From 3615e3968baa5a464a2725e280a7e0f89e3428cf Mon Sep 17 00:00:00 2001
From: gilad_ilsar <gandismidas1>
Date: Thu, 22 Sep 2016 16:34:57 +0300
Subject: parser into csv

---
 readers/xml_reader.py | 67 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 28 deletions(-)

(limited to 'readers/xml_reader.py')

diff --git a/readers/xml_reader.py b/readers/xml_reader.py
index ec2c696..2aaf8c6 100644
--- a/readers/xml_reader.py
+++ b/readers/xml_reader.py
@@ -1,4 +1,6 @@
 #  from __future__ import absolute_import
+import json
+import csv
 import parsers, factories
 
 try:
@@ -6,6 +8,7 @@ try:
 except ImportError:
     import xml.etree.ElementTree as ET
 
+CSV_FIELDS = ["name", "biodata", "comments"]
 
 def read_file(path, element_key):
     # get an iterable
@@ -20,33 +23,41 @@ def read_file(path, element_key):
 
     #the factory
     inl_factory = factories.INLFactory()
-
-    for event, element in context:
-        if 'end' in event:
-            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
-                inl_parser = parsers.INLXmlParser(element)
-                cleaned_element = inl_parser.clearxml()
-                entity = inl_factory.get_entity(cleaned_element)
-
-                #test print the entity
-                if entity != None:
-                    entity.print_entity()
-
-
-                #TODO analys and upload the entity
-
-
-                # import pdb; pdb.set_trace()
-                print(record_counter, cleaned_element.getroot().tag, '@@@', cleaned_element.getroot().attrib, '@@@', cleaned_element.getroot().text)
-            element.clear()
-
-
+    with open('out.csv', 'w', encoding='utf8') as f:
+        writer = csv.DictWriter(f, CSV_FIELDS)
+        writer.writeheader()
+        f667 = open("667.txt", 'w', encoding="utf8")
+        f678 = open("678.txt", 'w', encoding="utf8")
+        for event, element in context:
+            if 'end' in event:
+                if element_key in element.tag:
+                    #enter the processing here
+                    record_counter += 1
+
+                    #cleaned element is a tree
+                    inl_parser = parsers.INLXmlParser(element)
+                    cleaned_element = inl_parser.clearxml()
+                    entity = inl_factory.get_entity(cleaned_element)
+
+
+                    #test print the entity
+                    if entity != None:
+                        json_entity = entity.to_json()
+                        print(json_entity)
+                        writer.writerow({'name': entity.name, 'biodata': entity.bio_data, 'comments': json.dumps(entity.comments_list, ensure_ascii=False)})
+                        # json.dump(entity.comments_list, f667, indent=2, ensure_ascii=False)
+                        # json.dump(entity.bio_data, f678, indent=2, ensure_ascii=False)
+
+                        # entity.print_entity()
+
+
+                    #TODO analys and upload the entity
+
+
+                    # import pdb; pdb.set_trace()
+                    #print(record_counter, cleaned_element.getroot().tag, '@@@', cleaned_element.getroot().attrib, '@@@', cleaned_element.getroot().text)
+                    element.clear()
+        f667.close()
+        f678.close()
 if __name__ == '__main__':
     read_file(r"C:/Users/Ilsar/Documents/datahack/NLI-nnl10.xml", 'record')
-- 
cgit v1.2.3