{"id":21,"date":"2026-01-02T10:58:33","date_gmt":"2026-01-02T10:58:33","guid":{"rendered":"https:\/\/wordpress-fz3fv.wasmer.app\/?p=21"},"modified":"2026-04-15T07:01:58","modified_gmt":"2026-04-15T07:01:58","slug":"remove_duplicates","status":"publish","type":"post","link":"https:\/\/wp.bao.ksapp.me\/?p=21","title":{"rendered":"remove_duplicates"},"content":{"rendered":"\n<pre class=\"wp-block-code\"><code>import asyncio\nimport os\nimport sys\nfrom telethon import TelegramClient, errors\nfrom telethon.tl.types import MessageMediaDocument, DocumentAttributeFilename\nfrom dotenv import load_dotenv\n\n# ================== 1. \u8bfb\u53d6\u914d\u7f6e  \u9891\u9053\u89c6\u9891\u53bb\u91cd==================\nload_dotenv()\n\ntry:\n    api_id = int(os.getenv(\"API_ID\"))\n    api_hash = os.getenv(\"API_HASH\")\n    PHONE_NUMBER = os.getenv(\"PHONE_NUMBER\")\n    TWO_STEP_PASSWORD = os.getenv(\"TWO_STEP_PASSWORD\") or None\n    \n    # --- \u4fee\u590d\uff1a\u81ea\u52a8\u5224\u65ad\u9891\u9053 ID \u662f\u6570\u5b57\u8fd8\u662f\u7528\u6237\u540d ---\n    raw_target = os.getenv(\"TARGET_CHANNEL\")\n    try:\n        # \u5982\u679c\u662f\u6570\u5b57\uff08\u5982 -100xxx\uff09\uff0c\u8f6c\u6362\u4e3a\u6574\u6570\n        TARGET_CHANNEL = int(raw_target)\n    except (ValueError, TypeError):\n        # \u5982\u679c\u4e0d\u662f\u6570\u5b57\uff08\u5982 @username\uff09\uff0c\u4fdd\u6301\u5b57\u7b26\u4e32\n        TARGET_CHANNEL = raw_target\n\n    # \u626b\u63cf\u9650\u5236\uff1a\u8bbe\u7f6e\u4e3a\u60f3\u8981\u626b\u63cf\u7684\u3010\u89c6\u9891\u6570\u91cf\u3011\n    scan_env = os.getenv(\"SCAN_LIMIT\", \"21000\")\n    TARGET_VIDEO_COUNT = int(scan_env)\n    \nexcept Exception as e:\n    print(f\"\u274c \u914d\u7f6e\u9519\u8bef: {e}\")\n    sys.exit(1)\n\nclient = TelegramClient(\"session\/user_session\", api_id, api_hash)\n\n# ================== 2. \u5de5\u5177\u51fd\u6570 ==================\ndef get_video_info(message):\n    \"\"\"\n    \u89e3\u6790\u89c6\u9891\u4fe1\u606f\n    \u8fd4\u56de: (is_video, file_id, file_name)\n    \"\"\"\n    if not message.media or not isinstance(message.media, MessageMediaDocument):\n        return False, None, None\n\n    doc = message.media.document\n    \n    # \u5224\u5b9a\u662f\u5426\u4e3a\u89c6\u9891 mime \u7c7b\u578b\n    if not (doc.mime_type and doc.mime_type.startswith(\"video\/\")):\n        return False, None, None\n\n    # \u83b7\u53d6\u6587\u4ef6\u540d\uff08\u4ec5\u7528\u4e8e\u663e\u793a\uff0c\u4e0d\u7528\u4e8e\u5224\u91cd\uff09\n    file_name = \"\u672a\u77e5\u6587\u4ef6\u540d\"\n    for attr in doc.attributes:\n        if isinstance(attr, DocumentAttributeFilename):\n            file_name = attr.file_name\n            break\n\n    # Telethon document.id \u662f\u8be5\u6587\u4ef6\u5728 TG \u7cfb\u7edf\u5185\u7684\u552f\u4e00\u6807\u8bc6\n    return True, doc.id, file_name\n\n# ================== 3. \u4e3b\u903b\u8f91 ==================\nasync def main():\n    print(\"\ud83d\udd10 \u6b63\u5728\u767b\u5f55 Telegram...\")\n    # \u81ea\u52a8\u5904\u7406\u767b\u5f55\uff0c\u5982\u679c\u662f\u7b2c\u4e00\u6b21\u8fd0\u884c\uff0c\u63a7\u5236\u53f0\u4f1a\u8981\u6c42\u8f93\u5165\u9a8c\u8bc1\u7801\n    await client.start(phone=PHONE_NUMBER, password=TWO_STEP_PASSWORD)\n    print(\"\u2705 \u767b\u5f55\u6210\u529f\")\n\n    try:\n        # \u83b7\u53d6\u9891\u9053\u5b9e\u4f53\u5bf9\u8c61\n        target = await client.get_entity(TARGET_CHANNEL)\n        target_name = getattr(target, \"title\", TARGET_CHANNEL)\n    except Exception as e:\n        print(f\"\u274c \u65e0\u6cd5\u83b7\u53d6\u9891\u9053\u4fe1\u606f: {TARGET_CHANNEL}\")\n        print(f\"   \u539f\u56e0: {e}\")\n        print(\"   \u63d0\u793a: \u8bf7\u786e\u4fdd\u4f60\u5df2\u7ecf\u52a0\u5165\u4e86\u8be5\u9891\u9053\uff0c\u4e14 ID \u586b\u5199\u6b63\u786e\uff08ID\u5fc5\u987b\u662f\u6574\u6570\uff0c\u4e0d\u5e26\u5f15\u53f7\uff09\u3002\")\n        return\n\n    # \u663e\u793a\u5f53\u524d\u4efb\u52a1\u6a21\u5f0f\n    mode_str = \"\u65e0\u9650 (\u76f4\u5230\u626b\u63cf\u5b8c\u6240\u6709\u5386\u53f2)\" if TARGET_VIDEO_COUNT == 0 else f\"\u6700\u8fd1 {TARGET_VIDEO_COUNT} \u4e2a\u89c6\u9891\"\n    print(f\"\\n\ud83d\udcfa \u76ee\u6807\u9891\u9053\uff1a{target_name}\")\n    print(f\"\ud83c\udfaf \u626b\u63cf\u76ee\u6807\uff1a{mode_str}\")\n    print(f\"\u2699\ufe0f \u5224\u91cd\u7b56\u7565\uff1a\u4fdd\u7559\u3010\u6700\u65b0\u3011\u53d1\u5e03\u7684\u89c6\u9891\uff0c\u5220\u9664\u65e7\u7684\u91cd\u590d\u9879\")\n    print(\"-\" * 40)\n\n    seen_keys = set()    # \u8bb0\u5f55\u5df2\u51fa\u73b0\u7684\u89c6\u9891 ID\n    duplicates = &#91;]      # \u5b58\u50a8\u5f85\u5220\u9664\u7684\u6d88\u606f &#91;(msg_id, file_name), ...]\n\n    scanned_msgs = 0     # \u626b\u63cf\u8fc7\u7684\u6d88\u606f\u603b\u6570\uff08\u542b\u6587\u5b57\/\u56fe\u7247\uff09\n    found_videos = 0     # \u627e\u5230\u7684\u89c6\u9891\u6570\n\n    print(\"\u23f3 \u6b63\u5728\u626b\u63cf\u6d88\u606f (\u987a\u5e8f\uff1a\u4ece\u65b0 -> \u65e7)...\")\n\n    # limit=None \u8868\u793a\u5982\u679c\u4e0d\u624b\u52a8 break\uff0c\u5c31\u4e00\u76f4\u626b\u63cf\u4e0b\u53bb\n    async for msg in client.iter_messages(target, limit=None):\n        scanned_msgs += 1\n        \n        is_vid, file_id, file_name = get_video_info(msg)\n\n        if not is_vid:\n            continue\n\n        # \u627e\u5230\u4e00\u4e2a\u89c6\u9891\n        found_videos += 1\n        \n        # \u6838\u5fc3\u5224\u91cd\u903b\u8f91\n        if file_id in seen_keys:\n            # \u5df2\u7ecf\u5728 seen_keys \u91cc\uff0c\u8bf4\u660e\u4e4b\u524d\u626b\u63cf\u5230\u4e86\uff08\u5373\u66f4\u65b0\u7684\u6d88\u606f\u91cc\u6709\u8fd9\u4e2a\u89c6\u9891\uff09\n            # \u6240\u4ee5\u5f53\u524d\u8fd9\u6761\u8f83\u65e7\u7684\u6d88\u606f\u662f\u91cd\u590d\u7684\n            duplicates.append((msg.id, file_name))\n        else:\n            seen_keys.add(file_id)\n\n        # \u6253\u5370\u8fdb\u5ea6\u6761\n        if found_videos % 20 == 0:\n             print(f\"   \u5df2\u68c0\u7d22 {found_videos} \u4e2a\u89c6\u9891 (\u603b\u626b\u63cf\u6d88\u606f {scanned_msgs} \u6761)...\")\n\n        # \u8fbe\u5230\u6570\u91cf\u9650\u5236\uff0c\u9000\u51fa\u5faa\u73af\n        if TARGET_VIDEO_COUNT != 0 and found_videos >= TARGET_VIDEO_COUNT:\n            print(f\"\u2705 \u5df2\u8fbe\u5230\u8bbe\u5b9a\u7684 {TARGET_VIDEO_COUNT} \u4e2a\u89c6\u9891\u76ee\u6807\uff0c\u505c\u6b62\u626b\u63cf\u3002\")\n            break\n\n    print(\"-\" * 40)\n    print(\"\ud83d\udcca \u626b\u63cf\u7ed3\u679c\u7edf\u8ba1\")\n    print(f\"   \u603b\u626b\u63cf\u6d88\u606f\u6570\uff1a{scanned_msgs}\")\n    print(f\"   \u68c0\u7d22\u89c6\u9891\u603b\u6570\uff1a{found_videos}\")\n    print(f\"   \u53d1\u73b0\u91cd\u590d\u89c6\u9891\uff1a{len(duplicates)}\")\n\n    if not duplicates:\n        print(\"\u2705 \u6ca1\u6709\u53d1\u73b0\u9700\u8981\u5220\u9664\u7684\u91cd\u590d\u89c6\u9891\")\n        return\n\n    print(f\"\\n\u26a0\ufe0f \u5373\u5c06\u5220\u9664 {len(duplicates)} \u6761\u3010\u65e7\u7684\u91cd\u590d\u3011\u89c6\u9891\")\n    # \u7b49\u5f85\u7528\u6237\u786e\u8ba4\n    confirm = input(\"\u2753 \u786e\u8ba4\u5220\u9664\uff1f(\u8f93\u5165 y \u786e\u8ba4\uff0c\u5176\u4ed6\u952e\u53d6\u6d88): \").strip().lower()\n\n    if confirm != \"y\":\n        print(\"\ud83d\udeab \u5df2\u53d6\u6d88\u64cd\u4f5c\")\n        return\n\n    print(\"\ud83d\uddd1\ufe0f \u5f00\u59cb\u6267\u884c\u5220\u9664\u4efb\u52a1...\")\n    \n    # \u63d0\u53d6\u6240\u6709\u8981\u5220\u9664\u7684\u6d88\u606f ID\n    delete_ids = &#91;d&#91;0] for d in duplicates]\n    batch_size = 50 # \u6bcf\u6b21\u5220\u9664 50 \u6761\uff0c\u9632\u6b62\u8bf7\u6c42\u8fc7\u5927\n\n    for i in range(0, len(delete_ids), batch_size):\n        batch = delete_ids&#91;i:i + batch_size]\n        try:\n            await client.delete_messages(target, batch)\n            print(f\"   \u5df2\u5220\u9664 {min(i + batch_size, len(delete_ids))}\/{len(delete_ids)}\")\n            # \u9002\u5f53\u5ef6\u65f6\uff0c\u4fdd\u62a4\u8d26\u53f7\u5b89\u5168\n            await asyncio.sleep(1.5)\n        except errors.FloodWaitError as e:\n            print(f\"\u23f3 \u89e6\u53d1 Telegram \u6d41\u63a7 (FloodWait)\uff0c\u9700\u7b49\u5f85 {e.seconds} \u79d2...\")\n            await asyncio.sleep(e.seconds + 2)\n        except errors.MessageIdInvalidError:\n            print(f\"\u26a0\ufe0f \u67d0\u4e9b\u6d88\u606f\u53ef\u80fd\u5df2\u7ecf\u88ab\u5220\u9664\uff0c\u8df3\u8fc7\u8be5\u6279\u6b21\")\n        except Exception as e:\n            print(f\"\u274c \u5220\u9664\u51fa\u9519: {e}\")\n\n    print(f\"\\n\u2705 \u6e05\u7406\u5b8c\u6210\uff01\")\n\n# ================== 4. \u7a0b\u5e8f\u5165\u53e3 ==================\nif __name__ == \"__main__\":\n    # \u4f7f\u7528 with \u8bed\u6cd5\u81ea\u52a8\u7ba1\u7406\u8fde\u63a5\u548c\u65ad\u5f00\n    with client:\n        client.loop.run_until_complete(main())<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-21","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=\/wp\/v2\/posts\/21","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=21"}],"version-history":[{"count":0,"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=\/wp\/v2\/posts\/21\/revisions"}],"wp:attachment":[{"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=21"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=21"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.bao.ksapp.me\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=21"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}