From 8de055c73e976be3e09087dd99f3ecbfb8bab937 Mon Sep 17 00:00:00 2001 From: jxxghp Date: Sat, 17 Oct 2026 01:18:10 +0800 Subject: [PATCH] refactor(types): govern discuz site parser --- app/modules/indexer/parser/discuz.py | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/app/modules/indexer/parser/discuz.py b/app/modules/indexer/parser/discuz.py index 9a0e7c55f..d12e44082 100644 --- a/app/modules/indexer/parser/discuz.py +++ b/app/modules/indexer/parser/discuz.py @@ -8,13 +8,15 @@ from app.foundation import size as size_tools from app.foundation import temporal as time_tools from app.foundation import text as text_tools from app.foundation.dom import DomUtils -from app.modules.indexer.parser import SiteParserBase, SiteSchema +from app.modules.indexer.parser import SitePage, SiteParserBase, SiteSchema class DiscuzUserInfo(SiteParserBase): + """解析 Discuz 站点的用户资料、流量与消息。""" schema = SiteSchema.DiscuzX - def _parse_user_base_info(self, html_text: str): + def _parse_user_base_info(self, html_text: SitePage) -> None: + """解析站点用户身份和页面提供的基础统计。""" html_text = self._prepare_html_text(html_text) html = etree.HTML(html_text) try: @@ -30,10 +32,11 @@ class DiscuzUserInfo(SiteParserBase): if html is not None: del html - def _parse_site_page(self, html_text: str): + def _parse_site_page(self, html_text: SitePage) -> None: + """该站点在其他解析入口处理此数据，本入口不追加操作。""" pass - def _parse_user_detail_info(self, html_text: str): + def _parse_user_detail_info(self, html_text: str) -> None: """ 解析用户等级、加入时间、积分和流量信息 :param html_text: @@ -133,11 +136,14 @@ class DiscuzUserInfo(SiteParserBase): return next_page - def _parse_user_traffic_info(self, html_text: str): + def _parse_user_traffic_info(self, html_text: str) -> None: + """该站点在其他解析入口处理此数据，本入口不追加操作。""" pass - def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]: + def _parse_message_unread_links(self, html_text: str, msg_links: list[str]) -> Optional[str]: + """收集未读消息链接，返回仍需读取的下一页。""" return None - def _parse_message_content(self, html_text): + def _parse_message_content(self, html_text: str) -> tuple[Optional[str], Optional[str], Optional[str]]: + """解析消息标题、日期和正文；无独立消息页时返回空结果。""" return None, None, None