Evilom/dc-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: collect complete Feishu media assets

Browse Source
This commit is contained in:
Evilom
2026-07-11 12:30:54 +08:00
parent 3ea50649f6
commit bbafe770b3
662 changed files with 15404 additions and 14017 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/dingtalk-feishu-collector/scripts/step2_extract_links.py
+21 -4
View File
@@ -7,10 +7,11 @@ from paths import RAW_DIR, LINKS_DIR, normalize_messages
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*')
MEDIA_RE = re.compile(r'mediaId=([^\s)]+)')
def extract(messages):
feishu, files, kimi = [], [], []
seen_f, seen_files = set(), set()
feishu, files, kimi, media = [], [], [], []
seen_f, seen_files, seen_media = set(), set(), set()
for grp, msgs in messages.items():
for m in msgs:
c, s, t = m.get("content",""), m.get("sender","?"), m.get("createTime","")
@@ -25,7 +26,19 @@ def extract(messages):
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}
for resource_id in MEDIA_RE.findall(c):
message_id = m.get("openMessageId", "")
key = message_id or resource_id
if key not in seen_media:
seen_media.add(key)
media.append({
"resourceId": resource_id,
"messageId": message_id,
"conversationId": m.get("openConversationId", ""),
"mediaType": "video" if "[视频消息]" in c else "image",
"sender": s, "time": t, "group": grp,
})
return {"feishu_links":feishu,"file_attachments":files,"kimi_links":kimi,"chat_media":media}
def load_json(path, default):
if not os.path.isfile(path): return default
@@ -55,10 +68,12 @@ def main():
old_links = load_json(os.path.join(LINKS_DIR,"all_feishu_links.json"), {}).get("links",[])
old_files = load_json(os.path.join(LINKS_DIR,"all_file_attachments.json"), [])
old_kimi = load_json(os.path.join(LINKS_DIR,"all_kimi_links.json"), [])
old_media = load_json(os.path.join(LINKS_DIR,"all_chat_media.json"), [])
r["feishu_links"] = merge_by_key(old_links, r["feishu_links"], "doc_id")
r["file_attachments"] = merge_by_key(old_files, r["file_attachments"], "fileId")
r["kimi_links"] = merge_by_key(old_kimi, r["kimi_links"], "url")
print(f"飞书: {len(r['feishu_links'])}, 附件: {len(r['file_attachments'])}, Kimi: {len(r['kimi_links'])}")
r["chat_media"] = merge_by_key(old_media, r["chat_media"], "messageId")
print(f"飞书: {len(r['feishu_links'])}, 附件: {len(r['file_attachments'])}, 媒体: {len(r['chat_media'])}, 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]
@@ -70,6 +85,8 @@ def main():
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)
with open(os.path.join(LINKS_DIR,"all_chat_media.json"),"w",encoding="utf-8") as f:
json.dump(r['chat_media'],f,ensure_ascii=False,indent=2)
print(f"保存至: {LINKS_DIR}")
if __name__ == "__main__": main()