From 9eefd479c60d13bfbd0e06777823bda897830e80 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sascha=20I=C3=9Fbr=C3=BCcker?=
 <sascha.issbruecker@byteagenten.de>
Date: Sat, 29 Jun 2019 08:42:54 +0200
Subject: [PATCH] Implement basic importer

---
 .gitignore                                    |  1 +
 .idea/inspectionProfiles/Project_Default.xml  | 12 ++++++
 .../management/commands/import_netscape.py    | 21 ++++++++++
 bookmarks/services/importer.py                | 42 +++++++++++++++++++
 4 files changed, 76 insertions(+)
 create mode 100644 .idea/inspectionProfiles/Project_Default.xml
 create mode 100644 bookmarks/management/commands/import_netscape.py
 create mode 100644 bookmarks/services/importer.py

diff --git a/.gitignore b/.gitignore
index 459b73b..620cdae 100644
--- a/.gitignore
+++ b/.gitignore
@@ -159,3 +159,4 @@ venv.bak/
 .mypy_cache/
 
 polls
+tmp
diff --git a/.idea/inspectionProfiles/Project_Default.xml b/.idea/inspectionProfiles/Project_Default.xml
new file mode 100644
index 0000000..cbb35d0
--- /dev/null
+++ b/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,12 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPep8Inspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="E402" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file
diff --git a/bookmarks/management/commands/import_netscape.py b/bookmarks/management/commands/import_netscape.py
new file mode 100644
index 0000000..5691584
--- /dev/null
+++ b/bookmarks/management/commands/import_netscape.py
@@ -0,0 +1,21 @@
+from django.contrib.auth.models import User
+from django.core.management.base import BaseCommand
+
+from bookmarks.services.importer import import_netscape_html
+
+
+class Command(BaseCommand):
+    help = 'Import Netscape HTML bookmark file'
+
+    def add_arguments(self, parser):
+        parser.add_argument('file', type=str, help='Path to file')
+        parser.add_argument('user', type=str, help='Name of the user for which to import')
+
+    def handle(self, *args, **kwargs):
+        filepath = kwargs['file']
+        username = kwargs['user']
+        with open(filepath) as html_file:
+            html = html_file.read()
+        user = User.objects.get(username=username)
+
+        import_netscape_html(html, user)
diff --git a/bookmarks/services/importer.py b/bookmarks/services/importer.py
new file mode 100644
index 0000000..d39d9b6
--- /dev/null
+++ b/bookmarks/services/importer.py
@@ -0,0 +1,42 @@
+from datetime import datetime
+
+from bs4 import BeautifulSoup, Tag
+from django.contrib.auth.models import User
+
+from bookmarks.models import Bookmark
+
+
+def import_netscape_html(html: str, user: User):
+    soup = BeautifulSoup(html, 'html.parser')
+
+    bookmark_tags = soup.find_all('dt')
+
+    for bookmark_tag in bookmark_tags:
+        _import_bookmark_tag(bookmark_tag, user)
+
+
+def _import_bookmark_tag(bookmark_tag: Tag, user: User):
+    link_tag = bookmark_tag.a
+
+    if link_tag is None:
+        return
+
+    # Either modify existing bookmark for the URL or create new one
+    url = link_tag['href']
+    bookmark = _get_or_create_bookmark(url, user)
+
+    bookmark.url = url
+    bookmark.date_added = datetime.utcfromtimestamp(int(link_tag['add_date']))
+    bookmark.date_modified = bookmark.date_added
+    bookmark.unread = link_tag['toread'] == '1'
+    bookmark.title = link_tag.string
+    bookmark.owner = user
+
+    bookmark.save()
+
+
+def _get_or_create_bookmark(url: str, user: User):
+    try:
+        return Bookmark.objects.get(url=url, owner=user)
+    except Bookmark.DoesNotExist:
+        return Bookmark()