K2CrO4/NeoBot
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

refactor(scripts): 重构并优化脚本文件结构

Browse Source 
feat(scripts): 添加Python环境检查脚本
feat(scripts): 增强依赖导出脚本功能
perf(plugins/bili_parser): 优化B站解析器性能和代码结构
style(plugins/bili_parser): 统一代码风格和常量命名
This commit is contained in:
K2cr2O1
2026-01-18 21:01:15 +08:00
parent 03bcded7ed
commit bd8726b768
8 changed files with 319 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
plugins/bili_parser.py
View File

@@ -13,12 +13,16 @@ from models import MessageEvent, MessageSegment
# 创建一个TTL缓存，最大容量100，缓存时间10秒
processed_messages: TTLCache[int, bool] = TTLCache(maxsize=100, ttl=10)
# 插件元数据
__plugin_meta__ = {
"name": "bili_parser",
"description": "自动解析B站分享卡片，提取视频封面和播放量等信息。",
"usage": "（自动触发）当检测到B站小程序分享卡片时，自动发送视频信息。",
}
# 常量定义
BILI_NICKNAME = "B站视频解析"
HEADERS = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
@@ -29,7 +33,7 @@ _session: Optional[aiohttp.ClientSession] = None
async def get_session() -> aiohttp.ClientSession:
global _session
if _session is None or _session.closed:
_session = aiohttp.ClientSession()
_session = aiohttp.ClientSession(headers=HEADERS)
return _session
@@ -71,7 +75,7 @@ async def parse_video_info(video_url: str) -> Optional[Dict[str, Any]]:
if not script_tag or not script_tag.string:
return None
match = re.search(r'window\.__INITIAL_STATE__\s*=\s*(\{.*?\});', script_tag.string)
match = re.search(r'window\.__INITIAL_STATE__\s*=\s*(\{[^\}]*\});', script_tag.string)
if not match:
return None
@@ -135,9 +139,47 @@ async def get_direct_video_url(video_url: str) -> Optional[str]:
logger.error(f"[bili_parser] 调用第三方API解析视频失败: {e}")
return None
BILI_URL_PATTERN = re.compile(r"https?://(?:www\.)?(bilibili\.com/video/[a-zA-Z0-9_]+|b23\.tv/[a-zA-Z0-9]+)")
BILI_URL_PATTERN = re.compile(r"https?://(?:www\.)?(bilibili\.com/video/\w+|b23\.tv/[a-zA-Z0-9]+)")
def extract_url_from_json_segments(segments):
"""
从消息的JSON段中提取B站链接
:param segments: 消息段列表
:return: 提取到的URL或None
"""
for segment in segments:
if segment.type == "json":
logger.info(f"[bili_parser] 检测到JSON CQ码: {segment.data}")
try:
json_data = json.loads(segment.data.get("data", "{}"))
short_url = json_data.get("meta", {}).get("detail_1", {}).get("qqdocurl")
if short_url and "b23.tv" in short_url:
extracted_url = short_url.split('?')[0]
logger.success(f"[bili_parser] 成功从JSON卡片中提取到B站短链接: {extracted_url}")
return extracted_url
except (json.JSONDecodeError, KeyError) as e:
logger.error(f"[bili_parser] 解析JSON失败: {e}")
continue
return None
def extract_url_from_text_segments(segments):
"""
从消息的文本段中提取B站链接
:param segments: 消息段列表
:return: 提取到的URL或None
"""
for segment in segments:
if segment.type == "text":
text_content = segment.data.get("text", "")
match = BILI_URL_PATTERN.search(text_content)
if match:
extracted_url = match.group(0)
logger.success(f"[bili_parser] 成功从文本中提取到B站链接: {extracted_url}")
return extracted_url
return None
@matcher.on_message()
async def handle_bili_share(event: MessageEvent):
"""
@@ -153,34 +195,12 @@ async def handle_bili_share(event: MessageEvent):
if event.user_id == event.self_id:
return
url_to_process = None
# 1. 优先解析JSON卡片中的短链接
for segment in event.message:
if segment.type == "json":
logger.info(f"[bili_parser] 检测到JSON CQ码: {segment.data}")
try:
json_data = json.loads(segment.data.get("data", "{}"))
short_url = json_data.get("meta", {}).get("detail_1", {}).get("qqdocurl")
if short_url and "b23.tv" in short_url:
url_to_process = short_url.split('?')[0]
logger.success(f"[bili_parser] 成功从JSON卡片中提取到B站短链接: {url_to_process}")
break # 找到后立即跳出循环
except (json.JSONDecodeError, KeyError) as e:
logger.error(f"[bili_parser] 解析JSON失败: {e}")
continue
url_to_process = extract_url_from_json_segments(event.message)
# 2. 如果未在JSON卡片中找到链接，则在文本消息中查找
if not url_to_process:
for segment in event.message:
if segment.type == "text":
text_content = segment.data.get("text", "")
match = BILI_URL_PATTERN.search(text_content)
if match:
url_to_process = match.group(0)
logger.success(f"[bili_parser] 成功从文本中提取到B站链接: {url_to_process}")
break # 找到后立即跳出循环
url_to_process = extract_url_from_text_segments(event.message)
# 3. 如果找到了任何类型的B站链接，则进行处理
if url_to_process:
@@ -248,10 +268,10 @@ async def process_bili_link(event: MessageEvent, url: str):
]
nodes = [
event.bot.build_forward_node(user_id=event.self_id, nickname="B站视频解析", message=text_message),
event.bot.build_forward_node(user_id=event.self_id, nickname="B站视频解析", message=image_message_segment),
event.bot.build_forward_node(user_id=event.self_id, nickname="B站视频解析", message=up_info_segment),
event.bot.build_forward_node(user_id=event.self_id, nickname="B站视频解析", message=video_message)
event.bot.build_forward_node(user_id=event.self_id, nickname=BILI_NICKNAME, message=text_message),
event.bot.build_forward_node(user_id=event.self_id, nickname=BILI_NICKNAME, message=image_message_segment),
event.bot.build_forward_node(user_id=event.self_id, nickname=BILI_NICKNAME, message=up_info_segment),
event.bot.build_forward_node(user_id=event.self_id, nickname=BILI_NICKNAME, message=video_message)
]
logger.success(f"[bili_parser] 成功解析视频信息并准备以聊天记录形式回复: {video_info['title']}")