From 361f9d0bbebe773fd5934f27be8b5b1d92da8aec Mon Sep 17 00:00:00 2001
From: RGalyaviev <ruslan@ipcom.su>
Date: Thu, 4 Sep 2025 08:54:48 +0300
Subject: [PATCH] PDF export: sanitize HTML (remove <style>, style attributes,
 <script>) to avoid xhtml2pdf font-size error

---
 app.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/app.py b/app.py
index 351ee2f..0a2b03e 100644
--- a/app.py
+++ b/app.py
@@ -16,6 +16,7 @@ from flask import (
     Response,
 )
 from io import BytesIO
+import re
 from xhtml2pdf import pisa  # type: ignore
 from docx import Document  # type: ignore
 from htmldocx import HtmlToDocx  # type: ignore
@@ -268,6 +269,13 @@ def create_app():
             abort(404)
         return row
 
+    def _sanitize_html_for_pdf(html: str) -> str:
+        # xhtml2pdf плохо переносит современный CSS; вычищаем стили/скрипты
+        html = re.sub(r"<style[^>]*>.*?</style>", "", html, flags=re.I | re.S)
+        html = re.sub(r"\sstyle=(\"|\')(.*?)\1", "", html, flags=re.I | re.S)
+        html = re.sub(r"<script[^>]*>.*?</script>", "", html, flags=re.I | re.S)
+        return html
+
     def _wrap_html_for_export(title: str, html: str) -> str:
         head_title = f"<title>{title}</title>" if title else ""
         return (
@@ -280,7 +288,8 @@ def create_app():
     def export_pdf(uid: str):
         row = _fetch_page(uid)
         title = row["title"] or f"page-{uid[:8]}"
-        html_doc = _wrap_html_for_export(title, row["html"]) 
+        cleaned = _sanitize_html_for_pdf(row["html"])
+        html_doc = _wrap_html_for_export(title, cleaned)
         out = BytesIO()
         pisa.CreatePDF(src=html_doc, dest=out)
         out.seek(0)