+    print(f"  {i}. {tid}")
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1,5 @@
+requests
+urllib3
+# 可选：Salesforce 外链附件爬取
+scrapling[all]
+playwright
--- a/sap-c4c-AttachmentFolder.py
+++ b/sap-c4c-AttachmentFolder.py
@@ -373,7 +373,6 @@ def dsm_upload_downloaded_files(downloaded_files, ticket_id, serial_id, json_mod

    return upload_results

-
 def print_attachment_summary(all_attachments):
    """打印附件清单汇总"""
    print(f"\n{'='*60}")
@@ -680,7 +679,7 @@ def main():
        )
        result["dsmUpload"] = upload_results

-        # 上传完成后清理本地下载文件
+        # 上传完成后清理本地下载文件及子目录
        for f in result["downloadedFiles"]:
            local_path = f.get("savedPath")
            if local_path and os.path.exists(local_path):
@@ -691,6 +690,14 @@ def main():
                except OSError as e:
                    if not args.json_mode:
                        print(f"  删除失败: {local_path}: {e}")
+        # 删除空的下载子目录
+        try:
+            if os.path.isdir(args.output_dir) and not os.listdir(args.output_dir):
+                os.rmdir(args.output_dir)
+                if not args.json_mode:
+                    print(f"  已删除目录: {args.output_dir}")
+        except OSError:
+            pass

    if args.json_mode:
        print(json.dumps(result, ensure_ascii=False, indent=2))