commit

utils.py

@@ -14,10 +14,10 @@ from googletrans import Translator
 from transformers import pipeline
 from PyPDF2 import PdfReader
 
-# AWS_ACCESS_KEY_ID = os.environ['AWS_ACCESS_KEY_ID']
-# AWS_SECRET_ACCESS_KEY = os.environ['AWS_SECRET_ACCESS_KEY']
-AWS_ACCESS_KEY_ID="AKIAQFXZMGHQYXKWUDWR"
-AWS_SECRET_ACCESS_KEY="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"
+AWS_ACCESS_KEY_ID = os.environ['AWS_ACCESS_KEY_ID']
+AWS_SECRET_ACCESS_KEY = os.environ['AWS_SECRET_ACCESS_KEY']
+# AWS_ACCESS_KEY_ID="AKIAQFXZMGHQYXKWUDWR"
+# AWS_SECRET_ACCESS_KEY="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"
 
 analyzer = pipeline("sentiment-analysis", model="ProsusAI/finbert")
 
@@ -65,23 +65,6 @@ def encode(content):
         text += line
     return text
 
-# def encode(content):
-#     """Encode Function"""
-#     text = ''
-#     for element in content:
-#         if isinstance(element, etree._Element):
-#             subelement = etree.tostring(element).decode()
-#             subpage = etree.HTML(subelement)
-#             tree = subpage.xpath('//text()')
-#             line = ''.join(translist(tree)).\
-#                 replace('\n','').replace('\t','').replace('\r','').replace('  ','').strip()
-#         else:
-#             line = element
-#         text += line
-#         index = text.find('打印本页')
-#         if index != -1:
-#           text = text[:index]
-
 def encode_content(content):
     """Encode Function"""
     text = ''
@@ -205,7 +188,7 @@ def crawl(url, article):
 def upsert_content(report):
     """Upsert the content records"""
     dynamodb = get_db_connection()
-    table = dynamodb.Table('article_test')
+    table = dynamodb.Table('article_china')
         # Define the item data
     item = {
         'id': str(report['id']),