Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2025-02-16 21:38:33 +00:00
Code Issues Projects Releases Packages Wiki Activity

add more explanation about snapshot.save timestamp bump

Browse source
This commit is contained in:
Nick Sweeting 2021-02-17 13:34:46 -05:00
parent 265bcc0264
commit 084cf7ff51
1 changed files with 8 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
archivebox/extractors/__init__.py
View file

@ -114,7 +114,14 @@ def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[s
write_search_index(link=link, texts=result.index_texts) write_search_index(link=link, texts=result.index_texts)
ArchiveResult.objects.create(snapshot=snapshot, extractor=method_name, cmd=result.cmd, cmd_version=result.cmd_version, 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) output=result.output, pwd=result.pwd, start_ts=result.start_ts, end_ts=result.end_ts, status=result.status)
snapshot.save() # bump the updated time
# bump the updated time on the main Snapshot here, this is critical
# to be able to cache summaries of the ArchiveResults for a given
# snapshot without having to load all the results from the DB each time.
# (we use {Snapshot.id}-{Snapshot.updated} as the cache key and assume
# ArchiveResults are unchanged as long as the updated timestamp is unchanged)
snapshot.save()
else: else:
# print('{black} X {}{reset}'.format(method_name, **ANSI)) # print('{black} X {}{reset}'.format(method_name, **ANSI))
stats['skipped'] += 1 stats['skipped'] += 1