Implement basic importer

This commit is contained in:
Sascha Ißbrücker 2019-06-29 08:42:54 +02:00
parent 451a049d46
commit 9eefd479c6
4 changed files with 76 additions and 0 deletions

1
.gitignore vendored
View file

@ -159,3 +159,4 @@ venv.bak/
.mypy_cache/
polls
tmp

View file

@ -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>

View file

@ -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)

View file

@ -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()