liuwei_x_x/abot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

对消息进行格式化

Browse Source
This commit is contained in:
liuwei
2025-04-01 15:43:34 +08:00
parent 59898621f5
commit b0c66104f1
1 changed files with 40 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
utils/message_formatter.py
View File

@@ -1,5 +1,6 @@
import xml.etree.ElementTree as ET
import html
import re
def format_quote_message(xml_content):
@@ -13,26 +14,47 @@ def format_quote_message(xml_content):
格式化后的消息文本
"""
try:
# 解析XML
root = ET.fromstring(xml_content)
# 获取主消息内容
title_elem = root.find('.//title')
main_content = title_elem.text if title_elem is not None else ""
# 获取引用消息信息
refer_msg = root.find('.//refermsg')
if refer_msg is not None:
display_name = refer_msg.find('displayname').text if refer_msg.find('displayname') is not None else "未知用户"
quoted_content = refer_msg.find('content').text if refer_msg.find('content') is not None else ""
# 解码HTML实体
xml_content = xml_content.replace('&lt;', '<').replace('&gt;', '>')
print(xml_content)
# 使用正则表达式直接提取关键信息，避免XML解析问题
title_match = re.search(r'<title>(.*?)</title>', xml_content)
main_content = title_match.group(1) if title_match else "[无标题]"
# 提取引用消息的发送者和内容
display_name_match = re.search(r'<displayname>(.*?)</displayname>', xml_content)
display_name = display_name_match.group(1) if display_name_match else "未知用户"
quoted_content_match = re.search(r'<refermsg>.*?<content>(.*?)</content>', xml_content, re.DOTALL)
quoted_content = quoted_content_match.group(1) if quoted_content_match else ""
# 解码HTML实体
try:
quoted_content = html.unescape(quoted_content)
# 构建格式化的引用消息
except:
pass # 如果解码失败，使用原始内容
# 构建格式化的引用消息
if display_name and quoted_content:
formatted_message = f"┌─────────────────────────────────\n│ 引用 {display_name}：{quoted_content}\n└─────────────────────────────────\n{main_content}"
return formatted_message
return main_content
except Exception as e:
return f"解析引用消息失败: {str(e)}"
# 如果解析失败，尝试提取title标签内容
try:
match = re.search(r'<title>(.*?)</title>', xml_content)
if match:
return match.group(1)
except:
pass
return f"[引用消息]" # 返回一个简单的标识，而不是错误信息
if __name__ == '__main__':
strs ="""
<?xml version="1.0"?> <msg> <appmsg appid="" sdkver="0"> <title>那也没事，都是富二代，都是送出国镀个金回家继承家业的</title> <des /> <action /> <type>57</type> <showtype>0</showtype> <soundtype>0</soundtype> <mediatagname /> <messageext /> <messageaction /> <content /> <contentattr>0</contentattr> <url /> <lowurl /> <dataurl /> <lowdataurl /> <songalbumurl /> <songlyric /> <appattach> <totallen>0</totallen> <attachid /> <emoticonmd5></emoticonmd5> <fileext /> <aeskey></aeskey> </appattach> <extinfo /> <sourceusername /> <sourcedisplayname /> <thumburl /> <md5 /> <statextstr /> <refermsg> <type>1</type> <svrid>2568355911763278189</svrid> <fromusr>45317011307@chatroom</fromusr> <chatusr>wxid_twrbhdxddlud12</chatusr> <displayname>水牛🐃</displayname> <content>都是富二代。</content> <msgsource>&lt;msgsource&gt; &lt;sec_msg_node&gt; &lt;alnode&gt; &lt;fr&gt;1&lt;/fr&gt; &lt;/alnode&gt; &lt;/sec_msg_node&gt; &lt;pua&gt;1&lt;/pua&gt; &lt;silence&gt;1&lt;/silence&gt; &lt;membercount&gt;125&lt;/membercount&gt; &lt;signature&gt;N0_V1_DaX/Y3s2|v1_PvH3m56P&lt;/signature&gt; &lt;tmp_node&gt; &lt;publisher-id&gt;&lt;/publisher-id&gt; &lt;/tmp_node&gt; &lt;/msgsource&gt; </msgsource> <createtime>1743491847</createtime> </refermsg> </appmsg> <fromusername>maoyijie</fromusername> <scene>0</scene> <appinfo> <version>1</version> <appname /> </appinfo> <commenturl /> </msg>
"""
sss = format_quote_message(strs)
print(sss)