聊天记录显示添加自定义数据库路径功能

This commit is contained in:
xaoyaoo 2024-01-16 23:24:16 +08:00
parent 9e2fa29e93
commit 051ecf1b93
6 changed files with 245 additions and 158 deletions

View File

@ -6,6 +6,7 @@
# Date: 2023/12/14
# -------------------------------------------------------------------------------
from .api import api
from .utils import read_session, save_session
if __name__ == '__main__':
pass

View File

@ -6,11 +6,14 @@
# Date: 2024/01/02
# -------------------------------------------------------------------------------
import base64
import logging
import os
import time
from flask import Flask, request, render_template, g, Blueprint, send_file, make_response, send_from_directory
from pywxdump import analyzer, read_img_dat, read_audio
from flask import Flask, request, render_template, g, Blueprint, send_file, make_response, session
from pywxdump import analyzer, read_img_dat, read_audio, get_wechat_db
from pywxdump.api.rjson import ReJson, RqJson
from pywxdump.api.utils import read_session, save_session
from pywxdump import read_info, VERSION_LIST, batch_decrypt, BiasAddr, merge_db
import pywxdump
@ -26,21 +29,85 @@ def init():
初始化
:return:
"""
# g.msg_path = path
# g.micro_path = path
# g.media_path = path
# g.wx_path = r"C:\Users\xaoyo\Documents\Tencent\WeChat Files\wxid_vzzcn5fevion22"
# g.my_wxid = "wxid_vzzcn5fevion22"
try:
msg_path = request.json.get("msg_path", "").strip()
micro_path = request.json.get("micro_path", "").strip()
media_path = request.json.get("media_path", "").strip()
wx_path = request.json.get("wx_path", "").strip()
key = request.json.get("key", "").strip()
my_wxid = request.json.get("my_wxid", "").strip()
if key: # 如果key不为空表示是解密模式
if not wx_path:
return ReJson(1002)
if not os.path.exists(wx_path):
return ReJson(1001)
# 解密
WxDbPath = get_wechat_db('all', None, wxid=my_wxid, is_logging=False) # 获取微信数据库路径
if isinstance(WxDbPath, str): # 如果返回的是字符串,则表示出错
print(WxDbPath)
return ReJson(4007)
wxdbpaths = [path for user_dir in WxDbPath.values() for paths in user_dir.values() for path in paths]
if len(wxdbpaths) == 0:
print("[-] 未获取到数据库路径")
return ReJson(4007)
wxdbpaths = [i for i in wxdbpaths if "MicroMsg" in i or "MediaMSG" in i or r"Multi\MSG" in i] # 过滤掉无需解密的数据库
decrypted_path = os.path.join(g.tmp_path, "decrypted")
# 判断out_path是否为空目录
if os.path.exists(decrypted_path) and os.listdir(decrypted_path):
isdel = "y"
if isdel.lower() == 'y' or isdel.lower() == 'yes':
for root, dirs, files in os.walk(decrypted_path, topdown=False):
for name in files:
os.remove(os.path.join(root, name))
for name in dirs:
os.rmdir(os.path.join(root, name))
out_path = os.path.join(decrypted_path, my_wxid) if my_wxid else decrypted_path
if not os.path.exists(out_path):
os.makedirs(out_path)
# 调用 decrypt 函数,并传入参数 # 解密
code, ret = batch_decrypt(key, wxdbpaths, out_path, False)
if not code:
return ReJson(4007, msg=ret)
out_dbs = []
for code1, ret1 in ret:
if code1:
out_dbs.append(ret1[1])
parpare_merge_db_path = [i for i in out_dbs if "de_MicroMsg" in i or "de_MediaMSG" in i or "de_MSG" in i]
# 合并所有的数据库
logging.info("开始合并数据库")
merge_save_path = merge_db(parpare_merge_db_path, os.path.join(out_path, "merge_all.db"))
time.sleep(1)
save_session(g.sf, "msg_path", merge_save_path)
save_session(g.sf, "micro_path", merge_save_path)
save_session(g.sf, "media_path", merge_save_path)
save_session(g.sf, "wx_path", wx_path)
save_session(g.sf, "key", key)
save_session(g.sf, "my_wxid", my_wxid)
rdata = {
"msg_path": merge_save_path,
"micro_path": merge_save_path,
"media_path": merge_save_path,
"wx_path": wx_path,
"key": key,
"my_wxid": my_wxid,
"is_init": True,
}
return ReJson(0, rdata)
else:
return ReJson(1002)
except Exception as e:
return ReJson(9999, msg=str(e))
rdata = {
"msg_path": "",
"micro_path": "",
"media_path": "",
"wx_path": "",
"my_wxid": "",
"is_init": False,
}
return ReJson(0, rdata)
@api.route('/api/version', methods=["GET", 'POST'])
def version():
@ -50,6 +117,7 @@ def version():
"""
return ReJson(0, pywxdump.__version__)
@api.route('/api/contact_list', methods=["GET", 'POST'])
def contact_list():
"""
@ -61,12 +129,12 @@ def contact_list():
# 从header中读取micro_path
micro_path = request.headers.get("micro_path")
if not micro_path:
micro_path = g.micro_path
micro_path = read_session(g.sf, "micro_path")
start = request.json.get("start")
limit = request.json.get("limit")
contact_list = analyzer.get_contact_list(micro_path)
g.user_list = contact_list
save_session(g.sf, "user_list", contact_list)
if limit:
contact_list = contact_list[int(start):int(start) + int(limit)]
return ReJson(0, contact_list)
@ -85,7 +153,7 @@ def chat_count():
# 从header中读取micro_path
msg_path = request.headers.get("msg_path")
if not msg_path:
msg_path = g.msg_path
msg_path = read_session(g.sf, "msg_path")
username = request.json.get("username", "")
contact_list = analyzer.get_chat_count(msg_path, username)
return ReJson(0, contact_list)
@ -105,9 +173,9 @@ def contact_count_list():
msg_path = request.headers.get("msg_path")
micro_path = request.headers.get("micro_path")
if not msg_path:
msg_path = g.msg_path
msg_path = read_session(g.sf, "msg_path")
if not micro_path:
micro_path = g.micro_path
micro_path = read_session(g.sf, "micro_path")
start = request.json.get("start")
limit = request.json.get("limit")
word = request.json.get("word", "")
@ -121,7 +189,7 @@ def contact_count_list():
# 降序
contact_list = sorted(contact_list, key=lambda x: x["chat_count"], reverse=True)
g.user_list = contact_list
save_session(g.sf, "user_list", contact_list)
if word and word != "" and word != "undefined" and word != "null":
contact_list = [contact for contact in contact_list if
@ -139,9 +207,9 @@ def get_msgs():
msg_path = request.headers.get("msg_path")
micro_path = request.headers.get("micro_path")
if not msg_path:
msg_path = g.msg_path
msg_path = read_session(g.sf, "msg_path")
if not micro_path:
micro_path = g.micro_path
micro_path = read_session(g.sf, "micro_path")
start = request.json.get("start")
limit = request.json.get("limit")
wxid = request.json.get("wxid")
@ -151,9 +219,10 @@ def get_msgs():
contact_list = analyzer.get_contact_list(micro_path)
userlist = {}
my_wxid = read_session(g.sf, "my_wxid")
if wxid.endswith("@chatroom"):
# 群聊
talkers = [msg["talker"] for msg in msg_list] + [wxid, g.my_wxid]
talkers = [msg["talker"] for msg in msg_list] + [wxid, my_wxid]
talkers = list(set(talkers))
for user in contact_list:
if user["username"] in talkers:
@ -161,12 +230,12 @@ def get_msgs():
else:
# 单聊
for user in contact_list:
if user["username"] == wxid or user["username"] == g.my_wxid:
if user["username"] == wxid or user["username"] == my_wxid:
userlist[user["username"]] = user
if len(userlist) == 2:
break
return ReJson(0, {"msg_list": msg_list, "user_list": userlist, "my_wxid": g.my_wxid})
return ReJson(0, {"msg_list": msg_list, "user_list": userlist, "my_wxid": my_wxid})
@api.route('/api/img', methods=["GET", 'POST'])
@ -179,7 +248,8 @@ def get_img():
img_path = request.json.get("img_path", img_path)
if not img_path:
return ReJson(1002)
img_path_all = os.path.join(g.wx_path, img_path)
wx_path = read_session(g.sf, "wx_path")
img_path_all = os.path.join(wx_path, img_path)
if os.path.exists(img_path_all):
fomt, md5, out_bytes = read_img_dat(img_path_all)
out_bytes = base64.b64encode(out_bytes).decode("utf-8")
@ -197,7 +267,8 @@ def get_audio(savePath):
MsgSvrID = savePath.split("_")[-1].replace(".wav", "")
if not savePath:
return ReJson(1002)
wave_data = read_audio(MsgSvrID, is_wave=True, DB_PATH=g.media_path)
media_path = read_session(g.sf, "media_path")
wave_data = read_audio(MsgSvrID, is_wave=True, DB_PATH=media_path)
if not wave_data:
return ReJson(1001)
# 判断savePath路径的文件夹是否存在
@ -223,8 +294,8 @@ def export():
username = request.json.get("username")
# 可选参数
wx_path = request.json.get("wx_path", g.wx_path)
key = request.json.get("key", "")
wx_path = request.json.get("wx_path", read_session(g.sf, "wx_path"))
key = request.json.get("key", read_session(g.sf, "key"))
if not export_type or not start_time or not end_time or not chat_type or not username:
return ReJson(1002)
@ -250,7 +321,7 @@ def export():
outpath = os.path.join(outpath, "csv")
if not os.path.exists(outpath):
os.makedirs(outpath)
code, ret = analyzer.export_csv(username, outpath, g.msg_path)
code, ret = analyzer.export_csv(username, outpath, read_session(g.sf, "msg_path"))
if code:
return ReJson(0, ret)
elif export_type == "json":

View File

@ -25,6 +25,7 @@ def ReJson(code: int, body: [dict, list] = None, msg: str = None, error: str = N
4004: {'code': 4004, 'body': body, 'msg': "数据不存在!", "extra": extra},
4005: {'code': 4005, 'body': body, 'msg': "数据库异常!", "extra": extra},
4006: {'code': 4006, 'body': body, 'msg': "数据已存在!", "extra": extra},
4007: {'code': 4007, 'body': body, 'msg': "数据库解密异常!", "extra": extra},
5002: {'code': 5002, 'body': body, 'msg': "服务器错误!", "extra": extra},
9999: {'code': 9999, 'body': body, 'msg': "未知错误!", "extra": extra},
}

30
pywxdump/api/utils.py Normal file
View File

@ -0,0 +1,30 @@
# -*- coding: utf-8 -*-#
# -------------------------------------------------------------------------------
# Name: utils.py
# Description:
# Author: xaoyaoo
# Date: 2024/01/16
# -------------------------------------------------------------------------------
import json
def read_session(session_file, arg):
with open(session_file, 'r') as f:
session = json.load(f)
return session.get(arg, "")
def save_session(session_file, arg, value):
try:
with open(session_file, 'r') as f:
session = json.load(f)
except:
session = {}
session[arg] = value
with open(session_file, 'w') as f:
json.dump(session, f, indent=4)
return True
if __name__ == '__main__':
pass

View File

@ -210,80 +210,15 @@ class MainShowChatRecords():
args.micro_path = merge_path
args.media_path = merge_path
try:
from flask import Flask, request, jsonify, render_template, g
import logging
except Exception as e:
print(e)
print("[-] 请安装flask( pip install flask )")
return
online = args.online
if not os.path.exists(args.msg_path) or not os.path.exists(args.micro_path) or not os.path.exists(
args.media_path):
print("[-] 输入数据库路径不存在")
return
from flask_cors import CORS
from pywxdump.api import api
app = Flask(__name__, template_folder='./ui/web', static_folder='./ui/web/assets/', static_url_path='/assets/')
app.logger.setLevel(logging.ERROR)
CORS(app, resources={r"/*": {"origins": "*"}}, supports_credentials=True) # 允许所有域名跨域
@app.before_request
def before_request():
g.msg_path = args.msg_path
g.micro_path = args.micro_path
g.media_path = args.media_path
g.wx_path = args.wx_path
# g.key = args.key
g.my_wxid = args.my_wxid
g.tmp_path = os.path.join(os.getcwd(), "wxdump_tmp") # 临时文件夹,用于存放图片等
g.user_list = []
app.register_blueprint(api)
try:
# 自动打开浏览器
url = "http://127.0.0.1:5000/"
# 根据操作系统使用不同的命令打开默认浏览器
if sys.platform.startswith('darwin'): # macOS
subprocess.call(['open', url])
elif sys.platform.startswith('win'): # Windows
subprocess.call(['start', url], shell=True)
elif sys.platform.startswith('linux'): # Linux
subprocess.call(['xdg-open', url])
else:
print("Unsupported platform, can't open browser automatically.")
except Exception as e:
pass
def is_port_in_use(host, port):
import socket
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
try:
s.bind((host, port))
except socket.error:
return True
return False
online = args.online
# 检查端口是否被占用
if online:
host = '0.0.0.0'
else:
host = "127.0.0.1"
port = 5000
if is_port_in_use(host, port):
print(f"Port {port} is already in use. Choose a different port.")
input("Press Enter to exit...")
else:
time.sleep(1)
print("[+] 请使用浏览器访问 http://127.0.0.1:5000/ 查看聊天记录")
app.run(host=host, port=port, debug=False)
start_falsk(msg_path=args.msg_path, micro_path=args.micro_path, media_path=args.media_path,
wx_path=args.wx_path, key="", my_wxid=args.my_wxid, online=online)
class MainExportChatRecords():
@ -455,6 +390,103 @@ class MainAll():
MainShowChatRecords().run(args)
def start_falsk(merge_path="", msg_path="", micro_path="", media_path="", wx_path="", key="", my_wxid="", port=5000,
online=False, debug=False):
"""
启动flask
:param merge_path: 合并后的数据库路径
:param msg_path: MSG.db 的路径
:param micro_path: MicroMsg.db 的路径
:param media_path: MediaMSG.db 的路径
:param wx_path: 微信文件夹的路径用于显示图片
:param key: 密钥
:param my_wxid: 微信账号(本人微信id)
:param port: 端口号
:param online: 是否在线查看(局域网查看)
:param debug: 是否开启debug模式
:return:
"""
tmp_path = os.path.join(os.getcwd(), "wxdump_tmp") # 临时文件夹,用于存放图片等
if not os.path.exists(tmp_path):
os.makedirs(tmp_path)
print(f"[+] 创建临时文件夹:{tmp_path}")
session_file = os.path.join(tmp_path, "session") # 用于存放各种基础信息
from flask import Flask, g
from flask_cors import CORS
from pywxdump.api import api, read_session, save_session
import logging
if merge_path:
msg_path = merge_path
micro_path = merge_path
media_path = merge_path
# 检查端口是否被占用
if online:
host = '0.0.0.0'
else:
host = "127.0.0.1"
app = Flask(__name__, template_folder='./ui/web', static_folder='./ui/web/assets/', static_url_path='/assets/')
# 设置超时时间为 1000 秒
app.config['TIMEOUT'] = 1000
app.secret_key = 'secret_key'
app.logger.setLevel(logging.ERROR)
CORS(app, resources={r"/*": {"origins": "*"}}, supports_credentials=True) # 允许所有域名跨域
@app.before_request
def before_request():
g.tmp_path = tmp_path # 临时文件夹,用于存放图片等
g.sf = session_file # 用于存放各种基础信息
if msg_path: save_session(session_file, "msg_path", msg_path)
if micro_path: save_session(session_file, "micro_path", micro_path)
if media_path: save_session(session_file, "media_path", media_path)
if wx_path: save_session(session_file, "wx_path", wx_path)
if key: save_session(session_file, "key", key)
if my_wxid: save_session(session_file, "my_wxid", my_wxid)
app.register_blueprint(api)
try:
# 自动打开浏览器
url = f"http://127.0.0.1:{port}/"
# 根据操作系统使用不同的命令打开默认浏览器
if sys.platform.startswith('darwin'): # macOS
subprocess.call(['open', url])
elif sys.platform.startswith('win'): # Windows
subprocess.call(['start', url], shell=True)
elif sys.platform.startswith('linux'): # Linux
subprocess.call(['xdg-open', url])
else:
print("Unsupported platform, can't open browser automatically.")
except Exception as e:
pass
def is_port_in_use(host, port):
import socket
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
try:
s.bind((host, port))
except socket.error:
return True
return False
if is_port_in_use(host, port):
print(f"Port {port} is already in use. Choose a different port.")
input("Press Enter to exit...")
else:
time.sleep(1)
print("[+] 请使用浏览器访问 http://127.0.0.1:5000/ 查看聊天记录")
app.run(host=host, port=port, debug=debug)
class MainUi():
def init_parses(self, parser):
self.mode = "ui"
@ -470,67 +502,10 @@ class MainUi():
print(f"[*] PyWxDump v{pywxdump.__version__}")
# 从命令行参数获取值
online = args.online
# 检查端口是否被占用
if online:
host = '0.0.0.0'
else:
host = "127.0.0.1"
port = args.port
debug = args.debug
from flask import Flask, g
import logging
from flask_cors import CORS
from pywxdump.api import api
app = Flask(__name__, template_folder='./ui/web', static_folder='./ui/web/assets/', static_url_path='/assets/')
app.logger.setLevel(logging.ERROR)
CORS(app, resources={r"/*": {"origins": "*"}}, supports_credentials=True) # 允许所有域名跨域
@app.before_request
def before_request():
g.msg_path = ""
g.media_path = ""
g.wx_path = ""
g.my_wxid = ""
g.tmp_path = os.path.join(os.getcwd(), "wxdump_tmp") # 临时文件夹,用于存放图片等
g.user_list = []
app.register_blueprint(api)
try:
# 自动打开浏览器
url = f"http://127.0.0.1:{port}/"
# 根据操作系统使用不同的命令打开默认浏览器
if sys.platform.startswith('darwin'): # macOS
subprocess.call(['open', url])
elif sys.platform.startswith('win'): # Windows
subprocess.call(['start', url], shell=True)
elif sys.platform.startswith('linux'): # Linux
subprocess.call(['xdg-open', url])
else:
print("Unsupported platform, can't open browser automatically.")
except Exception as e:
pass
def is_port_in_use(host, port):
import socket
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
try:
s.bind((host, port))
except socket.error:
return True
return False
if is_port_in_use(host, port):
print(f"Port {port} is already in use. Choose a different port.")
input("Press Enter to exit...")
else:
time.sleep(1)
print("[+] 请使用浏览器访问 http://127.0.0.1:5000/ 查看聊天记录")
app.run(host=host, port=port, debug=debug)
start_falsk(port=port, online=online, debug=debug)
class CustomArgumentParser(argparse.ArgumentParser):

View File

@ -225,6 +225,15 @@ def read_info(version_list: dict = None, is_logging: bool = False, save_path: st
def get_wechat_db(require_list: Union[List[str], str] = "all", msg_dir: str = None, wxid: Union[List[str], str] = None,
is_logging: bool = False):
r"""
获取微信数据库路径
:param require_list: 需要获取的数据库类型
:param msg_dir: 微信数据库目录 eg: C:\Users\user\Documents\WeChat Files
:param wxid: 微信id
:param is_logging: 是否打印日志
:return:
"""
if not msg_dir:
msg_dir = get_info_filePath(wxid="all")