补充已过期或丢失文件的处理，添加文件和大小和类型等信息，集中处理一些用到的图标

app/DataBase/exporter_html.py

@@ -12,13 +12,24 @@ from app.DataBase.package_msg import PackageMsg
 from app.log import logger
 from app.person import Me
 from app.util import path
-from app.util.compress_content import parser_reply, share_card, music_share
+from app.util.compress_content import parser_reply, share_card, music_share, file
 from app.util.emoji import get_emoji_url
-from app.util.file import get_file
 from app.util.image import get_image_path, get_image
 from app.util.music import get_music_path
 
 
+icon_files = {
+    './icon/word.png': ['doc', 'docx'],
+    './icon/excel.png': ['xls', 'xlsx'],
+    './icon/csv.png': ['csv'],
+    './icon/txt.png': ['txt'],
+    './icon/zip.png': ['zip', '7z','rar'],
+    './icon/ppt.png': ['ppt', 'pptx'],
+    './icon/pdf.png': ['pdf'],
+}
+
+
+
 class HtmlExporter(ExporterBase):
     def text(self, doc, message):
         type_ = message[2]
@@ -95,20 +106,32 @@ class HtmlExporter(ExporterBase):
     def file(self, doc, message):
         origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{self.contact.remark}"
         bytesExtra = message[10]
+        compress_content = message[11]
         str_time = message[8]
         is_send = message[4]
         timestamp = message[5]
         is_chatroom = 1 if self.contact.is_chatroom else 0
         avatar = self.get_avatar_path(is_send, message)
         display_name = self.get_display_name(is_send, message)
-        link = get_file(bytesExtra, thumb=True, output_path=origin_docx_path + '/file')
+        file_info = file(bytesExtra, compress_content, output_path=origin_docx_path + '/file')
-        file_name = ''
+        if file_info.get('is_error') == False:
-        file_path = './icon/file.png'
+            icon_path = None
-        if link != "":
+            for icon, extensions in icon_files.items():
-            file_name = os.path.basename(link)
+                if file_info.get('file_ext') in extensions:
-            link = './file/' + file_name
+                    icon_path = icon
+                    break
+            # 如果没有与文件后缀匹配的图标，则使用默认图标
+            if icon_path is None:
+                default_icon = './icon/file.png'
+                icon_path = default_icon
+            file_path = file_info.get('file_path')
+            if file_path != "":
+                file_path = './file/' + file_info.get('file_name')
             doc.write(
-            f'''{{ type:49, text: '{file_path}',is_send:{is_send},avatar_path:'{avatar}',timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',link: '{link}',sub_type:6,file_name: '{file_name}'}},'''
+                f'''{{ type:49, text: '{file_path}',is_send:{is_send},avatar_path:'{avatar}',timestamp:{timestamp}
+                            ,is_chatroom:{is_chatroom},displayname:'{display_name}',icon_path: '{icon_path}'
+                            ,sub_type:6,file_name: '{file_info.get('file_name')}',file_size: '{file_info.get('file_len')}'
+                            ,app_name: '{file_info.get('app_name')}'}},'''
             )
 
     def refermsg(self, doc, message):
@@ -200,6 +223,7 @@ class HtmlExporter(ExporterBase):
         timestamp = message[5]
         content = music_share(message[11])
         music_path = ''
+        if content.get('is_error') == False:
             if content.get('audio_url') != '':
                 music_path = get_music_path(content.get('audio_url'), content.get('title'),
                                             output_path=origin_docx_path + '/music')
@@ -209,7 +233,6 @@ class HtmlExporter(ExporterBase):
             is_chatroom = 1 if self.contact.is_chatroom else 0
             avatar = self.get_avatar_path(is_send, message)
             display_name = self.get_display_name(is_send, message)
-        if content.get('is_error') == False:
             doc.write(
                 f'''{{ type:49, text:'{music_path}',is_send:{is_send},avatar_path:'{avatar}',link_url:'{content.get('link_url')}',
                 timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',sub_type:3,title:'{content.get('title')}',

app/DataBase/output.py

@@ -5,6 +5,7 @@ import shutil
 import sys
 import time
 import traceback
+import filecmp
 from re import findall
 
 import docx
@@ -51,21 +52,24 @@ def makedirs(path):
     os.makedirs(os.path.join(path, 'avatar'), exist_ok=True)
     os.makedirs(os.path.join(path, 'music'), exist_ok=True)
     os.makedirs(os.path.join(path, 'icon'), exist_ok=True)
-    file = './app/resources/data/file.png'
+    resource_dir = os.path.join('app', 'resources', 'data', 'icons')
-    if not os.path.exists(file):
+    target_folder = os.path.join(path, 'icon')
-        resource_dir = getattr(sys, '_MEIPASS', os.path.abspath(os.path.dirname(__file__)))
+    # 拷贝一些必备的图标
-        file = os.path.join(resource_dir, 'app', 'resources', 'data', 'file.png')
+    for root, dirs, files in os.walk(resource_dir):
-    shutil.copy(file, path + '/icon/file.png')
+        relative_path = os.path.relpath(root, resource_dir)
-    play_file = './app/resources/data/play.png'
+        target_path = os.path.join(target_folder, relative_path)
-    if not os.path.exists(play_file):
+
-        resource_dir = getattr(sys, '_MEIPASS', os.path.abspath(os.path.dirname(__file__)))
+        # 遍历文件夹中的文件
-        play_file = os.path.join(resource_dir, 'app', 'resources', 'data', 'play.png')
+        for file in files:
-    shutil.copy(play_file, path + '/icon/play.png')
+            source_file_path = os.path.join(root, file)
-    pause_file = './app/resources/data/pause.png'
+            target_file_path = os.path.join(target_path, file)
-    if not os.path.exists(pause_file):
+            if not os.path.exists(target_file_path):
-        resource_dir = getattr(sys, '_MEIPASS', os.path.abspath(os.path.dirname(__file__)))
+                shutil.copy(source_file_path, target_file_path)
-        pause_file = os.path.join(resource_dir, 'app', 'resources', 'data', 'pause.png')
+            else:
-    shutil.copy(pause_file, path + '/icon/pause.png')
+                # 比较文件内容
+                if not filecmp.cmp(source_file_path, target_file_path, shallow=False):
+                    # 文件内容不一致，进行覆盖拷贝
+                    shutil.copy(source_file_path, target_file_path)
 
 
 def escape_js_and_html(input_str):

app/resources/data/template.html

@@ -187,30 +187,7 @@ audio{
     margin-right: 9px;
 }
 
-.chat-file {
+.chat-music-audio, .chat-file{
-    width: 300px;
-    background-color: #fff;
-    margin-right: 20px;
-}
-.chat-file a ,.chat-file div{
-    display: flex;
-    color: #000;
-    outline: none;
-    text-decoration: none;
-    margin: 0 20px 20px 20px;
-}
-.chat-file div{
-    margin: 20px;
-}
-.chat-file a span ,.chat-file div span{
-    /* flex-grow: 1; */
-    width: 200px;
-}
-.chat-file a img,.chat-file div img{
-    width: 100px;
-}
-
-.chat-music-audio {
     width: 300px;
     margin-right: 20px;
     display: flex;
@@ -222,8 +199,11 @@ audio{
     height: 100px;
     margin-left: 10px;
 }
+.chat-file img{
+    width: 50px;
+}
 
-.chat-music-audio .player-box {
+.chat-music-audio .player-box,.chat-file .file-box {
     width: 300px;
     display: flex;
     align-items: center;
@@ -231,43 +211,43 @@ audio{
     height: 80px;
 }
 
-.chat-music-audio .player-original {
+.chat-music-audio .player-original ,.chat-file .app-info{
     border-top: 1px solid #ede3e3;
 }
 
-.chat-music-audio .player-original p {
+.chat-music-audio .player-original p ,.chat-file .app-info p{
     margin-top: 5px;
     color: #888;
 }
 
-.chat-music-audio .player-controls {
+.chat-music-audio .player-controls, .chat-file .file-img{
     display: flex;
     align-items: center;;
 }
 
-.chat-music-audio .flex1 {
+.chat-music-audio .flex1,.chat-file .flex1 {
     flex: 1;
     justify-content: start;
 }
 
-.chat-music-audio .flex2 {
+.chat-music-audio .flex2 ,.chat-file .flex2{
     flex: 2;
     justify-content: end;
 }
 
-.chat-music-audio .player-info {
+.chat-music-audio .player-info ,.chat-file .file-info{
     width: 200px;
     height: 80px;
     white-space: normal;
     flex-basis: 200px;
 }
 
-.chat-music-audio .song-title {
+.chat-music-audio .song-title,.chat-file .file-name {
     font-weight: bold;
     overflow-wrap: break-word;
 }
 
-.chat-music-audio .artist {
+.chat-music-audio .artist ,.chat-file .file-size{
     margin-top: 10px;
     color: #888;
 }
@@ -749,12 +729,26 @@ input {
         function messageFileBox(message) {
             const messageFileTag = document.createElement('div');
             messageFileTag.className = `chat-file`;
-            if (message.link !== ''){
+            messageFileTag.onclick = function (event) {
-                messageFileTag.innerHTML  = `
+                if (message.text !== '') {
-                <a href="${message.link}" target="_blank"><span>${message.file_name}</span><img loading="lazy" src="${message.text}"/></a>`
+                    window.open(message.text, '_blank');
                 }else{
-                messageFileTag.innerHTML = `<div><span>文件已丢失</span><img loading="lazy" src="${message.text}"/></div>`;
+                    alert("文件可能丢失、过期或不存放在该主机上")
                 }
+            }
+            if (message.file_name.length >= 26) {
+                message.file_name = message.file_name.slice(0, 25) + '...'
+            }
+            messageFileTag.innerHTML = `<div class="file-box">
+                    <div class="file-info flex1">
+                        <div class="file-title">${message.file_name}</div>
+                        <div class="file-size">${message.file_size}</div>
+                    </div>
+                    <div class="file-img flex2">
+                        <img src="${message.icon_path}"/>
+                    </div>
+                </div>
+                <div class="app-info"><p>${message.app_name}</p></div>`
             return messageFileTag;
         }
 

app/util/compress_content.py

@@ -4,10 +4,13 @@ import xml.etree.ElementTree as ET
 import lz4.block
 
 import requests
+import re
 from urllib.parse import urlparse
 from bs4 import BeautifulSoup
 
 from app.DataBase.hard_link import parseBytes
+from ..util.file import get_file
+
 
 
 def decompress_CompressContent(data):
@@ -206,3 +209,58 @@ def get_audio_url(url):
     except Exception as e:
         print(f"Get Audio Url Error: {e}")
     return path
+
+
+def file(bytes_extra, compress_content, output_path):
+    xml_content = decompress_CompressContent(compress_content)
+    if not xml_content:
+        return {
+            'type': 6,
+            'title': "发生错误",
+            "is_error": True
+        }
+    try:
+        root = ET.XML(xml_content)
+        appmsg = root.find('appmsg')
+        msg_type = int(appmsg.find('type').text)
+        file_name = appmsg.find('title').text
+        pattern = r'[\\/:*?"<>|\r\n]+'
+        file_name = re.sub(pattern, "_", file_name)
+        appattach = appmsg.find('appattach')
+        file_len = int(appattach.find('totallen').text)
+        app_name = ''
+        file_len = format_bytes(file_len)
+        file_ext = appattach.find('fileext').text
+        if root.find("appinfo") is not None:
+            app_info = root.find('appinfo')
+            app_name = app_info.find('appname').text
+            if app_name is None:
+                app_name = ''
+        file_path = get_file(bytes_extra, file_name, output_path)
+        return {
+            'type': msg_type,
+            'file_name': file_name,
+            'file_len': file_len,
+            'file_ext': file_ext,
+            'file_path': file_path,
+            'app_name': app_name,
+            "is_error": False
+        }
+    except Exception as e:
+        print(f"File Get Info Error: {e}")
+        return {
+            'type': 6,
+            'title': "发生错误",
+            "is_error": True
+        }
+
+
+def format_bytes(size):
+    units = ["B", "KB", "MB", "GB"]
+
+    def convert_bytes(size, unit_index):
+        if size < 1024 or unit_index >= len(units) - 1:
+            return size, unit_index
+        return convert_bytes(size / 1024, unit_index + 1)
+    final_size, final_unit_index = convert_bytes(size, 0)
+    return f"{final_size:.2f} {units[final_unit_index]}"

app/util/file.py

@@ -20,25 +20,21 @@ class File:
         self.open_flag = False
 
 
-def get_file(bytes_extra, thumb=False, output_path=root_path) -> str:
+def get_file(bytes_extra, file_name, output_path=root_path) -> str:
     try:
         msg_bytes = MessageBytesExtra()
         msg_bytes.ParseFromString(bytes_extra)
-        file_original_path = ''
         file_path = ''
-        file_name = ''
         real_path = ''
         if len(msg_bytes.message2) > 0:
-            file_field = msg_bytes.message2[-1].field2
+            for filed in msg_bytes.message2:
-            if file_field.find('sec_msg_node') == -1:
+                if filed.field1 == 4:
-                file_original_path = file_field
+                    file_original_path = filed.field2
-                file_name = os.path.basename(file_original_path)
-                if file_name != '' and file_name != Me().wxid:
                     file_path = os.path.join(output_path, file_name)
                     if os.path.exists(file_path):
-                        print('文件' + file_path + '已存在')
+                        # print('文件' + file_path + '已存在')
                         return file_path
-                    if os.path.isabs(file_original_path):
+                    if os.path.isabs(file_original_path):  # 绝对路径可能迁移过文件目录，也可能存在其他位置
                         if os.path.exists(file_original_path):
                             real_path = file_original_path
                         else:  # 如果没找到再判断一次是否是迁移了目录