解析Contact表里的ExtraBuf

app/DataBase/hard_link.py

@@ -10,19 +10,19 @@ image_db_lock = threading.Lock()
 video_db_lock = threading.Lock()
 image_db_path = "./app/Database/Msg/HardLinkImage.db"
 video_db_path = "./app/Database/Msg/HardLinkVideo.db"
-root_path = 'FileStorage/MsgAttach/'
+root_path = "FileStorage/MsgAttach/"
-video_root_path = 'FileStorage/Video/'
+video_root_path = "FileStorage/Video/"
 
 
 @log
-def get_md5_from_xml(content, type_='img'):
+def get_md5_from_xml(content, type_="img"):
     try:
         # 解析XML
         root = ET.fromstring(content)
-        if type_ == 'img':
+        if type_ == "img":
             # 提取md5的值
             md5_value = root.find(".//img").get("md5")
-        elif type_ == 'video':
+        elif type_ == "video":
             md5_value = root.find(".//videomsg").get("md5")
         # print(md5_value)
         return md5_value
@@ -30,7 +30,6 @@ def get_md5_from_xml(content, type_='img'):
         return None
 
 
-
 class tencent_struct:
     def __setVals__(self, data, off):
         if data:
@@ -138,7 +137,13 @@ class tencent_struct:
 
     __bytesExtra__ = {
         1: ("", __struct1__),
-        3: ("msg_info_struct", __msgInfo__),
+        3: ("msg_info_struct", "s"),
+    }
+
+    __struct2__ = {1: ("", "s"), 2: ("", "s")}
+
+    __extraBuf__ = {
+        1: ("", __struct2__),
     }
 
     def get_bytesExta_Content(self, data=None, off=0):
@@ -148,6 +153,13 @@ class tencent_struct:
         except:
             raise
 
+    def get_extraBuf_Content(self, data=None, off=0):
+        self.__setVals__(data, off)
+        try:
+            return self.readStruct("__extraBuf__")
+        except:
+            raise
+
     __contenttype__ = {
         "s": __readString,
         "I": __readUleb,
@@ -163,6 +175,74 @@ def parseBytes(content: bytes):
         pass
 
 
+def parseExtraBuf(content: bytes):
+    try:
+        extraBuf = tencent_struct().get_extraBuf_Content(content)
+        return extraBuf
+    except:
+        pass
+
+
+def decodeExtraBuf(extra_buf_content: bytes):
+    off = 0
+    types = [b"\x04", b"\x18", b"\x17", b"\x02", b"\x05"]
+    trunkName = {
+        "46CF10C4": "个性签名",
+        "A4D9024A": "国家",
+        "E2EAA8D1": "省份",
+        "1D025BBF": "市",
+        "81AE19B4": "朋友圈背景url",
+        "F917BCC0": "公司名称",
+        "4EB96D85": "企业微信属性",
+        "0E719F13": "备注图片",
+        "759378AD": "手机号",
+    }
+    res = {}
+    while off < len(extra_buf_content):
+        length = 4  # 块头
+        trunk_head = extra_buf_content[off : off + length]
+        off += length
+        trunk_head = binascii.hexlify(trunk_head).decode().upper()
+        if trunk_head in trunkName:
+            trunk_head = trunkName[trunk_head]
+        res[trunk_head] = {}
+        char = extra_buf_content[off : off + 1]
+        off += 1
+        field = binascii.hexlify(char).decode()
+        if char == b"\x04":  # 四个字节的int，小端序
+            length = 4
+            intContent = extra_buf_content[off : off + length]
+            off += 4
+            intContent = int.from_bytes(intContent, "little")
+            res[trunk_head][field] = intContent
+        elif char == b"\x18":  # utf-16字符串
+            length = 4
+            lengthContent = extra_buf_content[off : off + length]
+            off += 4
+            lengthContent = int.from_bytes(lengthContent, "little")
+            strContent = extra_buf_content[off : off + lengthContent]
+            off += lengthContent
+            res[trunk_head][field] = strContent.decode("utf-16").rstrip("\x00")
+        elif char == b"\x17":  # utf-8 protobuf
+            length = 4
+            lengthContent = extra_buf_content[off : off + length]
+            off += 4
+            lengthContent = int.from_bytes(lengthContent, "little")
+            strContent = extra_buf_content[off : off + lengthContent]
+            off += lengthContent
+            res[trunk_head][field] = parseExtraBuf(strContent)
+        elif char == b"\x02":  # 一个字节的int
+            content = extra_buf_content[off : off + 1]
+            off += 1
+            res[trunk_head][field] = int.from_bytes(content, "little")
+        elif char == b"\x05":  # 暂时不知道有啥用，固定8个字节
+            length = 8
+            content = extra_buf_content[off : off + length]
+            off += length
+            res[trunk_head][field] = int.from_bytes(content, "little")
+    return res
+
+
 def singleton(cls):
     _instance = {}
 
@@ -206,13 +286,13 @@ class HardLink:
             return None
         if not self.open_flag:
             return None
-        sql = '''
+        sql = """
             select Md5Hash,MD5,FileName,HardLinkImageID.Dir as DirName1,HardLinkImageID2.Dir as DirName2
             from HardLinkImageAttribute
             join HardLinkImageID on HardLinkImageAttribute.DirID1 = HardLinkImageID.DirID
             join HardLinkImageID as HardLinkImageID2 on HardLinkImageAttribute.DirID2 = HardLinkImageID2.DirID
             where MD5 = ?;
-            '''
+            """
         try:
             image_db_lock.acquire(True)
             try:
@@ -230,12 +310,12 @@ class HardLink:
             return None
         if not self.open_flag:
             return None
-        sql = '''
+        sql = """
             select Md5Hash,MD5,FileName,HardLinkVideoID2.Dir as DirName2
             from HardLinkVideoAttribute
             join HardLinkVideoID as HardLinkVideoID2 on HardLinkVideoAttribute.DirID2 = HardLinkVideoID2.DirID
             where MD5 = ?;
-            '''
+            """
         try:
             video_db_lock.acquire(True)
             try:
@@ -252,8 +332,8 @@ class HardLink:
         bytesDict = parseBytes(bytesExtra)
         for msginfo in bytesDict[3]:
             if msginfo[1][1][1] == (3 if thumb else 4):
-                pathh = msginfo[1][2][1] # wxid\FileStorage\...
+                pathh = msginfo[1][2][1]  # wxid\FileStorage\...
-                pathh = "\\".join(pathh.split('\\')[1:])
+                pathh = "\\".join(pathh.split("\\")[1:])
                 return pathh
         md5 = get_md5_from_xml(content)
         if not md5:
@@ -264,7 +344,7 @@ class HardLink:
             dir1 = result[3]
             dir2 = result[4]
             data_image = result[2]
-            dir0 = 'Thumb' if thumb else 'Image'
+            dir0 = "Thumb" if thumb else "Image"
             dat_image = os.path.join(root_path, dir1, dir0, dir2, data_image)
             return dat_image
 
@@ -272,16 +352,16 @@ class HardLink:
         bytesDict = parseBytes(bytesExtra)
         for msginfo in bytesDict[3]:
             if msginfo[1][1][1] == (3 if thumb else 4):
-                pathh = msginfo[1][2][1] # wxid\FileStorage\...
+                pathh = msginfo[1][2][1]  # wxid\FileStorage\...
-                pathh = "\\".join(pathh.split('\\')[1:])
+                pathh = "\\".join(pathh.split("\\")[1:])
                 return pathh
-        md5 = get_md5_from_xml(content, type_='video')
+        md5 = get_md5_from_xml(content, type_="video")
         if not md5:
             return None
         result = self.get_video_by_md5(binascii.unhexlify(md5))
         if result:
             dir2 = result[3]
-            data_image = result[2].split('.')[0] + '.jpg' if thumb else result[2]
+            data_image = result[2].split(".")[0] + ".jpg" if thumb else result[2]
             # dir0 = 'Thumb' if thumb else 'Image'
             dat_image = os.path.join(video_root_path, dir2, data_image)
             return dat_image
@@ -304,8 +384,8 @@ class HardLink:
 
 # 6b02292eecea118f06be3a5b20075afc_t
 
-if __name__ == '__main__':
+if __name__ == "__main__":
-    msg_root_path = './Msg/'
+    msg_root_path = "./Msg/"
     image_db_path = "./Msg/HardLinkImage.db"
     video_db_path = "./Msg/HardLinkVideo.db"
     hard_link_db = HardLink()
@@ -315,10 +395,10 @@ if __name__ == '__main__':
     # print(hard_link_db.get_image(content, thumb=False))
     # result = get_md5_from_xml(content)
     # print(result)
-    content = '''<?xml version="1.0"?>
+    content = """<?xml version="1.0"?>
 <msg>
 	<videomsg aeskey="d635d2013d221dbd05a4eab3a8185f5a" cdnvideourl="3057020100044b304902010002040297cead02032f540502042ba7b4de020465673b74042438316562356530652d653764352d343263632d613531642d6464383661313330623965330204052400040201000405004c537500" cdnthumbaeskey="d635d2013d221dbd05a4eab3a8185f5a" cdnthumburl="3057020100044b304902010002040297cead02032f540502042ba7b4de020465673b74042438316562356530652d653764352d343263632d613531642d6464383661313330623965330204052400040201000405004c537500" length="25164270" playlength="60" cdnthumblength="7419" cdnthumbwidth="1920" cdnthumbheight="1080" fromusername="wxid_yt67eeoo4blm22" md5="95558f0e503651375b475636519d2285" newmd5="4ece19bcd92dc5b93b83f397461a1310" isplaceholder="0" rawmd5="d660ba186bb31126d94fa568144face8" rawlength="143850007" cdnrawvideourl="3052020100044b30490201000204d8cd585302032f540502040f6a42b7020465673b85042464666462306634342d653339342d343232302d613534392d3930633030646236306266610204059400040201000400" cdnrawvideoaeskey="5915b14ac8d121e0944d9e444aebb7ed" overwritenewmsgid="0" originsourcemd5="a1a567d8c170bca33d075b787a60dd3f" isad="0" />
 </msg>
-'''
+"""
     print(hard_link_db.get_video(content))
     print(hard_link_db.get_video(content, thumb=True))