From 9844b80884adf025f013b2c82d730f3e40f0219f Mon Sep 17 00:00:00 2001 From: jxxghp Date: Sat, 17 Oct 2026 01:18:20 +0800 Subject: [PATCH] refactor(types): govern ipt site parser --- app/modules/indexer/parser/ipt.py | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/app/modules/indexer/parser/ipt.py b/app/modules/indexer/parser/ipt.py index a270a9b39..6dc0f3b8f 100644 --- a/app/modules/indexer/parser/ipt.py +++ b/app/modules/indexer/parser/ipt.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 IptSiteUserInfo(SiteParserBase): + """解析 Ipt 站点的用户资料、流量与消息。""" schema = SiteSchema.Ipt - 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: @@ -41,10 +43,12 @@ class IptSiteUserInfo(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、注册时间及其他资料。""" html = etree.HTML(html_text) try: if not DomUtils.has_child_elements(html): @@ -62,7 +66,8 @@ class IptSiteUserInfo(SiteParserBase): if html is not None: del html - def _parse_user_torrent_seeding_info(self, html_text: str, multi_page: bool = False) -> Optional[str]: + def _parse_user_torrent_seeding_info(self, html_text: str, multi_page: bool = False) -> None: + """读取做种页面数据并返回后续分页入口。""" html = etree.HTML(html_text) try: if not DomUtils.has_child_elements(html): @@ -91,11 +96,14 @@ class IptSiteUserInfo(SiteParserBase): if html is not None: del html - 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