common.py

+import json
 import sys
+import urllib.request
 
 if not sys.platform.startswith("win"):
     from getpass import getpass
@@ -21,3 +23,23 @@ def get_sessionid(service_name, cookie_key):
     if sid.startswith("s%3A"):
         return sid
     raise SystemExit(f"error: the supplied session id seems to be malformed")
+
+
+def print_block_heading(message):
+    separator = "======================================================================================================"
+    print(separator)
+    print(message)
+    print(separator)
+
+
+def check_accessibility(instance_url, session_id, cookie_key):
+    request_url = instance_url + '/me/'
+    headers = {"Cookie": f"{cookie_key}={session_id}"}
+
+    req = urllib.request.Request(request_url, headers=headers)
+    with urllib.request.urlopen(req) as response:
+        response_json = json.load(response)
+        if response_json["status"] != "ok":
+            raise SystemExit(f"Could not access protected resources at {request_url}. Make sure that the specified "
+                             f"cookie is correct. Aborting...")
+    print(f"Could access protected resources at {instance_url}. Proceeding...")

export_md/codimd_export.py

@@ -10,7 +10,7 @@ from urllib.parse import quote
 from urllib.request import Request, urlopen
 import sys
 
-from common import get_sessionid
+from common import get_sessionid, check_accessibility, print_block_heading
 
 
 def slurp(url, session_id):
@@ -31,15 +31,19 @@ def prepare_target_dir(pathname):
 
 
 def export_from_codimd(instance_url, session_id, export_to):
+    check_accessibility(instance_url, session_id, "connect.sid")
     """Retrieve CodiMD document history and try to download each document."""
+    print_block_heading(f"Trying to fetch history ({instance_url})")
     try:
         data = json.loads(slurp(f"{instance_url}/history", session_id))
     except OSError as error:
         raise SystemExit(f"error: couldn't access the /history endpoint: {error}")
     except json.JSONDecodeError as error:
         raise SystemExit(f"error: received malformed JSON: {error}")
+    print_block_heading(f"Preparing target directory ({export_to})")
     target_dir = prepare_target_dir(export_to)
     num_ok = num_fail = 0
+    print_block_heading(f"Accessing history and trying to fetch each document")
     for row in data["history"]:
         document_id = row["id"]
         document_url = f"{instance_url}/{quote(document_id)}"

import_md/hedgedoc_import.py

 #!/usr/bin/env python3
 import json
 from urllib.error import HTTPError
-from common import get_sessionid
+from common import get_sessionid, check_accessibility, print_block_heading
 from pathlib import Path
 import urllib.parse
 import urllib.request
 import os
-import subprocess
 from zipfile import ZipFile
 
 
-def check_accessibility(instance_url, session_id):
-    request_url = instance_url + '/me/'
-    headers = {"Cookie": f"connect.hedgeDoc.sid={session_id}"}
-
-    req = urllib.request.Request(request_url, headers=headers)
-    with urllib.request.urlopen(req) as response:
-        response_json = json.load(response)
-        if response_json["status"] != "ok":
-            raise SystemExit(f"Could not access protected resources at {request_url}. Make sure that the specified "
-                             f"cookie is correct. Aborting...")
-
-
 def import_single_document(instance_url, hedgedoc_free_url, content, session_id):
     sanitized_free_url = hedgedoc_free_url.replace(" ", "%20")
     request_url = instance_url + '/new/' + sanitized_free_url
@@ -33,17 +20,19 @@ def import_single_document(instance_url, hedgedoc_free_url, content, session_id)
         return response.url
 
 
-def check_archive_exists(archive_file):
-    if not os.path.exists(archive_file):
+def check_file_exists(file):
+    if not os.path.exists(file):
         raise SystemExit(
-            f"ERROR: File {archive_file} does not exist. Export your data from CodiMD and re-execute this script again!"
+            f"ERROR: File {file} does not exist. Export your data from CodiMD and re-execute this script again!"
             f" Aborting...")
+    print(f"Required file {file} exists. Proceeding...")
 
 
 def import_into_hedgedoc(instance_url, session_id, export_folder, archive_file):
-    print("Beginning import_md")
-    check_archive_exists(archive_file)
-    check_accessibility(instance_url, session_id)
+    print_block_heading(
+        f"Checking existence of archive file ({archive_file}) exists and authorization at {instance_url}")
+    check_file_exists(archive_file)
+    check_accessibility(instance_url, session_id, "connect.hedgeDoc.sid")
     # get exported history map
     with open(os.path.join(export_folder, "history.json")) as map_file:
         history_dictionary = json.load(map_file)
@@ -56,11 +45,11 @@ def import_into_hedgedoc(instance_url, session_id, export_folder, archive_file):
     # URLs to visit to make the new document available in the history
     urls_to_visit = []
 
-    iterate_over_archive(archive_file, instance_url, lookup_map, session_id, urls_to_visit)
+    process_archive_export(archive_file, instance_url, lookup_map, session_id, urls_to_visit)
     create_urls_to_visit_file("../hedgedoc_documents_to_visit.url", urls_to_visit)
 
 
-def iterate_over_archive(archive_file, instance_url, lookup_map, session_id, urls_to_visit):
+def process_archive_export(archive_file, instance_url, lookup_map, session_id, urls_to_visit):
     # iterate over files in archive
     with ZipFile(archive_file) as zf:
         print("Now scanning your provided archive file containing the documents you are the owner of")
@@ -76,21 +65,22 @@ def iterate_over_archive(archive_file, instance_url, lookup_map, session_id, url
 
             if document_title in lookup_map:
                 print(
-                    f"\tYou visited your own document \"{document_title}\".md) via the identifier/path " +
+                    f"You visited your own document \"{document_title}\".md) via the identifier/path " +
                     f"\"{lookup_map[document_title]}\"")
-                print(f"\tTrying to migrate this document and make it available under the already visited path")
+                print(f"Trying to migrate this document and make it available under the already visited path")
                 try:
                     new_url = import_single_document(instance_url, lookup_map[document_title], document_content,
                                                      session_id)
                     urls_to_visit.append(new_url)
-                    print(f"\tMigration was possible. New URL: {instance_url}/{lookup_map[document_title]}")
+                    print(f"Migration was possible. New URL: {instance_url}/{lookup_map[document_title]}")
                 except HTTPError as error:
                     if error.status == 409:
-                        print("\tATTENTION: Could not migrate document with the same path. Uploading anyways and "
+                        print("ATTENTION: Could not migrate document with the same path. Uploading anyways and "
                               "creating a new, random path")
                         new_url = import_single_document(instance_url, "", document_content, session_id)
                         print(f"New URL after document migration without migrating the URL/subpath: {new_url}")
                 urls_to_visit.append(new_url)
+                print()
             else:
                 print(f"According to your history, you did not visit \"{document_title}.md\" in the CodiMD "
                       "instance recently. Migrating the document and generating a new, random URL/path for it")
@@ -99,9 +89,11 @@ def iterate_over_archive(archive_file, instance_url, lookup_map, session_id, url
                 print(f"New URL after document migration with new, random URL/subpath: "
                       f"{generated_url}")
                 urls_to_visit.append(generated_url)
+                print()
 
 
 def create_urls_to_visit_file(filename, urls_to_visit):
+    print_block_heading("Creating file containg the URLs to visit")
     print(f"A new file {filename} will be created. It contains all URLs you need to visit in order to make the"
           f"migrated documents appear in your HedgeDoc history.")
     print("This can be automated by running the scripts in the directory \"history_scripts\"")

md-import-export.py

 from export_md.codimd_export import export_from_codimd
 from import_md.hedgedoc_import import import_into_hedgedoc
-from common import get_sessionid
+from common import get_sessionid, print_block_heading
 
 if __name__ == "__main__":
     export_folder = "codimd-documents"
     export_archive = "archive.zip"
+
+    print_block_heading("Beginning export from CodiMD...")
     export_from_codimd("http://localhost:3001", get_sessionid("CodiMD", "connect.sid"), export_folder)
+
+    print_block_heading("Beginning import to HedgeDoc...")
     import_into_hedgedoc("http://hedgedoc:3000", get_sessionid("HedgeDoc", "connect.hedgeDoc.sid"),
                          export_folder, export_archive)