125 lines
6.0 KiB
Python
125 lines
6.0 KiB
Python
import xml.etree.ElementTree as ET
|
||
import html
|
||
import re
|
||
|
||
|
||
def _clean_text(value: str) -> str:
|
||
if not value:
|
||
return ""
|
||
value = html.unescape(value)
|
||
value = re.sub(r"<br\s*/?>", "\n", value, flags=re.IGNORECASE)
|
||
value = re.sub(r"<[^>]+>", "", value)
|
||
return value.strip()
|
||
|
||
|
||
def _extract_first(pattern: str, text: str, default: str = "") -> str:
|
||
match = re.search(pattern, text, re.DOTALL | re.IGNORECASE)
|
||
return match.group(1) if match else default
|
||
|
||
|
||
def _format_referenced_content(ref_type: str, quoted_content: str, xml_content: str) -> str:
|
||
cleaned = _clean_text(quoted_content)
|
||
lower_xml = (quoted_content or "") + (xml_content or "")
|
||
lower_xml = lower_xml.lower()
|
||
|
||
if ref_type in {"3"} or "<img" in lower_xml or "cdnthumburl" in lower_xml:
|
||
return "[图片]"
|
||
if ref_type in {"43", "62"} or "<videomsg" in lower_xml or "cdnvideourl" in lower_xml:
|
||
return "[视频]"
|
||
if ref_type in {"47", "1048625", "1090519089"} or "<emoji" in lower_xml or "<emoticonmd5>" in lower_xml:
|
||
return "[表情]"
|
||
if ref_type in {"34"} or "<voicemsg" in lower_xml:
|
||
return "[语音]"
|
||
if ref_type in {"48"} or "<location" in lower_xml:
|
||
return "[位置]"
|
||
if ref_type in {"49"}:
|
||
title = _extract_first(r"<title>(.*?)</title>", quoted_content) or _extract_first(r"<title>(.*?)</title>", xml_content)
|
||
title = _clean_text(title)
|
||
return f"[链接] {title}" if title else "[链接]"
|
||
|
||
if cleaned:
|
||
return cleaned
|
||
return "[消息]"
|
||
|
||
|
||
def _extract_media_preview(ref_type: str, quoted_content: str) -> dict:
|
||
payload = html.unescape(quoted_content or "")
|
||
preview = {"reference_type": "text", "preview_image": "", "preview_video_thumb": ""}
|
||
|
||
if ref_type in {"3"} or "<img" in payload.lower():
|
||
preview["reference_type"] = "image"
|
||
preview["preview_image"] = (
|
||
_extract_first(r'cdnthumburl="(.*?)"', payload)
|
||
or _extract_first(r"<cdnthumburl><!\[CDATA\[(.*?)\]\]></cdnthumburl>", payload)
|
||
or _extract_first(r"<cdnmidimgurl><!\[CDATA\[(.*?)\]\]></cdnmidimgurl>", payload)
|
||
)
|
||
return preview
|
||
|
||
if ref_type in {"43", "62"} or "<videomsg" in payload.lower():
|
||
preview["reference_type"] = "video"
|
||
preview["preview_video_thumb"] = (
|
||
_extract_first(r'cdnthumburl="(.*?)"', payload)
|
||
or _extract_first(r"<cdnthumburl><!\[CDATA\[(.*?)\]\]></cdnthumburl>", payload)
|
||
)
|
||
return preview
|
||
|
||
if ref_type in {"47", "1048625", "1090519089"} or "<emoji" in payload.lower():
|
||
preview["reference_type"] = "emoji"
|
||
return preview
|
||
|
||
return preview
|
||
|
||
|
||
def parse_quote_message(xml_content: str) -> dict:
|
||
xml_content = xml_content.replace('<', '<').replace('>', '>')
|
||
main_content = _clean_text(_extract_first(r'<title>(.*?)</title>', xml_content, "[无标题]")) or "[无标题]"
|
||
display_name = _clean_text(_extract_first(r'<displayname>(.*?)</displayname>', xml_content, "未知用户")) or "未知用户"
|
||
quoted_content = _extract_first(r'<refermsg>.*?<content>(.*?)</content>', xml_content)
|
||
ref_type = _extract_first(r'<refermsg>.*?<type>(.*?)</type>', xml_content)
|
||
reference_svrid = _extract_first(r'<refermsg>.*?<svrid>(.*?)</svrid>', xml_content)
|
||
pretty_reference = _format_referenced_content(ref_type, quoted_content, xml_content)
|
||
media_preview = _extract_media_preview(ref_type, quoted_content)
|
||
|
||
return {
|
||
"main_content": main_content,
|
||
"display_name": display_name,
|
||
"quoted_content": pretty_reference,
|
||
"reference_svrid": reference_svrid,
|
||
"reference_type": media_preview.get("reference_type", "text"),
|
||
"preview_image": media_preview.get("preview_image", ""),
|
||
"preview_video_thumb": media_preview.get("preview_video_thumb", ""),
|
||
"formatted_message": f"{main_content}\n引用 {display_name}：{pretty_reference}" if display_name and pretty_reference else main_content
|
||
}
|
||
|
||
|
||
def format_quote_message(xml_content):
|
||
"""
|
||
格式化引用消息
|
||
|
||
Args:
|
||
xml_content: XML格式的消息内容
|
||
|
||
Returns:
|
||
格式化后的消息文本
|
||
"""
|
||
try:
|
||
return parse_quote_message(xml_content)["formatted_message"]
|
||
except Exception as 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><msgsource> <sec_msg_node> <alnode> <fr>1</fr> </alnode> </sec_msg_node> <pua>1</pua> <silence>1</silence> <membercount>125</membercount> <signature>N0_V1_DaX/Y3s2|v1_PvH3m56P</signature> <tmp_node> <publisher-id></publisher-id> </tmp_node> </msgsource> </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)
|