From 6405185cd4136b04b45b3b9d756fdd5d38405f07 Mon Sep 17 00:00:00 2001 From: gilad_ilsar Date: Thu, 22 Sep 2016 14:53:42 +0300 Subject: updates --- readers/xml_reader.py | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'readers') diff --git a/readers/xml_reader.py b/readers/xml_reader.py index 3e630cb..ec2c696 100644 --- a/readers/xml_reader.py +++ b/readers/xml_reader.py @@ -26,12 +26,18 @@ def read_file(path, element_key): if element_key in element.tag: #enter the processing here record_counter += 1 + + for field in element: + print(field.tag, field.attrib) + #cleaned element is a tree - cleaned_element = parsers.INLXmlParser(element).clearxml() + inl_parser = parsers.INLXmlParser(element) + cleaned_element = inl_parser.clearxml() entity = inl_factory.get_entity(cleaned_element) #test print the entity - entity.print_entity() + if entity != None: + entity.print_entity() #TODO analys and upload the entity @@ -43,4 +49,4 @@ def read_file(path, element_key): if __name__ == '__main__': - read_file(r"../../NLI-nnl10.xml", 'record') + read_file(r"C:/Users/Ilsar/Documents/datahack/NLI-nnl10.xml", 'record') -- cgit v1.2.3