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 +1,51 @@
+"""Step 2: 从消息中提取飞书链接和文件附件"""
+import argparse, json, os, re, sys
+from datetime import datetime
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from paths import RAW_DIR, LINKS_DIR
+
+FEISHU_RE = re.compile(r'https?://[a-zA-Z0-9.-]+\.feishu\.cn/(?:wiki|docx)/[A-Za-z0-9]+')
+FILE_RE = re.compile(r'\[文件\]\s+(.+?)\s+fileId:\s+(\S+)')
+KIMI_RE = re.compile(r'https?://[a-zA-Z0-9.-]+\.ok\.kimi\.link/\S*')
+
+def extract(messages):
+    feishu, files, kimi = [], [], []
+    seen_f, seen_files = set(), set()
+    for grp, msgs in messages.items():
+        for m in msgs:
+            c, s, t = m.get("content",""), m.get("sender","?"), m.get("createTime","")
+            for url in FEISHU_RE.findall(c):
+                if url not in seen_f:
+                    seen_f.add(url)
+                    dm = re.search(r'feishu\.cn/(?:wiki|docx)/([A-Za-z0-9]+)', url)
+                    feishu.append({"url":url,"doc_id":dm.group(1) if dm else "","type":"wiki" if "/wiki/" in url else "docx","sender":s,"time":t,"group":grp})
+            for name, fid in FILE_RE.findall(c):
+                if fid not in seen_files:
+                    seen_files.add(fid)
+                    files.append({"name":name.strip(),"fileId":fid,"sender":s,"time":t,"group":grp})
+            for url in KIMI_RE.findall(c):
+                kimi.append({"url":url,"desc":c.split("https")[0].strip()[:80],"sender":s,"group":grp})
+    return {"feishu_links":feishu,"file_attachments":files,"kimi_links":kimi}
+
+def main():
+    p = argparse.ArgumentParser(); p.add_argument("--incremental",action="store_true"); args = p.parse_args()
+    path = os.path.join(RAW_DIR, "all_messages_combined.json")
+    if not os.path.isfile(path): print(f"ERROR: {path} not found"); sys.exit(1)
+    with open(path,"r",encoding="utf-8") as f: messages = json.load(f)
+    print(f"消息: {sum(len(v) for v in messages.values())} 条")
+    r = extract(messages)
+    print(f"飞书: {len(r['feishu_links'])}, 附件: {len(r['file_attachments'])}, Kimi: {len(r['kimi_links'])}")
+    for grp in messages:
+        gl = [l for l in r['feishu_links'] if l['group']==grp]
+        gf = [f for f in r['file_attachments'] if f['group']==grp]
+        print(f"  [{grp}] 飞书:{len(gl)} 附件:{len(gf)}")
+    os.makedirs(LINKS_DIR, exist_ok=True)
+    with open(os.path.join(LINKS_DIR,"all_feishu_links.json"),"w",encoding="utf-8") as f:
+        json.dump({"date":datetime.now().strftime("%Y-%m-%d"),"total":len(r['feishu_links']),"links":r['feishu_links']},f,ensure_ascii=False,indent=2)
+    with open(os.path.join(LINKS_DIR,"all_file_attachments.json"),"w",encoding="utf-8") as f:
+        json.dump(r['file_attachments'],f,ensure_ascii=False,indent=2)
+    with open(os.path.join(LINKS_DIR,"all_kimi_links.json"),"w",encoding="utf-8") as f:
+        json.dump(r['kimi_links'],f,ensure_ascii=False,indent=2)
+    print(f"保存至: {LINKS_DIR}")
+
+if __name__ == "__main__": main()