Files
zWorkFlow/chat_export_helpers.py
Davy 67de4a1d0c feat: 批量导出所有聊天为 JSON + 提取共享 helper 模块 (#77)
* Add export_all_chats.py: batch export all WeChat chats to JSON

Mirrors export_chat.py functionality to export every chat in the
decrypted WeChat database at once. Output format is byte-for-byte
identical to export_chat.py.

Usage: python3 export_all_chats.py [output_dir]

- Reads all sessions from decrypted/session/session.db
- Uses the same content extraction pipeline as export_chat.py:
  _resolve_sender, _extract_content, _msg_type_str, sticker/video/system
- Outputs group_<display>.json or single_<display>.json with same schema
- Progress reporting every 100 exports with summary at end

* refactor: 将 7 个重复 helper 函数提取到 chat_export_helpers.py

根据 PR #77 review 反馈,将 export_chat.py 和 export_all_chats.py 中
逐字复制的消息格式化函数提取到共享模块 chat_export_helpers.py。

提取的函数:
  MSG_TYPE_MAP, _msg_type_str, _resolve_sender,
  _decode_sticker_desc, _format_sticker_message,
  _format_system_message, _format_video_message, _extract_content

两个导出脚本现在从 chat_export_helpers import 所需函数,
消除代码漂移风险。
2026-05-12 11:42:48 +08:00

139 lines
4.2 KiB
Python

"""聊天导出共享工具函数。
本模块包含 export_chat.py 和 export_all_chats.py 共用的消息格式化函数。
统一维护,避免两处代码漂移。
"""
import base64
import mcp_server
MSG_TYPE_MAP = {
1: "text",
3: "image",
34: "voice",
42: "contact_card",
43: "video",
47: "sticker",
48: "location",
49: "link_or_file",
50: "call",
10000: "system",
10002: "recall",
}
def _msg_type_str(local_type):
base, _ = mcp_server._split_msg_type(local_type)
return MSG_TYPE_MAP.get(base, f"type_{local_type}")
def _resolve_sender(row, ctx, names, id_to_username):
"""Resolve the sender of a message.
Returns "me" for the logged-in user, or the sender's display name otherwise
(the contact's name in 1-on-1 chats, the member's name in groups). Empty
string for unattributable messages (e.g. system notifications).
"""
local_id, local_type, create_time, real_sender_id, content, ct = row
decoded = mcp_server._decompress_content(content, ct)
sender_from_content, _ = mcp_server._format_message_text(
local_id, local_type, decoded, ctx["is_group"], ctx["username"], ctx["display_name"], names
)
label = mcp_server._resolve_sender_label(
real_sender_id,
sender_from_content,
ctx["is_group"],
ctx["username"],
ctx["display_name"],
names,
id_to_username,
)
return label or ""
def _decode_sticker_desc(b64_desc):
"""WeChat encodes sticker labels as base64 protobuf: repeated (lang, text) pairs.
Returns the 'default' language label (usually Chinese), or None.
Limitation: treats the length byte as a single octet rather than a real protobuf
varint — labels >127 bytes would be misread. In practice sticker descriptions are
short (<30 chars), so this is adequate. Also sensitive to the bytes b"default"
appearing inside a preceding value; no such cases observed.
"""
try:
raw = base64.b64decode(b64_desc)
except Exception:
return None
# Find the 'default' marker; text follows as: \x12 <varint len> <utf-8>
i = raw.find(b"default")
if i < 0 or i + 7 >= len(raw) or raw[i + 7] != 0x12:
return None
try:
text_len = raw[i + 8]
text_bytes = raw[i + 9 : i + 9 + text_len]
return text_bytes.decode("utf-8") or None
except (IndexError, UnicodeDecodeError):
return None
def _format_sticker_message(content):
root = mcp_server._parse_xml_root(content) if content else None
if root is None:
return "[表情]"
emoji = root.find(".//emoji")
if emoji is None:
return "[表情]"
desc = emoji.get("desc") or ""
label = _decode_sticker_desc(desc) if desc else None
return f"[表情] {label}" if label else "[表情]"
def _format_system_message(content):
if not content:
return "[系统消息]"
if "<sysmsg" not in content:
return content
root = mcp_server._parse_xml_root(content)
if root is None:
return content
inner = root.findtext(".//content")
return inner.strip() if inner else content
def _format_video_message(content):
root = mcp_server._parse_xml_root(content) if content else None
if root is None:
return "[视频]"
video = root.find(".//videomsg")
if video is None:
return "[视频]"
playlength = video.get("playlength")
return f"[视频] {playlength}" if playlength else "[视频]"
def _extract_content(local_id, local_type, content, ct, chat_username, chat_display_name):
content = mcp_server._decompress_content(content, ct)
if content is None:
return None
base, _ = mcp_server._split_msg_type(local_type)
if base == 1:
return content or ""
if base == 43:
return _format_video_message(content)
if base == 47:
return _format_sticker_message(content)
if base == 49:
return mcp_server._format_app_message_text(
content, local_type, False, chat_username, chat_display_name, {}
)
if base == 50:
return mcp_server._format_voip_message_text(content)
if base == 10000:
return _format_system_message(content)
if base == 10002:
return "[撤回消息]"
return None