Update document export helper script

server/handle_content_block.py

@@ -7,6 +7,9 @@ from books.models.custom_document import CustomDocument
 # from books.schema.nodes.content import ContentBlockNode
 from graphql_relay import to_global_id
 
+"""
+Script with helpers to make a CSV export of old document links to compare them to new document links
+"""
 
 columns = [
     "content_block_id",
@@ -38,6 +41,33 @@ def handle_all_content_blocks():
             handle_content_block(content_block=cb, contents=cb.contents, writer=writer)
 
 
+def handle_even_older_backup():  # helper to get backup from february and may 2023 and compare the old link with the old link from october
+    output_columns = columns + ["older", "older_s3"]
+    with open("old-links.csv", mode="r", encoding="utf-8") as file:
+        with open("even-older-links.csv", mode="w", encoding="utf-8") as destination:
+            reader = csv.DictReader(file)
+            writer = csv.DictWriter(destination, fieldnames=output_columns)
+            writer.writeheader()
+
+            for row in reader:
+                try:
+                    document_id = row["document_id"]
+                    if document_id == "":
+                        continue
+                    document = CustomDocument.objects.get(id=document_id)
+                    old_s3_url = format_link_s3(document)
+                    old_django_url = format_link_django(document)
+
+                    if row["old_s3"] == old_s3_url:
+                        continue
+                    row["older"] = old_django_url
+                    row["older_s3"] = old_s3_url
+
+                    writer.writerow(row)
+                except CustomDocument.DoesNotExist:
+                    continue
+
+
 def fill_csv_with_old_data():
     with open("source.csv", mode="r", encoding="utf-8") as file:
         with open("output.csv", mode="w", encoding="utf-8") as destination: