From 4fb2e158810232cc4f65c5df430fb1dc31ec81e0 Mon Sep 17 00:00:00 2001
From: "Milena T. Bagdasarian" <milena.bagdasarian@hhi.fraunhofer.de>
Date: Tue, 3 Sep 2024 14:00:03 +0200
Subject: [PATCH] check for HTML Tag and remove them for LaTeX

---
 data_extraction/latex/build_latex.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/data_extraction/latex/build_latex.py b/data_extraction/latex/build_latex.py
index 9651e9a..c0b7723 100644
--- a/data_extraction/latex/build_latex.py
+++ b/data_extraction/latex/build_latex.py
@@ -7,6 +7,7 @@
 import io
 from decimal import Decimal
 import shutil
+import re
 
 methodsdir = "../../methods"
 imagedir = "../../project-page/static/images/"
@@ -208,6 +209,9 @@ def extract_title_and_text(markdown: str):
     # Who puts hashtags in a title anyway?
     title = lines[0].replace("#", "").strip()
     text = "\n".join(lines[1:]).strip()
+    # check for html
+    clean = re.compile("<.*?>")
+    text = re.sub(clean, "", text)
     return title, text