add timezone support, tons of CSS and layout improvements, more detailed snapshot admin form info, ability to sort by recently updated, better grid view styling, better table layouts, better dark mode support

archivebox/extractors/__init__.py

@@ -4,7 +4,7 @@ import os
 from pathlib import Path
 
 from typing import Optional, List, Iterable, Union
-from datetime import datetime
+from datetime import datetime, timezone
 from django.db.models import QuerySet
 
 from ..index.schema import Link
@@ -94,7 +94,7 @@ def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[s
         link = load_link_details(link, out_dir=out_dir)
         write_link_details(link, out_dir=out_dir, skip_sql_index=False)
         log_link_archiving_started(link, out_dir, is_new)
-        link = link.overwrite(updated=datetime.now())
+        link = link.overwrite(updated=datetime.now(timezone.utc))
         stats = {'skipped': 0, 'succeeded': 0, 'failed': 0}
 
         for method_name, should_run, method_function in ARCHIVE_METHODS:

archivebox/extractors/readability.py

@@ -92,6 +92,7 @@ def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEO
         result = run(cmd, cwd=out_dir, timeout=timeout)
         try:
             result_json = json.loads(result.stdout)
+            assert result_json and 'content' in result_json
         except json.JSONDecodeError:
             raise ArchiveError('Readability was not able to archive the page', result.stdout + result.stderr)
 

archivebox/extractors/wget.py

@@ -4,7 +4,7 @@ import re
 from pathlib import Path
 
 from typing import Optional
-from datetime import datetime
+from datetime import datetime, timezone
 
 from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
 from ..system import run, chmod_file
@@ -51,7 +51,7 @@ def save_wget(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
     if SAVE_WARC:
         warc_dir = out_dir / "warc"
         warc_dir.mkdir(exist_ok=True)
-        warc_path = warc_dir / str(int(datetime.now().timestamp()))
+        warc_path = warc_dir / str(int(datetime.now(timezone.utc).timestamp()))
 
     # WGET CLI Docs: https://www.gnu.org/software/wget/manual/wget.html
     output: ArchiveOutput = None