feat: add dingtalk-feishu-collector SOP skill

Reusable 6-step pipeline for collecting DingTalk group messages, extracting Feishu doc links, fetching content, and generating summaries. Skills structure: - SKILL.md: trigger rules, workflow, config reference - config.yaml: group IDs, collection settings - scripts/paths.py: shared path resolution - scripts/step1-6: modular pipeline steps - scripts/run_all.py: one-click runner
2026-06-06 11:14:00 +08:00
parent fae01e9217
commit ab2ca1d836
15 changed files with 1476 additions and 0 deletions
@@ -0,0 +1,64 @@
+"""Step 5: 生成结构化总结"""
+import argparse, json, os, sys
+from datetime import datetime, timedelta
+from collections import defaultdict
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from paths import DATA_DIR, LINKS_DIR, DOCS_DIR, REPORTS_DIR
+
+def load_json(path):
+    if not os.path.isfile(path): return None
+    with open(path,"r",encoding="utf-8") as f: return json.load(f)
+
+def main():
+    p = argparse.ArgumentParser()
+    p.add_argument("--since",type=str); p.add_argument("--days",type=int)
+    p.add_argument("--full",action="store_true"); p.add_argument("--brief",action="store_true")
+    args = p.parse_args()
+
+    messages = load_json(os.path.join(DATA_DIR,"raw-messages","all_messages_combined.json")) or {}
+    content = load_json(os.path.join(LINKS_DIR,"all_feishu_content.json")) or {}
+    files = load_json(os.path.join(LINKS_DIR,"all_file_attachments.json")) or []
+    docs = {}
+    for d in content.get("documents",[]):
+        did = d.get("doc_id","") or d.get("url","")
+        if did: docs[did] = d
+
+    if args.since:
+        since = datetime.now().strftime("%Y-%m-%d 00:00:00") if args.since=="today" else (datetime.now()-timedelta(days=1)).strftime("%Y-%m-%d 00:00:00") if args.since=="yesterday" else args.since
+        messages = {g:[m for m in msgs if m.get("createTime","")>=since] for g,msgs in messages.items()}
+    elif args.days:
+        since = (datetime.now()-timedelta(days=args.days)).strftime("%Y-%m-%d 00:00:00")
+        messages = {g:[m for m in msgs if m.get("createTime","")>=since] for g,msgs in messages.items()}
+
+    lines = [f"# 钉钉群聊飞书文档采集报告", f"> 生成: {datetime.now().strftime('%Y-%m-%d %H:%M')}", ""]
+    total_m = sum(len(v) for v in messages.values())
+    lines += ["## 数据总览","","| 指标 | 数量 |","|------|------|",
+              f"| 消息 | {total_m} |", f"| 文档 | {len(docs)} |", f"| 附件 | {len(files)} |", ""]
+
+    for grp, msgs in messages.items():
+        if not msgs: continue
+        times = sorted([m.get("createTime","") for m in msgs])
+        gd = [d for d in docs.values() if d.get("group")==grp]
+        gf = [f for f in files if f.get("group")==grp]
+        lines += [f"### {grp}", f"- 消息: {len(msgs)} ({times[0]} ~ {times[-1]})", f"- 文档: {len(gd)}", f"- 附件: {len(gf)}", ""]
+        if args.brief: continue
+        senders = defaultdict(lambda: {"m":0,"d":0})
+        for m in msgs: senders[m.get("sender","?")]["m"]+=1
+        for d in gd: senders[d.get("sender","?")]["d"]+=1
+        lines += ["| 发送者 | 消息 | 文档 |","|--------|------|------|"]
+        for s,st in sorted(senders.items(),key=lambda x:-(x[1]["m"]+x[1]["d"])):
+            lines.append(f"| {s} | {st['m']} | {st['d']} |")
+        lines.append("")
+        lines.append("**最新消息:**")
+        for m in sorted(msgs,key=lambda x:x.get("createTime",""),reverse=True)[:10]:
+            c = m.get('content','')[:80].replace('\n',' ')
+            lines.append(f"- [{m.get('createTime','')}] **{m.get('sender','?')}**: {c}")
+        lines.append("")
+
+    os.makedirs(REPORTS_DIR, exist_ok=True)
+    report = "\n".join(lines)
+    for name in ["latest_summary.md", f"summary_{datetime.now().strftime('%Y%m%d')}.md"]:
+        with open(os.path.join(REPORTS_DIR,name),"w",encoding="utf-8") as f: f.write(report)
+    print(f"报告已生成: {REPORTS_DIR}")
+
+if __name__ == "__main__": main()