修正一些逻辑细节
This commit is contained in:
-51
@@ -1,51 +0,0 @@
|
||||
# wxbot
|
||||
|
||||
微信聊天记录自动存sqlite数据库，基于微信网页版。注意，Web版获取不到微信用户的微信ID，所得到的用户名/ID是仅当前会话有效的，因此只有根据备注名在数据库中识别用户比较靠谱。
|
||||
|
||||
项目fork自[@Urinx/WeixinBot](https://github.com/Urinx/WeixinBot)，我只是加了个存到sqlite的壳，感谢老哥的网页版微信API。
|
||||
|
||||
## 数据表结构
|
||||
| 字段名 | 类型 | 说明 |
|
||||
| -- | -- | -- |
|
||||
| msg_id| TEXT | 消息ID |
|
||||
|create_time | INTEGER | 创建时间，Unix时间戳 |
|
||||
| msg_type | INTEGER | 消息类型，1-文本，3-图片，34-语音，43-视频，0-其它
|
||||
| content | TEXT | 消息的文本内容
|
||||
| from_id | TEXT | 消息发送者ID（不是微信ID，没啥用），如果是来自群的消息此字段为空
|
||||
| from_name | TEXT | 消息发送者的备注，没备注就昵称，如果是来自群的消息此字段为空
|
||||
| from_nickname | TEXT | 消息发送者的昵称，如果是来自群的消息此字段为空
|
||||
| to_id | TEXT | 接收者ID，如果是发送到群的消息此字段为空
|
||||
| to_name | TEXT | 接收者备注，没备注就昵称，如果是发送到群的消息此字段为空
|
||||
| to_nickname | TEXT | 接收者昵称，如果是发送到群的消息此字段为空
|
||||
| group_id | TEXT | 如果是群消息则为群的ID否则为空，照样，没啥用
|
||||
| group_name | TEXT | 如果是群消息则为群聊名称（应该吧🤣我不关注群消息），否则为空
|
||||
|
||||
消息里的图片等文件以`img_`，`voice_`等前缀 + 消息ID存储于命令行参数给定的数据目录中。
|
||||
|
||||
其它信息请参考[项目@Urinx/WeixinBot](https://github.com/Urinx/WeixinBot)。
|
||||
|
||||
## 使用
|
||||
### 克隆仓库并安装python依赖
|
||||
```shell
|
||||
# 不适用win系统
|
||||
git clone https://github.com/mattuylee/wxbot.git
|
||||
cd wxbot
|
||||
python3 -m venv ./venv
|
||||
source ./venv/bin/activate
|
||||
pip3 install -r ./requirements.txt
|
||||
```
|
||||
|
||||
### 运行
|
||||
`python ./main.py -f <DB_FILE> -d <DATA_DIR>`
|
||||
其中`DB_FILE`是sqlite数据库文件路径，`DATA_DIR`是图片视频等数据的存储目录。
|
||||
|
||||
支持sqlcipher加密，程序启动会要求输入密码，如不需要加密可留空直接回车。注意，以后每次启动必须输入相同的密码。暂不支持修改密码，可自行安装sqlcipher打开数据库修改密码。
|
||||
|
||||
未加密数据库可直接通过sqlite3打开，加密数据库需要sqlcipher才能打开。程序只负责记录数据，没有读取能力。
|
||||
|
||||
### 其它
|
||||
关于表情包，如果是从表情商店里添加的表情包网页版微信是获取不到的，为了保护创作者的权益。这倒是可以理解。
|
||||
|
||||
如果发现无法登录先试试在浏览器登录网页版微信，有可能是腾讯为了“安全”限制了你的微信帐号在网页登录。
|
||||
|
||||
最后，祝腾讯早点倒闭。
|
||||
@@ -7,20 +7,20 @@
|
||||
## 数据表结构
|
||||
| 字段名 | 类型 | 说明 |
|
||||
| -- | -- | -- |
|
||||
| msg_id| TEXT | 消息ID |
|
||||
| msg_id| TEXT | 消息ID，结构为创建时间+原微信消息ID |
|
||||
|create_time | INTEGER | 创建时间，Unix时间戳 |
|
||||
| msg_type | INTEGER | 消息类型，1-文本，3-图片，34-语音，43-视频，0-其它
|
||||
| content | TEXT | 消息的文本内容
|
||||
| from_id | TEXT | 消息发送者ID（不是微信ID，没啥用），如果是来自群的消息此字段为空
|
||||
| from_name | TEXT | 消息发送者的备注，没备注就昵称，如果是来自群的消息此字段为空
|
||||
| from_nickname | TEXT | 消息发送者的昵称，如果是来自群的消息此字段为空
|
||||
| to_id | TEXT | 接收者ID，如果是发送到群的消息此字段为空
|
||||
| to_name | TEXT | 接收者备注，没备注就昵称，如果是发送到群的消息此字段为空
|
||||
| to_nickname | TEXT | 接收者昵称，如果是发送到群的消息此字段为空
|
||||
| group_id | TEXT | 如果是群消息则为群的ID否则为空，照样，没啥用
|
||||
| group_name | TEXT | 如果是群消息则为群聊名称（应该吧🤣我不关注群消息），否则为空
|
||||
| msg_type | INTEGER | 消息类型，1-文本，3-图片，34-语音，43-视频，0-其它 |
|
||||
| content | TEXT | 消息的文本内容 |
|
||||
| from_id | TEXT | 消息发送者ID（不是微信ID，没啥用），如果是来自群的消息此字段为空 |
|
||||
| from_name | TEXT | 消息发送者的备注，没备注就昵称，如果是来自群的消息此字段为空 |
|
||||
| from_nickname | TEXT | 消息发送者的昵称，如果是来自群的消息此字段为空 |
|
||||
| to_id | TEXT | 接收者ID，如果是发送到群的消息此字段为空 |
|
||||
| to_name | TEXT | 接收者备注，没备注就昵称，如果是发送到群的消息此字段为空 |
|
||||
| to_nickname | TEXT | 接收者昵称，如果是发送到群的消息此字段为空 |
|
||||
| group_id | TEXT | 如果是群消息则为群的ID否则为空，照样，没啥用 |
|
||||
| group_name | TEXT | 如果是群消息则为群聊名称（应该吧🤣我不关注群消息），否则为空 |
|
||||
|
||||
消息里的图片等文件以`img_`，`voice_`等前缀 + 消息ID存储于命令行参数给定的数据目录中。
|
||||
消息里的图片等文件以消息ID存储于命令行参数给定的数据目录中，并根据年份划分子目录。
|
||||
|
||||
其它信息请参考[项目@Urinx/WeixinBot](https://github.com/Urinx/WeixinBot)。
|
||||
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
# coding: utf-8
|
||||
import argparse
|
||||
import getpass
|
||||
import logging
|
||||
import sys
|
||||
import time
|
||||
import os
|
||||
from weixin import WebWeixin
|
||||
from sqlcipher3 import dbapi2 as sqlite
|
||||
@@ -9,8 +12,9 @@ from sqlcipher3 import dbapi2 as sqlite
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("-f", "--db-file", required=True, help="数据库文件")
|
||||
parser.add_argument("-d", "--data-dir",required=True, help="文件存储目录")
|
||||
parser.add_argument('-f', '--db-file', required=True, help='数据库文件')
|
||||
parser.add_argument('-d', '--data-dir',required=True, help='文件存储目录')
|
||||
parser.add_argument('--debug', action='store_true', help='调试模式')
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
@@ -24,69 +28,116 @@ class WXBot(WebWeixin):
|
||||
return member['NickName']
|
||||
return None
|
||||
|
||||
def composeMessageID(self, msgID, timestamp):
|
||||
return time.strftime('%Y%m%d%H%M%S', time.localtime(timestamp)) + msgID
|
||||
|
||||
def saveMessageImage(self, msgid, composedID):
|
||||
url = self.base_uri + \
|
||||
'/webwxgetmsgimg?MsgID=%s&skey=%s' % (msgid, self.skey)
|
||||
data = self._get(url, 'webwxgetmsgimg')
|
||||
return self.saveFile(composedID[:4], composedID + '.jpg', data)
|
||||
|
||||
def saveVoice(self, msgid, composedID):
|
||||
url = self.base_uri + \
|
||||
'/webwxgetvoice?msgid=%s&skey=%s' % (msgid, self.skey)
|
||||
data = self._get(url, api='webwxgetvoice')
|
||||
return self.saveFile(composedID[:4], composedID + '.mp3', data)
|
||||
|
||||
def saveVideo(self, msgid, composedID):
|
||||
url = self.base_uri + \
|
||||
'/webwxgetvideo?msgid=%s&skey=%s' % (msgid, self.skey)
|
||||
data = self._get(url, api='webwxgetvideo')
|
||||
return self.saveFile(composedID[:4], composedID + '.mp4', data)
|
||||
|
||||
def saveFile(self, subdir, filename, data):
|
||||
if data == '':
|
||||
return False
|
||||
dirName = os.path.join(dataDir, subdir)
|
||||
if not os.path.exists(dirName):
|
||||
os.makedirs(dirName)
|
||||
fn = os.path.join(dirName, filename)
|
||||
with open(fn, 'wb') as f:
|
||||
f.write(data)
|
||||
f.close()
|
||||
return True
|
||||
|
||||
def handleMsg(self, r):
|
||||
if self.DEBUG:
|
||||
print("处理消息, NewMessageCount =", r['AddMsgCount'])
|
||||
for msg in r['AddMsgList']:
|
||||
msgID = msg['MsgId']
|
||||
composedID = self.composeMessageID(msgID, msg['CreateTime'])
|
||||
msgType = msg['MsgType']
|
||||
if msg['FromUserName'] in self.SpecialUsers or msg['ToUserName'] in self.SpecialUsers:
|
||||
# 过滤特殊帐号消息
|
||||
continue
|
||||
elif msgType in (50, 51, 52, 53, 9999):
|
||||
#无用消息
|
||||
continue
|
||||
sql = "INSERT INTO msg (\
|
||||
msg_id,\
|
||||
create_time,\
|
||||
msg_type,\
|
||||
content,\
|
||||
from_id,\
|
||||
from_name,\
|
||||
from_nickname,\
|
||||
to_id,\
|
||||
to_name,\
|
||||
to_nickname,\
|
||||
group_id,\
|
||||
group_name\
|
||||
) VALUES (\
|
||||
:msg_id,\
|
||||
:create_time,\
|
||||
:msg_type,\
|
||||
:content,\
|
||||
:from_id,\
|
||||
:from_name,\
|
||||
:from_nickname,\
|
||||
:to_id,\
|
||||
:to_name,\
|
||||
:to_nickname,\
|
||||
:group_id,\
|
||||
:group_name\
|
||||
)"
|
||||
params = {
|
||||
"msg_id": msgID,
|
||||
"msg_id": composedID,
|
||||
"create_time": msg['CreateTime'],
|
||||
"msg_type": msgType,
|
||||
"content": None,
|
||||
"from_id": msg['FromUserName'],
|
||||
"from_name": self.getUserRemarkName(msg['FromUserName']),
|
||||
"from_nickname": self.getUserNickName(msg['FromUserName']),
|
||||
"to_id": msg['ToUserName'],
|
||||
"to_name": self.getUserRemarkName(msg['ToUserName']),
|
||||
"to_nickname": self.getUserNickName(msg['ToUserName']),
|
||||
"group_id": None,
|
||||
"group_name": None
|
||||
}
|
||||
# 过滤特殊帐号消息
|
||||
if msg['FromUserName'] in self.SpecialUsers or msg['ToUserName'] in self.SpecialUsers:
|
||||
continue
|
||||
if msg['FromUserName'] == self.User['UserName']:
|
||||
params['from_name'] = '_self'
|
||||
elif msg['ToUserName'] == self.User['UserName']:
|
||||
params['to_name'] = '_self'
|
||||
if msg['FromUserName'][:2] == '@@':
|
||||
# 群消息
|
||||
if ":<br/>" in content:
|
||||
[people, content] = msg['Content'].split(':<br/>', 1)
|
||||
params['group_name'] = self.getUserRemarkName(msg['FromUserName'])
|
||||
params['from_name'] = self.getUserRemarkName(people)
|
||||
params['to_name'] = params['to_nickname'] = None
|
||||
elif msg['ToUserName'][:2] == '@@':
|
||||
# 发送的群消息
|
||||
params['group_name'] = self.getUserRemarkName(msg['ToUserName'])
|
||||
params['from_name'] = self.User['NickName']
|
||||
params['to_name'] = params['to_nickname'] = None
|
||||
if msgType == 1:
|
||||
# 文字消息
|
||||
params['content'] = msg['Content'].replace('<', '<').replace('>', '>')
|
||||
elif msgType == 3:
|
||||
params['content'] = "[图片](%s)" % msgID
|
||||
self.webwxgetmsgimg(msgID)
|
||||
params['content'] = "[图片](%s)" % composedID
|
||||
self.saveMessageImage(msgID, composedID)
|
||||
elif msgType == 34:
|
||||
params['content'] = "[语音](%s)" % msgID
|
||||
self.webwxgetvoice(msgID)
|
||||
params['content'] = "[语音](%s)" % composedID
|
||||
self.saveVoice(msgID, composedID)
|
||||
elif msgType == 43:
|
||||
params['content'] = "[视频](%s)" % msgID
|
||||
self.webwxgetvideo(msgID)
|
||||
params['content'] = "[视频](%s)" % composedID
|
||||
self.saveVideo(msgID, composedID)
|
||||
elif msgType == 62:
|
||||
params['msg_type'] = 43
|
||||
params['content'] = "[小视频](%s)" % msgID
|
||||
self.webwxgetvideo(msgID)
|
||||
params['content'] = "[小视频](%s)" % composedID
|
||||
self.saveVideo(msgID, composedID)
|
||||
elif msgType == 42:
|
||||
params['msg_type'] = 0
|
||||
params['content'] = "[名片](%s)" % msg['RecommendInfo']['NickName']
|
||||
@@ -97,34 +148,33 @@ class WXBot(WebWeixin):
|
||||
params['content'] = "[表情包图片]"
|
||||
else:
|
||||
params['msg_type'] = 3
|
||||
params['content'] = "[动画表情](%s)" % msgID
|
||||
self.webwxgetmsgimg(msgID)
|
||||
params['content'] = "[动画表情](%s)" % composedID
|
||||
self.saveMessageImage(msgID, composedID)
|
||||
elif msgType == 49:
|
||||
params['msg_type'] = 0
|
||||
params['content'] = "[链接：%s](%s)" % (msg['FileName'], msg['Url'])
|
||||
elif (50, 51, 52, 53, 9999, 10000, 10002).index(msgType) >= 0:
|
||||
continue
|
||||
elif msgType == 10000:
|
||||
params['msg_type'] = 0
|
||||
params['content'] = "[系统消息](%s)" % (msg['Content'])
|
||||
elif msgType == 10002:
|
||||
params['msg_type'] = 0
|
||||
params['content'] = "[系统消息](%s撤回了一条消息)" % params['from_name']
|
||||
else:
|
||||
params['msg_type'] = 0
|
||||
params['content'] = ""
|
||||
continue
|
||||
# 群消息
|
||||
if msg['FromUserName'][:2] == '@@':
|
||||
if ":<br/>" in content:
|
||||
[people, content] = msg['Content'].split(':<br/>', 1)
|
||||
params['group_name'] = self.getUserRemarkName(msg['FromUserName'])
|
||||
params['from_id'] = people
|
||||
params['from_name'] = self.getUserRemarkName(people)
|
||||
params['to_id'] = params['to_name'] = params['to_nickname'] = None
|
||||
elif msg['ToUserName'][:2] == '@@':
|
||||
params['group_name'] = self.getUserRemarkName(msg['ToUserName'])
|
||||
params['from_id'] = self.User['UserName']
|
||||
params['from_name'] = self.User['NickName']
|
||||
params['to_id'] = params['to_name'] = params['to_nickname'] = None
|
||||
params['content'] = "[未识别消息]" + msg['Content']
|
||||
conn.execute(sql, params)
|
||||
conn.commit()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if sys.stdout.encoding == 'cp936':
|
||||
sys.stdout = UnicodeStreamFilter(sys.stdout)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not sys.platform.startswith('win'):
|
||||
import coloredlogs
|
||||
coloredlogs.install(level='INFO')
|
||||
|
||||
args = parse_args()
|
||||
dataDir = args.data_dir
|
||||
if not os.access(os.path.dirname(args.db_file), os.X_OK) and not os.access(args.db_file, os.W_OK):
|
||||
@@ -134,7 +184,6 @@ elif not os.access(dataDir, os.X_OK):
|
||||
print("数据目录不存在或权限不足")
|
||||
exit()
|
||||
conn = sqlite.connect(args.db_file)
|
||||
|
||||
while True:
|
||||
try:
|
||||
passwd = getpass.getpass("输入数据库密码：")
|
||||
@@ -145,13 +194,10 @@ while True:
|
||||
create_time INTEGER NOT NULL,\
|
||||
msg_type INTEGER NOT NULL,\
|
||||
content TEXT,\
|
||||
from_id TEXT,\
|
||||
from_name TEXT,\
|
||||
from_nickname TEXT,\
|
||||
to_id TEXT,\
|
||||
to_name TEXT,\
|
||||
to_nickname TEXT,\
|
||||
group_id TEXT,\
|
||||
group_name TEXT\
|
||||
);")
|
||||
break
|
||||
@@ -165,16 +211,7 @@ while True:
|
||||
except Exception as e:
|
||||
print("打开数据库失败", e)
|
||||
exit(1)
|
||||
|
||||
|
||||
if sys.stdout.encoding == 'cp936':
|
||||
sys.stdout = UnicodeStreamFilter(sys.stdout)
|
||||
|
||||
if __name__ == '__main__':
|
||||
logger = logging.getLogger(__name__)
|
||||
if not sys.platform.startswith('win'):
|
||||
import coloredlogs
|
||||
coloredlogs.install(level='INFO')
|
||||
wxbot = WXBot()
|
||||
wxbot.DEBUG = args.debug
|
||||
wxbot.saveFolder = dataDir
|
||||
wxbot.start()
|
||||
|
||||
@@ -118,7 +118,6 @@ class WebWeixin(object):
|
||||
self.memberCount = 0
|
||||
self.SpecialUsers = ['newsapp', 'fmessage', 'filehelper', 'weibo', 'qqmail', 'fmessage', 'tmessage', 'qmessage', 'qqsync', 'floatbottle', 'lbsapp', 'shakeapp', 'medianote', 'qqfriend', 'readerapp', 'blogapp', 'facebookapp', 'masssendapp', 'meishiapp', 'feedsapp',
|
||||
'voip', 'blogappweixin', 'weixin', 'brandsessionholder', 'weixinreminder', 'wxid_novlwrv3lqwv11', 'gh_22b87fa7cb3c', 'officialaccounts', 'notification_messages', 'wxid_novlwrv3lqwv11', 'gh_22b87fa7cb3c', 'wxitil', 'userexperience_alarm', 'notification_messages']
|
||||
self.TimeOut = 20 # 同步最短时间间隔（单位：秒）
|
||||
self.media_count = -1
|
||||
|
||||
self.cookie = http.cookiejar.CookieJar()
|
||||
@@ -265,6 +264,15 @@ class WebWeixin(object):
|
||||
}
|
||||
return True
|
||||
|
||||
def logout(self):
|
||||
request = urllib.request.Request(
|
||||
url='https://wx.qq.com/cgi-bin/mmwebwx-bin/webwxlogout?redirect=0&type=1&skey=%s' % self.skey,
|
||||
data=urllib.parse.urlencode({
|
||||
'sid': self.sid,
|
||||
'uin': self.uin,
|
||||
}).encode(encoding='utf-8'))
|
||||
urllib.request.urlopen(request)
|
||||
|
||||
def webwxinit(self):
|
||||
url = self.base_uri + '/webwxinit?pass_ticket=%s&skey=%s&r=%s' % (
|
||||
self.pass_ticket, self.skey, int(time.time()))
|
||||
@@ -406,7 +414,7 @@ class WebWeixin(object):
|
||||
'_': int(time.time()),
|
||||
}
|
||||
url = 'https://' + self.syncHost + '/cgi-bin/mmwebwx-bin/synccheck?' + urllib.parse.urlencode(params)
|
||||
data = self._get(url, timeout=5)
|
||||
data = self._get(url, timeout=30)
|
||||
if data == '':
|
||||
return [-1,-1]
|
||||
|
||||
@@ -893,24 +901,18 @@ class WebWeixin(object):
|
||||
logging.debug('[*] 你在其他地方登录了 WEB 版微信，债见')
|
||||
break
|
||||
elif retcode == '0':
|
||||
if selector == '2':
|
||||
shouldSleep = True
|
||||
if selector != '0':
|
||||
# 有需要同步的消息
|
||||
r = self.webwxsync()
|
||||
if r is not None:
|
||||
if r is not None and r['AddMsgCount'] > 0:
|
||||
shouldSleep = False
|
||||
self.handleMsg(r)
|
||||
elif selector == '6':
|
||||
# TODO
|
||||
redEnvelope += 1
|
||||
print('[*] 收到疑似红包消息 %d 次' % redEnvelope)
|
||||
logging.debug('[*] 收到疑似红包消息 %d 次' % redEnvelope)
|
||||
elif selector == '7':
|
||||
playWeChat += 1
|
||||
print('[*] 你在手机上玩微信被我发现了 %d 次' % playWeChat)
|
||||
logging.debug('[*] 你在手机上玩微信被我发现了 %d 次' % playWeChat)
|
||||
r = self.webwxsync()
|
||||
elif selector == '0':
|
||||
time.sleep(1)
|
||||
if (time.time() - self.lastCheckTs) <= 20:
|
||||
time.sleep(time.time() - self.lastCheckTs)
|
||||
if shouldSleep and time.time() - self.lastCheckTs <= 5:
|
||||
# 微信有bug，发送某些消息后轮询会立马返回并报告有消息，但是调用同步接口后发现根本没有新消息，当收到其它消息后又会恢复
|
||||
# 这个现象一般出现在发送表情包之后。可以在浏览器打开控制台，会发现在手机发送表情后轮询接口被疯狂调用
|
||||
# 这里是防止轮询接口调用太频繁而实际上根本没有消息，浪费带宽
|
||||
time.sleep(5)
|
||||
|
||||
def sendMsg(self, name, word, isfile=False):
|
||||
id = self.getUSerID(name)
|
||||
@@ -1020,6 +1022,7 @@ class WebWeixin(object):
|
||||
listenProcess.terminate()
|
||||
print('[*] 退出微信')
|
||||
logging.debug('[*] 退出微信')
|
||||
self.logout()
|
||||
exit()
|
||||
elif text[:2] == '->':
|
||||
[name, word] = text[2:].split(':')
|
||||
|
||||
+2
-20
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"modules": [
|
||||
{
|
||||
"name": "core",
|
||||
"chnname": "NOTA核心",
|
||||
"name": "wxbot",
|
||||
"chnname": "wxbot",
|
||||
"entities": [
|
||||
{
|
||||
"title": "msg",
|
||||
@@ -37,12 +37,6 @@
|
||||
"remark": "",
|
||||
"chnname": "消息内容"
|
||||
},
|
||||
{
|
||||
"name": "from_id",
|
||||
"type": "TEXT_ID",
|
||||
"remark": "",
|
||||
"chnname": "发送者ID"
|
||||
},
|
||||
{
|
||||
"name": "from_name",
|
||||
"type": "TEXT",
|
||||
@@ -55,12 +49,6 @@
|
||||
"remark": "昵称",
|
||||
"chnname": "发送者昵称"
|
||||
},
|
||||
{
|
||||
"name": "to_id",
|
||||
"type": "TEXT_ID",
|
||||
"remark": "",
|
||||
"chnname": "接收者ID"
|
||||
},
|
||||
{
|
||||
"name": "to_name",
|
||||
"type": "TEXT",
|
||||
@@ -73,12 +61,6 @@
|
||||
"remark": "",
|
||||
"chnname": "接收者昵称"
|
||||
},
|
||||
{
|
||||
"name": "group_id",
|
||||
"type": "TEXT_ID",
|
||||
"remark": "",
|
||||
"chnname": "群组ID"
|
||||
},
|
||||
{
|
||||
"name": "group_name",
|
||||
"type": "TEXT",
|
||||
|
||||
Reference in New Issue
Block a user