update

write_data_into_es/revise_data_from_es.py

@@ -41,50 +41,54 @@ search_body = {
 }
 es2_re = es2.search(index=target_index, doc_type=target_type,
                   body=search_body)
-q3_total = es2_re['hits']['total']
-write_into_scan = scan(client=es2,
-                       query=search_body,
-                       index=target_index,
-                       doc_type=target_type,
-                       scroll='5m',
-                       request_timeout=100
-                       )
-
-count = 0
-for one_scan in write_into_scan:
-    count = count + 1
-    line = one_scan['_source']
-    doc_id = one_scan['_id']
-    try:
-        if line['facevideo_is_assistant'] == 1:
-            line['facevideo_is_assistant'] = True
-        else:
-            line['facevideo_is_assistant'] = False
-    except:
-        pass
-
-    bulk_head = '{"index": {"_id":"%s"}}' % doc_id
-    data_str = json.dumps(line, ensure_ascii=False)
-
-    bulk_one_body = bulk_head + '\n' + data_str + '\n'
-    # print(bulk_one_body)
-    bulk_all_body += bulk_one_body
-    # break
-    if count%500 == 0:
-
-         eror_dic=es7.bulk(index=target_index,
-                body=bulk_all_body, request_timeout=200)
-         bulk_all_body=''
-         if eror_dic['errors'] is True:
-             print(eror_dic['items'])
-             print(bulk_all_body)
-         print(count)
-
-if bulk_all_body != '':
-     eror_dic = es7.bulk(body=bulk_all_body,
-                        index=target_index,
-                        request_timeout=200)
-     if eror_dic['errors'] is True:
-         print(eror_dic)
+es7_re = es7.search(index=target_index, doc_type=target_type,
+                  body=search_body)
 
-     bulk_all_body = ''
+#
+# q3_total = es2_re['hits']['total']
+# write_into_scan = scan(client=es2,
+#                        query=search_body,
+#                        index=target_index,
+#                        doc_type=target_type,
+#                        scroll='5m',
+#                        request_timeout=100
+#                        )
+#
+# count = 0
+# for one_scan in write_into_scan:
+#     count = count + 1
+#     line = one_scan['_source']
+#     doc_id = one_scan['_id']
+#     try:
+#         if line['facevideo_is_assistant'] == 1:
+#             line['facevideo_is_assistant'] = True
+#         else:
+#             line['facevideo_is_assistant'] = False
+#     except:
+#         pass
+#
+#     bulk_head = '{"index": {"_id":"%s"}}' % doc_id
+#     data_str = json.dumps(line, ensure_ascii=False)
+#
+#     bulk_one_body = bulk_head + '\n' + data_str + '\n'
+#     # print(bulk_one_body)
+#     bulk_all_body += bulk_one_body
+#     # break
+#     if count%500 == 0:
+#
+#          eror_dic=es7.bulk(index=target_index,
+#                 body=bulk_all_body, request_timeout=200)
+#          bulk_all_body=''
+#          if eror_dic['errors'] is True:
+#              print(eror_dic['items'])
+#              print(bulk_all_body)
+#          print(count)
+#
+# if bulk_all_body != '':
+#      eror_dic = es7.bulk(body=bulk_all_body,
+#                         index=target_index,
+#                         request_timeout=200)
+#      if eror_dic['errors'] is True:
+#          print(eror_dic)
+#
+#      bulk_all_body = ''