Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-10 06:34:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

feat: Create ArchiveResult after finishing an extractor process

Browse source
This commit is contained in:
Cristian 2020-11-04 11:22:55 -05:00
parent b3e0400bc0
commit 4484491fb7
2 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
archivebox/core/utils.py
View file

@ -1,8 +1,6 @@
from pathlib import Path
from django.utils.html import format_html
from core.models import Snapshot, ArchiveResult, EXTRACTORS
from core.models import Snapshot, EXTRACTORS
def get_icons(snapshot: Snapshot) -> str:
@ -70,4 +68,4 @@ def get_icons(snapshot: Snapshot) -> str:
# *link_tuple(link, 'git_path')[:2], any((out_dir / canon['git_path']).glob('*')),
# canon['archive_org_path'], (out_dir / 'archive.org.txt').exists(),
# )
#
#

7
archivebox/extractors/__init__.py
View file

@ -65,6 +65,10 @@ def ignore_methods(to_ignore: List[str]):
def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[str]]=None, out_dir: Optional[Path]=None, skip_index: bool=False) -> Link:
"""download the DOM, PDF, and a screenshot into a folder named after the link's timestamp"""
# TODO: Remove when the input is changed to be a snapshot. Suboptimal approach.
from core.models import Snapshot, ArchiveResult
snapshot = Snapshot.objects.get(url=link.url)
ARCHIVE_METHODS = get_default_archive_methods()
if methods:
@ -99,6 +103,9 @@ def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[s
stats[result.status] += 1
log_archive_method_finished(result)
ArchiveResult.objects.create(snapshot=snapshot, extractor=method_name, cmd=result.cmd, cmd_version=result.cmd_version,
output=result.output, pwd=result.pwd, start_ts=result.start_ts, end_ts=result.end_ts, status=result.status)
else:
# print('{black} X {}{reset}'.format(method_name, **ANSI))
stats['skipped'] += 1