mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-17 08:34:26 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: All parsers return snapshot instead of link

Browse source
This commit is contained in:
Cristian 2021-01-04 09:31:14 -05:00
parent 15d88be229
commit b8efaa5b6a
11 changed files with 72 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

12
archivebox/parsers/netscape_html.py
View file

@ -6,7 +6,8 @@ import re
from typing import IO, Iterable
from datetime import datetime
from ..index.schema import Link
from django.db.models imort Model
from ..util import (
htmldecode,
enforce_types,
@ -14,8 +15,9 @@ from ..util import (
@enforce_types
def parse_netscape_html_export(html_file: IO[str], **_kwargs) -> Iterable[Link]:
def parse_netscape_html_export(html_file: IO[str], **_kwargs) -> Iterable[Model]:
"""Parse netscape-format bookmarks export files (produced by all browsers)"""
from core.models import Snapshot
html_file.seek(0)
pattern = re.compile("<a href=\"(.+?)\" add_date=\"(\\d+)\"[^>]*>(.+)</a>", re.UNICODE | re.IGNORECASE)
@ -29,11 +31,11 @@ def parse_netscape_html_export(html_file: IO[str], **_kwargs) -> Iterable[Link]:
time = datetime.fromtimestamp(float(match.group(2)))
title = match.group(3).strip()
yield Link(
yield Snapshot(
url=htmldecode(url),
timestamp=str(time.timestamp()),
title=htmldecode(title) or None,
tags=None,
sources=[html_file.name],
#tags=None,
#sources=[html_file.name],
)