notwa/respodns
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

use an alternative to the now-defunct Alexa top-1m

Browse source
This commit is contained in:
Connor Olding 2023-11-08 05:53:08 -08:00
parent e9a36ed397
commit c95b6ba0e1
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
respodns/top1m.py
View file

@ -1,4 +1,5 @@
urltop_default = "http://s3.amazonaws.com/alexa-static/top-1m.csv.zip"
# https://github.com/PeterDaveHello/top-1m-domains
urltop_default = "https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip"
csvfn_default = "top-1m.csv" # path within the zip file
one_week = 7 * 24 * 60 * 60 # in seconds
@ -51,5 +52,5 @@ def retrieve_top1m_entries(csv_fp="top-1m.csv"):
# for data that *should* be just a subset of ascii.
lines = uncomp.splitlines()
entries = [(lambda a: (int(a[0]), a[2]))(line.partition(","))
for line in lines]
for line in lines if line]
return entries