150 lines
4.3 KiB
Python
150 lines
4.3 KiB
Python
import requests, schedule, time, os
|
|
from bs4 import BeautifulSoup
|
|
from whatDomain import *
|
|
|
|
|
|
if os.environ["DEBMIRRORURL"]:
|
|
DEBMIRRORURL = os.environ["DEBMIRRORURL"]
|
|
else:
|
|
DEBMIRRORURL = "https://www.debian.org/mirror/list"
|
|
|
|
IPv4FILE = "/etc/debmirror/MirrorListV4"
|
|
IPv6FILE = "/etc/debmirror/MirrorListV6"
|
|
|
|
|
|
# Define EU and American countries
|
|
target_countries = set([
|
|
# Europe
|
|
"Austria", "Belgium", "Bulgaria", "Croatia", "Czech Republic", "Denmark",
|
|
"Estonia", "Finland", "France", "Germany", "Greece", "Hungary", "Iceland",
|
|
"Ireland", "Italy", "Latvia", "Lithuania", "Netherlands", "Norway", "Poland",
|
|
"Portugal", "Romania", "Slovakia", "Slovenia", "Spain", "Sweden", "Switzerland",
|
|
"United Kingdom", "Moldova",
|
|
# America
|
|
"Argentina", "Brazil", "Canada", "Chile", "Colombia", "Costa Rica", "Ecuador",
|
|
"Mexico", "Peru", "United States", "Uruguay", "Venezuela"
|
|
])
|
|
|
|
|
|
def sanitizeURL(inpurl: str):
|
|
if "https://" in inpurl:
|
|
outurl = inpurl[8:]
|
|
elif "http://" in inpurl:
|
|
outurl = inpurl[7:]
|
|
elif "http://" or "https://" not in url:
|
|
outurl = inpurl
|
|
else:
|
|
return -1
|
|
|
|
i = 0
|
|
for char in outurl:
|
|
i += 1
|
|
if char == "/":
|
|
outurl = outurl[:i]
|
|
|
|
if char == "/":
|
|
outurl = outurl[:-1]
|
|
return outurl
|
|
|
|
|
|
def getFreshData():
|
|
payload = requests.get(DEBMIRRORURL)
|
|
soup = BeautifulSoup(payload.content, "html.parser")
|
|
return soup
|
|
|
|
|
|
def sanitizeUrlsGodWhatTheFuckIsThis(SoupInput: BeautifulSoup):
|
|
|
|
outMirrorDict = {}
|
|
current_country = None
|
|
|
|
# Iterate through all table rows
|
|
for table in SoupInput.find_all("table"):
|
|
for row in table.find_all("tr"):
|
|
# Check for country name in a full-row header (<strong><big>)
|
|
strong = row.find("strong")
|
|
if strong:
|
|
country_name = strong.get_text(strip=True)
|
|
if country_name in target_countries:
|
|
current_country = country_name
|
|
else:
|
|
current_country = None
|
|
continue # move to next row
|
|
|
|
# Check for inline country name in first column
|
|
cols = row.find_all("td")
|
|
if len(cols) >= 2:
|
|
possible_country = cols[0].get_text(strip=True)
|
|
link_tag = cols[1].find("a", href=True)
|
|
if possible_country in target_countries:
|
|
current_country = possible_country
|
|
if current_country and link_tag:
|
|
url = link_tag['href']
|
|
if current_country not in outMirrorDict:
|
|
outMirrorDict[current_country] = []
|
|
outMirrorDict[current_country].append(url)
|
|
|
|
return outMirrorDict
|
|
|
|
def LeJob():
|
|
|
|
print("Starting lookup")
|
|
|
|
LeSoup = getFreshData()
|
|
|
|
LeMirrorDict = sanitizeUrlsGodWhatTheFuckIsThis(LeSoup)
|
|
|
|
# print(LeMirrorDict)
|
|
|
|
with open(IPv4FILE, "r",) as fR, open(IPv4FILE, "w",) as fW:
|
|
|
|
for key, urls in LeMirrorDict.items():
|
|
# print(urls)
|
|
if key in target_countries:
|
|
|
|
for url in urls:
|
|
# print(url)
|
|
|
|
if url not in fR:
|
|
|
|
goodurl = sanitizeURL(url)
|
|
# print(goodurl)
|
|
|
|
ip4Dict = ermWhatATheIpFromDomainYaCrazy(goodurl)
|
|
|
|
if ip4Dict == -1:
|
|
continue
|
|
|
|
for key, ip in ip4Dict.items():
|
|
# print(ip)
|
|
|
|
fW.write(ip + "/32" + "\n")
|
|
|
|
|
|
with open(IPv6FILE, "r",) as fR, open(IPv6FILE, "w",) as fW:
|
|
|
|
for key, urls in LeMirrorDict.items():
|
|
if key in target_countries:
|
|
|
|
for url in urls:
|
|
|
|
if url not in fR:
|
|
|
|
goodurl = sanitizeURL(url)
|
|
# print(goodurl)
|
|
|
|
ip6Dict = ermWhatAAAATheIpFromDomainYaCrazy(goodurl)
|
|
|
|
if ip6Dict == -1:
|
|
continue
|
|
|
|
for key, ip in ip6Dict.items():
|
|
# print(ip)
|
|
|
|
fW.write(ip + "/128" + "\n")
|
|
|
|
|
|
|
|
LeJob()
|
|
|
|
print("Done") |