Last active
April 8, 2018 19:40
-
-
Save onlurking/0b0100893c89cff54fa2d72c44ad0b62 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from datetime import datetime | |
from collections import namedtuple | |
def normalize_date(ct, m = '00', s = '00'): | |
"""Return formated time_object with hour - 1, | |
and zero-filled minutes and seconds. | |
>>> normalize_date(datetime.strptime('Jun 1 2005 1:33PM', '%b %d %Y %I:%M%p')) | |
Date(year=2005, month=6, day=1, hour=12, minute='00', second='00') | |
string.format help: https://pyformat.info | |
""" | |
Date = namedtuple('Date', 'year month day hour minute second') | |
return Date(str(ct.year), | |
str(ct.month).zfill(2), | |
str(ct.day).zfill(2), | |
str((ct.hour - 1)).zfill(2), | |
str(m).zfill(2), | |
str(s).zfill(2)) | |
date = normalize_date(ct) # Date(year='2018', month='04', day='08', hour='15', minute='00', second='00') | |
def download_link(date): | |
base_url = "https://dumps.wikimedia.org/other/pageviews/" | |
download_url = base_url + ("{}/{}/pageviews-{}-{}.gz" | |
.format(date.year, | |
date.year + date.month, | |
date.year + date.month + date.day, | |
date.hour + date.minute + date.second)) | |
return download_url | |
ct = datetime.now() # get current time | |
for link in [download_link(normalize_date(ct, str(m).zfill(2), '00')) for m in range(0, 60)]: | |
print(link) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment