mirror of
https://github.com/pirate/ArchiveBox.git
synced 2025-08-24 23:16:19 +02:00
dont remove query when uniquifying links
This commit is contained in:
2
util.py
2
util.py
@@ -33,7 +33,7 @@ without_query = lambda url: url.split('?', 1)[0]
|
|||||||
without_hash = lambda url: url.split('#', 1)[0]
|
without_hash = lambda url: url.split('#', 1)[0]
|
||||||
without_path = lambda url: url.split('/', 1)[0]
|
without_path = lambda url: url.split('/', 1)[0]
|
||||||
domain = lambda url: without_hash(without_query(without_path(without_scheme(url))))
|
domain = lambda url: without_hash(without_query(without_path(without_scheme(url))))
|
||||||
base_url = lambda url: without_query(without_scheme(url))
|
base_url = lambda url: without_scheme(url) # uniq base url used to dedupe links
|
||||||
|
|
||||||
short_ts = lambda ts: ts.split('.')[0]
|
short_ts = lambda ts: ts.split('.')[0]
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user