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。
This commit is contained in:
Davy
138
chat_export_helpers.py
Normal file
138
chat_export_helpers.py
Normal file
@@ -0,0 +1,138 @@
|
||||
"""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}秒" 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
|
||||
159
export_all_chats.py
Normal file
159
export_all_chats.py
Normal file
@@ -0,0 +1,159 @@
|
||||
#!/usr/bin/env python3
|
||||
"""批量导出所有微信聊天记录为 JSON 文件。
|
||||
|
||||
此脚本将导出所有会话的聊天记录，输出格式与 export_chat.py 完全一致。
|
||||
支持导出到指定目录，默认输出到 ./exported_chats 目录。
|
||||
|
||||
用法:
|
||||
python3 export_all_chats.py [output_dir]
|
||||
|
||||
示例:
|
||||
python3 export_all_chats.py /path/to/output
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sqlite3
|
||||
import sys
|
||||
from contextlib import closing
|
||||
from datetime import datetime
|
||||
|
||||
import mcp_server
|
||||
from chat_export_helpers import _extract_content, _msg_type_str, _resolve_sender
|
||||
|
||||
|
||||
def export_one(username, output_dir, names):
|
||||
"""
|
||||
导出单个会话。
|
||||
|
||||
返回: (成功标志, 消息数, 错误信息)
|
||||
"""
|
||||
ctx = mcp_server._resolve_chat_context(username)
|
||||
if ctx is None:
|
||||
return False, 0, f"Cannot resolve: {username}"
|
||||
|
||||
display_name = ctx["display_name"]
|
||||
message_tables = ctx["message_tables"]
|
||||
|
||||
if not message_tables:
|
||||
return False, 0, "no tables"
|
||||
|
||||
all_rows = []
|
||||
for table_info in message_tables:
|
||||
db_path = table_info["db_path"]
|
||||
table_name = table_info["table_name"]
|
||||
try:
|
||||
with closing(sqlite3.connect(db_path)) as conn:
|
||||
id_to_username = mcp_server._load_name2id_maps(conn)
|
||||
rows = mcp_server._query_messages(
|
||||
conn, table_name, limit=None, oldest_first=True
|
||||
)
|
||||
for row in rows:
|
||||
all_rows.append((row, id_to_username))
|
||||
except Exception as e:
|
||||
return False, 0, f"DB query error: {e}"
|
||||
|
||||
all_rows.sort(key=lambda pair: pair[0][2] or 0)
|
||||
|
||||
messages = []
|
||||
for row, id_to_username in all_rows:
|
||||
local_id, local_type, create_time, real_sender_id, content, ct = row
|
||||
sender = _resolve_sender(row, ctx, names, id_to_username)
|
||||
type_str = _msg_type_str(local_type)
|
||||
rendered = _extract_content(local_id, local_type, content, ct, username, display_name)
|
||||
|
||||
msg = {"local_id": local_id, "timestamp": create_time, "sender": sender}
|
||||
if type_str != "text":
|
||||
msg["type"] = type_str
|
||||
if rendered is not None:
|
||||
msg["content"] = rendered
|
||||
messages.append(msg)
|
||||
|
||||
if not messages:
|
||||
return False, 0, "empty"
|
||||
|
||||
output = {
|
||||
"chat": display_name,
|
||||
"username": username,
|
||||
"exported_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
"messages": messages,
|
||||
}
|
||||
if ctx["is_group"]:
|
||||
output["is_group"] = True
|
||||
|
||||
prefix = "group" if ctx["is_group"] else "single"
|
||||
safe = re.sub(r'[\\/:*?"<>|]', "_", f"{prefix}_{display_name}")
|
||||
out_path = os.path.join(output_dir, f"{safe}.json")
|
||||
with open(out_path, "w", encoding="utf-8") as f:
|
||||
json.dump(output, f, ensure_ascii=False, indent=2)
|
||||
|
||||
return True, len(messages), None
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="批量导出所有微信聊天记录为 JSON 文件",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog="""
|
||||
示例:
|
||||
python3 export_all_chats.py /path/to/output
|
||||
""",
|
||||
)
|
||||
parser.add_argument(
|
||||
"output_dir",
|
||||
nargs="?",
|
||||
default=None,
|
||||
help="输出目录路径 (默认: ./exported_chats)",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
output_dir = args.output_dir or os.path.join(script_dir, "exported_chats")
|
||||
|
||||
if not os.path.exists(mcp_server.DECRYPTED_DIR):
|
||||
print(f"错误: 解密目录不存在: {mcp_server.DECRYPTED_DIR}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
|
||||
session_db = os.path.join(mcp_server.DECRYPTED_DIR, "session", "session.db")
|
||||
try:
|
||||
with closing(sqlite3.connect(session_db)) as conn:
|
||||
sessions = [u for u, _ in conn.execute("SELECT username, type FROM SessionTable")]
|
||||
except sqlite3.Error as e:
|
||||
print(f"会话数据库查询失败: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
names = mcp_server.get_contact_names()
|
||||
|
||||
print(f"会话总数: {len(sessions)}")
|
||||
print(f"联系人映射: {len(names)}")
|
||||
print(f"输出目录: {output_dir}")
|
||||
print("=" * 60)
|
||||
|
||||
ok, skip, err, total = 0, 0, 0, 0
|
||||
for i, username in enumerate(sessions, 1):
|
||||
display = names.get(username, username)
|
||||
success, count, reason = export_one(username, output_dir, names)
|
||||
if success:
|
||||
ok += 1
|
||||
total += count
|
||||
if i <= 10 or i % 100 == 0:
|
||||
print(f"[{i}/{len(sessions)}] {display} - {count} 条消息")
|
||||
else:
|
||||
if "no tables" in str(reason) or "empty" in str(reason):
|
||||
skip += 1
|
||||
if i <= 10 or i % 50 == 0:
|
||||
print(f"[{i}/{len(sessions)}] {display} - 跳过({reason})")
|
||||
else:
|
||||
err += 1
|
||||
print(f"[{i}/{len(sessions)}] {display} - 失败: {reason}")
|
||||
|
||||
print()
|
||||
print("=" * 60)
|
||||
print(f"完成! 成功={ok} 跳过={skip} 失败={err} 总消息={total}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
133
export_chat.py
133
export_chat.py
@@ -41,136 +41,11 @@ from contextlib import closing
|
||||
from datetime import datetime
|
||||
|
||||
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
|
||||
from chat_export_helpers import (
|
||||
_extract_content,
|
||||
_msg_type_str,
|
||||
_resolve_sender,
|
||||
)
|
||||
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.
|
||||
"""
|
||||
import base64
|
||||
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}秒" 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
|
||||
|
||||
|
||||
def export_chat(chat_name, output_path):
|
||||
|
||||
Reference in New Issue
Block a user