Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-22 20:23:12 +00:00
Code Issues Projects Releases Packages Wiki Activity

add note about saving timestamp strings independently

Browse source
This commit is contained in:
Nick Sweeting 2019-03-30 17:57:39 -04:00
parent 6d92784dbb
commit 880b425df6
1 changed files with 11 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
archivebox/util.py
View file

@ -373,6 +373,11 @@ def parse_date(date: Any) -> Optional[datetime]:
# anything from hours to decades, depending on which app, OS,
# and sytem time configuration was used for the original timestamp
# more info: https://github.com/pirate/ArchiveBox/issues/119
# Note: always always always store the original timestamp string
# somewhere indepentendly of the parsed datetime, so that later
# bugs dont repeatedly misparse and rewrite increasingly worse dates.
# the correct date can always be re-derived from the timestamp str
timestamp = float(date)
EARLIEST_POSSIBLE = 473403600.0 # 1985
@ -389,6 +394,12 @@ def parse_date(date: Any) -> Optional[datetime]:
# number is microseconds
return datetime.fromtimestamp(timestamp / (1000*1000))
else:
# continue to the end and raise a parsing failed error.
# we dont want to even attempt parsing timestamp strings that
# arent within these ranges
pass
if '-' in date:
try:
return datetime.fromisoformat(date)