From 8619b7b9242791032d3bcc7f353a2790b9bc5d79 Mon Sep 17 00:00:00 2001
From: Alexander Schlemmer <a.schlemmer@indiscale.com>
Date: Tue, 20 Aug 2024 17:54:31 +0200
Subject: [PATCH] ENH: improved handling of non-existing text nodes
---
src/caoscrawler/xml_converter.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/src/caoscrawler/xml_converter.py b/src/caoscrawler/xml_converter.py
index fe10c738..908cd9ae 100644
--- a/src/caoscrawler/xml_converter.py
+++ b/src/caoscrawler/xml_converter.py
@@ -97,7 +97,10 @@ class XMLTagConverter(Converter):
vardict.update(m_tag.groupdict())
if "match_text" in self.definition:
- m_text = re.match(self.definition["match_text"], element.tag.text)
+ tagtext = element.tag.text
+ if element.tag.text is None:
+ tagtext = ""
+ m_text = re.match(self.definition["match_text"], tagtext, re.DOTALL)
if m_text is None:
return None
vardict.update(m_text.groupdict())
@@ -114,7 +117,6 @@ class XMLTagConverter(Converter):
matched_m_attrib = m_attrib
m_attrib_value = re.match(attrib_def_value, attr_value)
if m_attrib_value is None:
- breakpoint()
return None
matched_m_attrib_value = m_attrib_value
# TODO: How to deal with multiple matches?
--
GitLab