Update export helper

server/handle_content_block.py

@@ -1,4 +1,6 @@
 import csv
+
+from wagtail.blocks import StreamValue
 from books.models.contentblock import ContentBlock
 from books.models.custom_document import CustomDocument
 
@@ -10,32 +12,33 @@ columns = [
     "content_block_id",
     "document_id",
     "old",
+    "old_s3",
     "new",
     "module",
     "content_block",
 ]
 
 
-def format_link(document):
+def format_link_s3(document):
     return (
         f"https://skillbox-my-kv-prod.s3-eu-west-1.amazonaws.com{document.file.url[6:]}"
     )
 
 
-def format_link2(document):
+def format_link_django(document):
     return f"https://app.mykv.ch{document.url}"
 
 
 def handle_all_content_blocks():
     with open("source.csv", mode="w", encoding="utf-8") as file:
-        writer = csv.writer(file)
-        writer.writerow(columns)
+        writer = csv.DictWriter(file, fieldnames=columns)
+        writer.writeheader()
         # print("id,old link,new link,module,content block link")
         for cb in ContentBlock.objects.all():
-            handle_content_block(cb, writer)
+            handle_content_block(content_block=cb, contents=cb.contents, writer=writer)
 
 
-def read_csv():
+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:
             reader = csv.DictReader(file)
@@ -45,32 +48,12 @@ def read_csv():
             for row in reader:
                 try:
                     document = CustomDocument.objects.get(id=row["document_id"])
-                    old_url = format_link(document)
+                    old_django_url = format_link_django(document)
+                    old_s3_url = format_link_s3(document)
                     # print(document.file.url)
                     # print(row["new"])
-                    row["old"] = old_url
-                except ValueError:
-                    pass
-                except CustomDocument.DoesNotExist:
-                    print(f"Document with id {row['document_id']} does not exist")
-
-                writer.writerow(row)
-
-
-def read_csv_2():
-    with open("output.csv", mode="r", encoding="utf-8") as file:
-        with open("output2.csv", mode="w", encoding="utf-8") as destination:
-            reader = csv.DictReader(file)
-            writer = csv.DictWriter(destination, fieldnames=columns)
-            writer.writeheader()
-
-            for row in reader:
-                try:
-                    document = CustomDocument.objects.get(id=row["document_id"])
-                    new_url = format_link2(document)
-                    # print(document.file.url)
-                    # print(row["new"])
-                    row["new"] = new_url
+                    row["old"] = old_django_url
+                    row["old_s3"] = old_s3_url
                 except ValueError:
                     pass
                 except CustomDocument.DoesNotExist:
@@ -83,7 +66,7 @@ def print_document(document, content_block, writer):
     content_block_id = content_block.id
     try:
         # new_link = f"https://skillbox-my-kv-prod.s3-eu-west-1.amazonaws.com{document.file.url[6:]}"
-        new_link = format_link(document)
+        new_link = format_link_django(document)
         document_id = document.id
     except AttributeError:
         new_link = "missing document"
@@ -96,15 +79,31 @@ def print_document(document, content_block, writer):
     # content_block_url = f"https://app.mykv.ch/{content_block_path}"
     content_block_url = f"https://app.mykv.ch/content/{node_id}"
     # print(f"{id},,{new_link},{module_url}")
-    writer.writerow(
-        [content_block_id, document_id, "", new_link, module_url, content_block_url]
+    row = {
+        "content_block_id": content_block_id,
+        "document_id": document_id,
+        "old": "",
+        "old_s3": "",
+        "new": new_link,
+        "module": module_url,
+        "content_block": content_block_url,
+    }
+    writer.writerow(row)
+    # writer.writerow(
+    #     [content_block_id, document_id, "", new_link, module_url, content_block_url]
+    # )
+
+
+def handle_content_block(content_block: ContentBlock, contents: StreamValue, writer):
+    # contents: StreamValue
+    document_blocks = contents.blocks_by_name("cms_document_block")
+    instruction_block = contents.blocks_by_name("instruction")
+    solution_block = contents.blocks_by_name("solution")
+    list_item_blocks = contents.blocks_by_name("content_list_item")
+    for li in list_item_blocks:
+        handle_content_block(
+            contents=li.value, content_block=content_block, writer=writer
         )
-
-
-def handle_content_block(content_block: ContentBlock, writer):
-    document_blocks = content_block.contents.blocks_by_name("cms_document_block")
-    instruction_block = content_block.contents.blocks_by_name("instruction")
-    solution_block = content_block.contents.blocks_by_name("solution")
     for db in document_blocks:
         document = db.value
         print_document(document, content_block, writer)