alex/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-01-06 19:06:08 +10:00
Code Issues Packages Projects Releases Wiki Activity

continue renaming extractor to plugin, add plan for hook concurrency, add chrome kill helper script

Browse Source
This commit is contained in:
Nick Sweeting
2025-12-28 05:29:24 -08:00
parent d2e65cfd38
commit 4ccb0863bb
53 changed files with 456 additions and 493 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
archivebox/plugins/parse_netscape_urls/on_Snapshot__63_parse_netscape_urls.py
View File

@@ -22,7 +22,7 @@ from urllib.parse import urlparse
import rich_click as click
EXTRACTOR_NAME = 'parse_netscape_urls'
PLUGIN_NAME = 'parse_netscape_urls'
# Constants for timestamp epoch detection
UNIX_EPOCH = 0 # 1970-01-01 00:00:00 UTC
@@ -187,7 +187,7 @@ def main(url: str, snapshot_id: str = None):
entry = {
'type': 'Snapshot',
'url': unescape(bookmark_url),
'via_extractor': EXTRACTOR_NAME,
'plugin': PLUGIN_NAME,
}
if title:
entry['title'] = unescape(title)