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 +1,79 @@
+"""Step 6: 更新知识库（Obsidian + 知识图谱）"""
+import json, os, sys
+from datetime import datetime
+from collections import defaultdict
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from paths import LINKS_DIR, DATA_DIR, DOCS_DIR, OBSIDIAN_DIR, KG_DIR
+
+def safe_name(n):
+    for c in '<>:"/\\|?*': n=n.replace(c,'_')
+    return n[:80]
+
+def w(path, content):
+    os.makedirs(os.path.dirname(path), exist_ok=True)
+    with open(path,"w",encoding="utf-8") as f: f.write(content)
+
+def load_json(p):
+    if not os.path.isfile(p): return None
+    with open(p,"r",encoding="utf-8") as f: return json.load(f)
+
+def main():
+    content = load_json(os.path.join(LINKS_DIR,"all_feishu_content.json")) or {}
+    messages = load_json(os.path.join(DATA_DIR,"raw-messages","all_messages_combined.json")) or {}
+    docs = content.get("documents",[])
+
+    print(f"文档: {len(docs)}, 消息: {sum(len(v) for v in messages.values())}")
+
+    # Obsidian
+    by_group = defaultdict(list)
+    for d in docs: by_group[d.get("group","未分组")].append(d)
+    by_sender = defaultdict(list)
+    for d in docs: by_sender[d.get("sender","?")].append(d)
+
+    moc = ["---","tags: [MOC, 飞书文档]",f"created: {datetime.now().strftime('%Y-%m-%d')}","---","","# 飞书文档知识库","",f"> 更新: {datetime.now().strftime('%Y-%m-%d %H:%M')}",""]
+    for grp, gd in sorted(by_group.items()):
+        moc.append(f"## {grp}")
+        for d in sorted(gd,key=lambda x:x.get("time",""),reverse=True):
+            t = d.get("title","") or d.get("doc_id","")
+            moc.append(f"- [[{safe_name(t)}]] ({d.get('sender','?')}, {d.get('time','')})")
+        moc.append("")
+    w(os.path.join(OBSIDIAN_DIR,"00-MOC","飞书文档索引.md"),"\n".join(moc))
+
+    for sender, sd in sorted(by_sender.items()):
+        lines = ["---",f"tags: [人物, {sender}]","---",f"# {sender}",f"\n贡献: {len(sd)} 篇\n"]
+        for d in sorted(sd,key=lambda x:x.get("time",""),reverse=True):
+            t = d.get("title","") or d.get("doc_id","")
+            lines.append(f"- [[{safe_name(t)}]] ({d.get('time','')})")
+        w(os.path.join(OBSIDIAN_DIR,"04-人物",f"{safe_name(sender)}.md"),"\n".join(lines))
+
+    for d in docs:
+        did = d.get("doc_id","")
+        fpath = os.path.join(DOCS_DIR,f"{did}.md")
+        if not os.path.isfile(fpath): continue
+        with open(fpath,"r",encoding="utf-8") as f: c = f.read()
+        t = d.get("title","") or did
+        fm = ["---",f"tags: [飞书文档, {d.get('group','')}]",f"sender: {d.get('sender','')}",f"date: {d.get('time','')}",f"source: {d.get('url','')}","---",""]
+        w(os.path.join(OBSIDIAN_DIR,"01-产品研究",f"{safe_name(t)}.md"),"\n".join(fm)+c)
+    print(f"  Obsidian: {len(docs)} 文档, {len(by_sender)} 人物")
+
+    # 知识图谱
+    nodes, edges, nids = [], [], set()
+    for s in {d.get("sender","") for d in docs} | {m.get("sender","") for msgs in messages.values() for m in msgs}:
+        if s: nid=f"person:{s}"; nodes.append({"id":nid,"type":"person","label":s}); nids.add(nid)
+    for d in docs:
+        did,t = d.get("doc_id",""), d.get("title","") or d.get("doc_id","")
+        nid = f"doc:{did}"
+        if nid not in nids: nodes.append({"id":nid,"type":"document","label":t[:50]}); nids.add(nid)
+        s = d.get("sender","")
+        if s: edges.append({"source":f"person:{s}","target":nid,"type":"authored"})
+        g = d.get("group","")
+        if g:
+            gid=f"group:{g}"
+            if gid not in nids: nodes.append({"id":gid,"type":"group","label":g}); nids.add(gid)
+            edges.append({"source":gid,"target":nid,"type":"contains"})
+    os.makedirs(KG_DIR, exist_ok=True)
+    with open(os.path.join(KG_DIR,"knowledge_graph.json"),"w",encoding="utf-8") as f:
+        json.dump({"date":datetime.now().strftime("%Y-%m-%d"),"nodes":nodes,"edges":edges},f,ensure_ascii=False,indent=2)
+    print(f"  图谱: {len(nodes)} 节点, {len(edges)} 关系")
+
+if __name__ == "__main__": main()