Commit 6ef6aaa2 authored by jvoisin's avatar jvoisin

Improve a bit get_meta for libreoffice files

parent 6cc034e8
......@@ -384,7 +384,7 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
return {}
with open(full_path, encoding='utf-8') as f:
results = re.findall(r"<((?:meta|dc|cp).+?)>(.+)</\1>",, re.I|re.M)
results = re.findall(r"<((?:meta|dc|cp).+?)[^>]*>(.+)</\1>",, re.I|re.M)
return {k:v for (k, v) in results}
except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file
# We didn't manage to parse the xml file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment