From 4b5c758f05acb626b7256ea02d7b5d8b4017d66a Mon Sep 17 00:00:00 2001 From: NFC666 <2954834129@qq.com> Date: Fri, 16 Oct 2026 17:57:56 +0800 Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=20verify=5Fgitea=5Fmath.py?= =?UTF-8?q?=EF=BC=9A=E6=8A=93=20Gitea=20=E9=A1=B5=E9=9D=A2=E6=89=B9?= =?UTF-8?q?=E9=87=8F=E6=A0=B8=E9=AA=8C=E5=85=AC=E5=BC=8F=E6=B8=B2=E6=9F=93?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .workbuddy/tools/md2pdf/verify_gitea_math.py | 36 ++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 .workbuddy/tools/md2pdf/verify_gitea_math.py diff --git a/.workbuddy/tools/md2pdf/verify_gitea_math.py b/.workbuddy/tools/md2pdf/verify_gitea_math.py new file mode 100644 index 0000000..0c7763b --- /dev/null +++ b/.workbuddy/tools/md2pdf/verify_gitea_math.py @@ -0,0 +1,36 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +"""验证 Gitea 网页端的公式渲染情况(抓页面,统计已渲染/残留)。""" +import re +import sys +import urllib.parse +import urllib.request + +BASE = 'https://app.zhantiandoudi.cn/Yimu/MathNotesVersion2/src/branch/main/' +REL = [ + '基于考研的学习/数学一/在学练习/概率论-第3讲-多维随机变量及其分布/01-考点手册.md', + '基于考研的学习/数学一/在学练习/概率论-第3讲-多维随机变量及其分布/03-解析.md', + '基于考研的学习/数学一/在学练习/概率论-第3讲-多维随机变量及其分布/04-答疑笔记.md', + '基于考研的学习/数学一/在学练习/概率论-第3讲-多维随机变量及其分布/06-解析-中高难度.md', + '基于考研的学习/数学一/在学练习/概率论-第5讲-大数定律与中心极限定理/01-考点手册.md', + '基于考研的学习/数学一/在学练习/概率论-第5讲-大数定律与中心极限定理/03-解析.md', + '基于考研的学习/数学一/在学练习/概率论-第6讲-数理统计/01-考点手册.md', + '基于考研的学习/数学一/在学练习/概率论-第6讲-数理统计/03-解析.md', + '基于考研的学习/数学一/每日小练/02-数列-加强版.md', +] + +for rel in REL: + url = BASE + urllib.parse.quote(rel) + req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'}) + try: + html = urllib.request.urlopen(req, timeout=45).read().decode('utf-8') + except Exception as exc: # noqa: BLE001 + print(f'{rel} -> 抓取失败: {exc}') + continue + i = html.find('markup markdown') + body = html[i:] if i > 0 else html + inline = len(re.findall(r'class="language-math">', body)) + disp = len(re.findall(r'class="language-math display">', body)) + raw = len(re.findall(r'\$[^$\n]{0,200}?\$', body)) + mark = 'OK ' if raw == 0 else '!! ' + print(f'{mark}{rel.split("/")[-1]:<22} 行内={inline:<4} 块级={disp:<3} 残留=${raw}')