feat: collect complete Feishu media assets

skills/dingtalk-feishu-collector/scripts/fetch_feishu_full.py

@@ -4,15 +4,22 @@ import argparse, json, os, subprocess, sys, time
 from datetime import datetime
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-from paths import LINKS_DIR, DOCS_DIR, OUTPUT_DIR
+from paths import LINKS_DIR, DOCS_DIR, OUTPUT_DIR, find_lark_cli
 
-LARK = r'C:\Users\admin\AppData\Roaming\npm\node_modules\@larksuite\cli\bin\lark-cli.exe'
+LARK = find_lark_cli()
 IMAGES_DIR = os.path.join(OUTPUT_DIR, 'feishu-images')
 
-def lark_api(path, timeout=30):
-    r = subprocess.run([LARK, 'api', 'GET', path, '--format', 'json'], capture_output=True, timeout=timeout)
+def lark_api(path, params=None, timeout=30):
+    cmd = [LARK, 'api', 'GET', path, '--format', 'json']
+    if params:
+        cmd += ['--params', json.dumps(params, ensure_ascii=False)]
+    r = subprocess.run(cmd, capture_output=True, timeout=timeout)
     out = r.stdout.decode('utf-8', errors='replace')
-    try: return json.loads(out)
+    try:
+        result = json.loads(out)
+        if result.get('ok') is True:
+            return {'code': 0, 'data': result.get('data', {})}
+        return result
     except: return None
 
 def download_media(token, local_path, timeout=30):
@@ -29,7 +36,7 @@ def download_media(token, local_path, timeout=30):
     except: return False
 
 def resolve_wiki(node_id):
-    data = lark_api(f'/open-apis/wiki/v2/spaces/get_node?token={node_id}')
+    data = lark_api('/open-apis/wiki/v2/spaces/get_node', params={'token': node_id})
     if data and data.get('code') == 0:
         node = data.get('data', {}).get('node', {})
         return node.get('obj_token', ''), node.get('title', '')
@@ -192,7 +199,14 @@ def main():
         
         if not args.rebuild and doc_id in existing:
             old = existing[doc_id]
-            if old.get('fetched', False) and old.get('content_length', 0) > 200 and old.get('images_downloaded', 0) > 0:
+            image_blocks = old.get('image_blocks')
+            images_downloaded = old.get('images_downloaded')
+            media_complete = (
+                image_blocks is not None
+                and images_downloaded is not None
+                and images_downloaded >= image_blocks
+            )
+            if old.get('fetched', False) and old.get('content_length', 0) > 200 and media_complete:
                 skip += 1
                 continue