重构导出csv

pywxdump/api/api.py

@@ -23,6 +23,7 @@ from pywxdump import read_info, VERSION_LIST, batch_decrypt, BiasAddr, merge_db,
 import pywxdump
 from pywxdump.dbpreprocess import wxid2userinfo, ParsingMSG, get_user_list, get_recent_user_list, ParsingMediaMSG, \
     download_file
+from pywxdump.dbpreprocess import export_csv
 
 # app = Flask(__name__, static_folder='../ui/web/dist', static_url_path='/')
 
@@ -440,7 +441,7 @@ def get_file(filePath):
 # start 导出聊天记录 *****************************************************************************************************
 
 @api.route('/api/export_endb', methods=["GET", 'POST'])
-def export_endb():
+def get_export_endb():
     """
     导出加密数据库
     :return:
@@ -472,7 +473,7 @@ def export_endb():
 
 
 @api.route('/api/export_dedb', methods=["GET", "POST"])
-def export_dedb():
+def get_export_dedb():
     """
     导出解密数据库
     :return:
@@ -483,15 +484,47 @@ def export_dedb():
     key = request.json.get("key", read_session(g.sf, my_wxid, "key"))
     wx_path = request.json.get("wx_path", read_session(g.sf, my_wxid, "wx_path"))
 
+    if not key:
+        return ReJson(1002, body=f"key is required: {key}")
+    if not wx_path:
+        return ReJson(1002, body=f"wx_path is required: {wx_path}")
+    if not os.path.exists(wx_path):
+        return ReJson(1001, body=f"wx_path not exists: {wx_path}")
+
     outpath = os.path.join(g.tmp_path, "export", my_wxid, "dedb")
     if not os.path.exists(outpath):
         os.makedirs(outpath)
 
-    merge_path = read_session(g.sf, my_wxid, "merge_path")
-    assert isinstance(outpath, str)  # 为了解决pycharm的警告, 无实际意义
-    shutil.copy(merge_path, os.path.join(outpath, os.path.basename(merge_path)))
+    code, merge_save_path = decrypt_merge(wx_path=wx_path, key=key, outpath=outpath)
+    time.sleep(1)
+    if code:
+        return ReJson(0, body=merge_save_path)
+    else:
+        return ReJson(2001, body=merge_save_path)
 
-    return ReJson(0, body=outpath)
+
+@api.route('/api/export_csv', methods=["GET", 'POST'])
+def get_export_csv():
+    """
+    导出csv
+    :return:
+    """
+    my_wxid = read_session(g.sf, "test", "last")
+    if not my_wxid: return ReJson(1001, body="my_wxid is required")
+
+    wxid = request.json.get("wxid")
+    if not wxid:
+        return ReJson(1002, body=f"username is required: {wxid}")
+
+    outpath = os.path.join(g.tmp_path, "export", my_wxid, "csv", wxid)
+    if not os.path.exists(outpath):
+        os.makedirs(outpath)
+
+    code, ret = export_csv(wxid, outpath, read_session(g.sf, my_wxid, "msg_path"))
+    if code:
+        return ReJson(0, ret)
+    else:
+        return ReJson(2001, body=ret)
 
 
 @api.route('/api/export', methods=["GET", 'POST'])

pywxdump/dbpreprocess/__init__.py

@@ -13,6 +13,8 @@ from .parsingMediaMSG import ParsingMediaMSG
 from .parsingOpenIMContact import ParsingOpenIMContact
 from .utils import download_file
 
+from .export.exportCSV import export_csv
+
 
 def get_user_list(MicroMsg_db_path, OpenIMContact_db_path=None, word=None):
     """
@@ -65,7 +67,7 @@ def wxid2userinfo(MicroMsg_db_path, OpenIMContact_db_path, wxid):
     """
     获取联系人信息
     :param MicroMsg_db_path: MicroMsg.db 文件路径
-    :param wxid: 微信id
+    :param wxid: 微信id,可以是单个id，也可以是多个id，使用list传入
     :return: 联系人信息 {wxid: {wxid: wxid, nickname: nickname, remark: remark, account: account, describe: describe, headImgUrl: headImgUrl}}
     """
     # 连接 MicroMsg.db 数据库，并执行查询

pywxdump/dbpreprocess/export/exportCSV.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-#
+# -------------------------------------------------------------------------------
+# Name:         exportCSV.py
+# Description:  
+# Author:       xaoyaoo
+# Date:         2024/04/20
+# -------------------------------------------------------------------------------
+import csv
+import json
+import os
+from ..parsingMSG import ParsingMSG
+
+
+def export_csv(wxid, outpath, msg_path, page_size=5000):
+    if not os.path.exists(outpath):
+        outpath = os.path.join(os.getcwd(), "export" + os.sep + wxid)
+        if not os.path.exists(outpath):
+            os.makedirs(outpath)
+
+    pmsg = ParsingMSG(msg_path)
+
+    count = pmsg.msg_count(wxid)
+    chatCount = count.get(wxid, 0)
+    if chatCount == 0:
+        return False, "没有聊天记录"
+
+    if page_size > chatCount:
+        page_size = chatCount + 1
+
+    for i in range(0, chatCount, page_size):
+        start_index = i
+        data, wxid_list = pmsg.msg_list(wxid, start_index, page_size)
+
+        if len(data) == 0:
+            return False, "没有聊天记录"
+
+        save_path = os.path.join(outpath, f"{wxid}_{i}_{i + page_size}.csv")
+
+        with open(save_path, "w", encoding="utf-8", newline='') as f:
+            csv_writer = csv.writer(f, quoting=csv.QUOTE_MINIMAL)
+
+            csv_writer.writerow(["id", "MsgSvrID", "type_name", "is_sender", "talker", "room_name", "content",
+                                 "CreateTime"])
+            for row in data:
+                id = row.get("id", "")
+                MsgSvrID = row.get("MsgSvrID", "")
+                type_name = row.get("type_name", "")
+                is_sender = row.get("is_sender", "")
+                talker = row.get("talker", "")
+                room_name = row.get("room_name", "")
+                content = row.get("content", "")
+                CreateTime = row.get("CreateTime", "")
+
+                content = json.dumps(content, ensure_ascii=False)
+                csv_writer.writerow([id, MsgSvrID, type_name, is_sender, talker, room_name, content, CreateTime])
+
+    return True, f"导出成功: {outpath}"
+
+
+if __name__ == '__main__':
+    pass

pywxdump/dbpreprocess/parsingMSG.py

@@ -50,7 +50,7 @@ class ParsingMSG(DatabaseBase):
         """
         获取聊天记录数量,根据wxid获取单个联系人的聊天记录数量，不传wxid则获取所有联系人的聊天记录数量
         :param MSG_db_path: MSG.db 文件路径
-        :return: 聊天记录数量列表
+        :return: 聊天记录数量列表 {wxid: chat_count}
         """
         if wxid:
             sql = f"SELECT StrTalker, COUNT(*) FROM MSG WHERE StrTalker='{wxid}';"

pywxdump/dbpreprocess/parsingMicroMsg.py

@@ -42,7 +42,7 @@ class ParsingMicroMsg(DatabaseBase):
     def wxid2userinfo(self, wxid):
         """
         获取单个联系人信息
-        :param wxid: 微信id
+        :param wxid: 微信id,可以是单个id，也可以是id列表
         :return: 联系人信息
         """
         if isinstance(wxid, str):

pywxdump/wx_info/merge_db.py

@@ -291,7 +291,7 @@ def merge_db(db_paths, save_path="merge.db", CreateTime: int = 0, endCreateTime:
 
 def decrypt_merge(wx_path, key, outpath="", CreateTime: int = 0, endCreateTime: int = 0) -> (bool, str):
     """
-    解密合并数据库 msg.db, microMsg.db, media.db
+    解密合并数据库 msg.db, microMsg.db, media.db,注意：会删除原数据库
     :param wx_path: 微信路径 eg: C:\*******\WeChat Files\wxid_*********
     :param key: 解密密钥
     :return: (true,解密后的数据库路径) or (false,错误信息)