Merge remote-tracking branch 'refs/remotes/cllcode/master' into feature/20240629

README.md

@@ -14,8 +14,6 @@
 [![PyPI-Downloads](https://img.shields.io/pypi/dm/pywxdump)](https://pypistats.org/packages/pywxdump)
 [![GitHub license](https://img.shields.io/pypi/l/pywxdump)](https://github.com/xaoyaoo/PyWxDump/blob/master/LICENSE)
 
-V3.0.* 有很多bug，如果你有问题，请使用V2.4.71版本，或者等待后续版本（发现bug请提交issue）
-
 * Welcome to provide more ideas or code to improve this project together.
 
 ### If you are a novice, please pay attention to the Official Accounts: `逍遥之芯` (the QR code is below), and reply: `PyWxDump` to get a picture text tutorial.

doc/CHANGELOG.md

@@ -1,5 +1,20 @@
-## v3.0.36.(待发布)
+## v3.0.38.(待发布)
 
+- 
+
+## v3.0.37
+
+- 增加公众号消息显示
+- fix and add
+- add (分享)卡片式链接 解析
+- UPDATE CHANGELOG.md
+- release_new_version
+
+## v3.0.36
+
+- fix
+- Update README.md
+- add wx 3.9.11.19
 - UPDATE CHANGELOG.md
 
 ## v3.0.35

pywxdump/__init__.py

@@ -13,7 +13,7 @@ from .wx_info import merge_copy_db, merge_msg_db, merge_media_msg_db, merge_db,
     all_merge_real_time_db
 from .analyzer import DBPool
 from .dbpreprocess import get_user_list, get_recent_user_list, wxid2userinfo, ParsingMSG, ParsingMicroMsg, \
-    ParsingMediaMSG, ParsingOpenIMContact, ParsingFavorite
+    ParsingMediaMSG, ParsingOpenIMContact, ParsingFavorite,ParsingPublicMsg
 from .server import start_falsk
 import os, json
 
@@ -28,4 +28,4 @@ except:
 # PYWXDUMP_ROOT_PATH = os.path.dirname(__file__)
 # db_init = DBPool("DBPOOL_INIT")
 
-__version__ = "3.0.35"
+__version__ = "3.0.37"

pywxdump/api/api.py

@@ -28,7 +28,7 @@ from pywxdump.api.utils import read_session, get_session_wxids, save_session, er
 from pywxdump import read_info, VERSION_LIST, batch_decrypt, BiasAddr, merge_db, decrypt_merge, merge_real_time_db
 
 from pywxdump.dbpreprocess import wxid2userinfo, ParsingMSG, get_user_list, get_recent_user_list, ParsingMediaMSG, \
-    download_file, export_csv, export_json, ParsingMicroMsg
+    download_file, export_csv, export_json, ParsingMicroMsg, ParsingPublicMsg
 from pywxdump.dbpreprocess.utils import dat2img
 
 # app = Flask(__name__, static_folder='../ui/web/dist', static_url_path='/')
@@ -316,6 +316,8 @@ def msg_count():
     if not my_wxid: return ReJson(1001, body="my_wxid is required")
     merge_path = read_session(g.sf, my_wxid, "merge_path")
     chat_count = ParsingMSG(merge_path).msg_count(wxid)
+    if None in chat_count:
+        chat_count = ParsingPublicMsg(merge_path).msg_count(wxid)
     return ReJson(0, chat_count)
 
 
@@ -412,6 +414,9 @@ def get_msgs():
 
     parsing_msg = ParsingMSG(merge_path)
     msgs, wxid_list = parsing_msg.msg_list(wxid, start, limit)
+    if not msgs:
+        parsing_public_msg = ParsingPublicMsg(merge_path)
+        msgs, wxid_list = parsing_public_msg.msg_list(wxid, start, limit)
     wxid_list.append(my_wxid)
     user_list = wxid2userinfo(merge_path, merge_path, wxid_list)
     return ReJson(0, {"msg_list": msgs, "user_list": user_list})

pywxdump/dbpreprocess/__init__.py

@@ -12,6 +12,7 @@ from .parsingMSG import ParsingMSG
 from .parsingMicroMsg import ParsingMicroMsg
 from .parsingMediaMSG import ParsingMediaMSG
 from .parsingOpenIMContact import ParsingOpenIMContact
+from .parsingPublicMsg import ParsingPublicMsg
 from .utils import download_file
 
 from .export.exportCSV import export_csv

pywxdump/dbpreprocess/parsingMSG.py

@@ -341,7 +341,8 @@ class ParsingMSG(DatabaseBase):
         """
         获取单条消息详情,格式化输出
         """
-        localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType, CreateTime, MsgSvrID, DisplayContent, CompressContent, BytesExtra, id = row
+        (localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType, CreateTime, MsgSvrID,
+         DisplayContent, CompressContent, BytesExtra, id) = row
         CreateTime = timestamp2str(CreateTime)
 
         type_id = (Type, SubType)
@@ -416,6 +417,16 @@ class ParsingMSG(DatabaseBase):
             file_name = os.path.basename(url)
             content["msg"] = file_name
 
+        elif type_id == (49, 5):  # (分享)卡片式链接
+            CompressContent = self.decompress_CompressContent(CompressContent)
+            CompressContent_tmp = xml2dict(CompressContent)
+            appmsg = CompressContent_tmp.get("appmsg", {})
+            title = appmsg.get("title", "")
+            des = appmsg.get("des", "")
+            url = appmsg.get("url", "")
+            content["msg"] = f"{title}\n{des}\n\n{url}"
+            content["src"] = url
+
         elif type_id == (49, 19):  # 合并转发的聊天记录
             CompressContent = self.decompress_CompressContent(CompressContent)
             content_tmp = xml2dict(CompressContent)

pywxdump/dbpreprocess/parsingPublicMsg.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-#
+# -------------------------------------------------------------------------------
+# Name:         parsingPublicMsg.py
+# Description:  
+# Author:       xaoyaoo
+# Date:         2024/07/03
+# -------------------------------------------------------------------------------
+
+# -*- coding: utf-8 -*-#
+# -------------------------------------------------------------------------------
+# Name:         parsingMSG.py
+# Description:
+# Author:       xaoyaoo
+# Date:         2024/04/15
+# -------------------------------------------------------------------------------
+import json
+import os
+import re
+from typing import Union, Tuple
+
+import pandas as pd
+
+from .dbbase import DatabaseBase
+from .parsingMSG import ParsingMSG
+from .utils import get_md5, name2typeid, typeid2name, type_converter, timestamp2str, xml2dict, match_BytesExtra
+import lz4.block
+import blackboxprotobuf
+
+
+class ParsingPublicMsg(ParsingMSG):
+    _class_name = "PublicMSG"
+
+    def msg_count(self, wxid: str = ""):
+        """
+        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 {wxid: chat_count}
+        """
+        if wxid:
+            sql = f"SELECT StrTalker, COUNT(*) FROM PublicMsg WHERE StrTalker='{wxid}';"
+        else:
+            sql = f"SELECT StrTalker, COUNT(*) FROM PublicMsg GROUP BY StrTalker ORDER BY COUNT(*) DESC;"
+
+        result = self.execute_sql(sql)
+        if not result:
+            return {}
+        df = pd.DataFrame(result, columns=["wxid", "msg_count"])
+        # # 排序
+        df = df.sort_values(by="msg_count", ascending=False)
+        # chat_counts ： {wxid: chat_count}
+        chat_counts = df.set_index("wxid").to_dict()["msg_count"]
+        return chat_counts
+
+    def msg_count_total(self):
+        """
+        获取聊天记录总数
+        :return: 聊天记录总数
+        """
+        sql = "SELECT COUNT(*) FROM PublicMsg;"
+        result = self.execute_sql(sql)
+        if result and len(result) > 0:
+            chat_counts = result[0][0]
+            return chat_counts
+        return 0
+
+
+    def msg_list(self, wxid="", start_index=0, page_size=500, msg_type: str = ""):
+        sql = (
+            "SELECT localId, IsSender, StrContent, StrTalker, Sequence, Type, SubType, CreateTime, MsgSvrID, "
+            "DisplayContent, CompressContent, BytesExtra, ROW_NUMBER() OVER (ORDER BY CreateTime ASC) AS id "
+            "FROM PublicMsg WHERE 1==1 "
+            "ORDER BY CreateTime ASC LIMIT ?, ?"
+        )
+        params = [start_index, page_size]
+        if msg_type:
+            sql = sql.replace("ORDER BY CreateTime ASC LIMIT ?, ?",
+                              f"AND Type=? ORDER BY CreateTime ASC LIMIT ?,?")
+            params = [msg_type] + params
+
+        if wxid:
+            sql = sql.replace("WHERE 1==1", f"WHERE StrTalker=? ")
+            params = [wxid] + params
+        params = tuple(params)
+        result1 = self.execute_sql(sql, params)
+        if not result1:
+            return [], []
+        data = []
+        wxid_list = []
+        for row in result1:
+            tmpdata = self.msg_detail(row)
+            wxid_list.append(tmpdata["talker"])
+            data.append(tmpdata)
+        wxid_list = list(set(wxid_list))
+        return data, wxid_list

pywxdump/version_list.json

@@ -390,5 +390,12 @@
     93550168,
     0,
     93551632
+  ],
+  "3.9.11.19": [
+    93550296,
+    93551632,
+    93550104,
+    0,
+    93551568
   ]
 }

pywxdump/wx_info/get_wx_info.py

@@ -408,7 +408,7 @@ def get_core_db(wx_path: str, db_type: list = None) -> [str]:
     """
     if not os.path.exists(wx_path):
         return False, f"[-] 目录不存在: {wx_path}"
-    db_type_all = ["MSG", "MediaMSG", "MicroMsg", "OpenIMContact", "OpenIMMedia", "OpenIMMsg", "Favorite"]
+    db_type_all = ["MSG", "MediaMSG", "MicroMsg", "OpenIMContact", "OpenIMMedia", "OpenIMMsg", "Favorite", "PublicMsg"]
 
     if not db_type:
         db_type = db_type_all

pywxdump/wx_info/merge_db.py

@@ -14,6 +14,7 @@ import subprocess
 import time
 from typing import List
 
+
 def merge_copy_db(db_path, save_path):
     if isinstance(db_path, list) and len(db_path) == 1:
         db_path = db_path[0]
@@ -299,7 +300,8 @@ def merge_db(db_paths, save_path="merge.db", CreateTime: int = 0, endCreateTime:
     return save_path
 
 
-def decrypt_merge(wx_path, key, outpath="", CreateTime: int = 0, endCreateTime: int = 0, db_type: List[str] = []) -> (bool, str):
+def decrypt_merge(wx_path, key, outpath="", CreateTime: int = 0, endCreateTime: int = 0, db_type: List[str] = []) -> (
+bool, str):
     """
     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_*********
@@ -319,7 +321,8 @@ def decrypt_merge(wx_path, key, outpath="", CreateTime: int = 0, endCreateTime:
     # 分割wx_path的文件名和父目录
     msg_dir = os.path.dirname(wx_path)
     my_wxid = os.path.basename(wx_path)
-    db_type_set: set[str] = {"MSG", "MediaMSG", "MicroMsg", "OpenIMContact", "OpenIMMedia", "OpenIMMsg", "Favorite"}
+    db_type_set: set[str] = {"MSG", "MediaMSG", "MicroMsg", "OpenIMContact", "OpenIMMedia", "OpenIMMsg", "Favorite",
+                             "PublicMsg"}
     if len(db_type) == 0:
         db_type = list(db_type_set)
     else:

tests/release_new_version.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-#
+# -------------------------------------------------------------------------------
+# Name:         release_new_version.py
+# Description:  
+# Author:       xaoyaoo
+# Date:         2024/07/02
+# -------------------------------------------------------------------------------
+import os
+import sys
+import time
+
+# 获取当前文件所在目录
+current_path = os.path.dirname(os.path.abspath(__file__))
+PyWxDump_path = os.path.dirname((current_path))
+os.chdir(PyWxDump_path)
+version_path = os.path.join(PyWxDump_path, "pywxdump", "__init__.py")
+
+# 读取版本号 pywxdump/__init__.py 中的 __version__
+with open(version_path, "r", encoding="utf-8") as f:
+    for line in f.readlines():
+        if line.startswith("__version__"):
+            version = line.split("=")[-1].strip().strip("\"'")
+            break
+    else:
+        raise RuntimeError("version not found")
+
+# print("PyWxDump_path", PyWxDump_path)
+# print("version", version)
+print(f"git tag -a v{version} -m 'v{version} release'")
+os.system(f"git tag -a v{version} -m 'v{version}'")
+time.sleep(1)
+os.system(f"git push origin v{version}")