Check whether our mirror packages are up to date.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

67 lines
2.3 KiB

from bs4 import BeautifulSoup
import requests
import re
import datefinder # another date finding library
from project import Project
from shared import CSC_MIRROR
class linuxmint(Project):
"""linuxmint class"""
def checker(directory_URL, file_name):
page = requests.get(directory_URL).text
file_index = page.find(file_name)
# print(page)
if file_index == -1:
return False
str_dates = re.findall(r'(\d{2}-\w{3}-\d{4} \d{2}:\d{2})|(\d{4}-\d{2}-\d{2} \d{2}:\d{2})', page[file_index:])
return list(datefinder.find_dates("".join(str_dates[0])))[0]
def scrape(cls, compare, folders, site1, site2, directory):
if cls.checker(site1+directory, "sha256sum.txt") != False:
# print (site1+directory)
# print (cls.checker(site1+directory, "sha256sum.txt"))
if cls.checker(site2+directory, "sha256sum.txt") != False:
# print (site2+directory)
# print (cls.checker(site2+directory, "sha256sum.txt"))
compare.append(cls.checker(site1+directory, "sha256sum.txt") <= cls.checker(site2+directory, "sha256sum.txt"))
# getting the request from url
r = requests.get(site1 + directory)
# converting the text
s = BeautifulSoup(r.text,"html.parser")
for i in s.find_all("a"): # for a href directories
href = i.attrs['href']
if href.endswith("/") and href != "../" and href != "/" and not href.startswith("/"):
dir_next = directory+href
# print(dir_next)
# calling it self
if dir_next not in folders:
cls.scrape(compare, folders, site1, site2, dir_next)
def check(cls, data, project, current_time):
"""Check if project packages are up-to-date"""
# lists
csc_url = CSC_MIRROR + data[project]["csc"] + data[project]["file"]
upstream_url = data[project]["upstream"] + data[project]["file"]
# calling function
cls.scrape(compare, folders, upstream_url, csc_url, "")
return all(compare)